Remote Sensing

35 pages, 3324 KB

Open AccessArticle

POCA-Lite: A Lightweight Change-Detection Architecture with Geometry-Aware Auxiliary Supervision and Feedback Fusion

by Yongqi Shi, Ruopeng Yang, Bo Huang, Zhaoyang Gu, Yiwei Lu, Changsheng Yin, Yongqi Wen and Yihao Zhong

Remote Sens. 2026, 18(10), 1673; https://doi.org/10.3390/rs18101673 - 21 May 2026

Viewed by 365

Abstract

Building change detection from bi-temporal remote-sensing imagery underpins urban planning, infrastructure monitoring, and disaster assessment. Existing deep-learning methods achieve high accuracy but rely on large parameter counts, while pixel-level supervision provides limited boundary guidance. We propose POCA-lite, a lightweight encoder–decoder with an inference-coupled [...] Read more.

Building change detection from bi-temporal remote-sensing imagery underpins urban planning, infrastructure monitoring, and disaster assessment. Existing deep-learning methods achieve high accuracy but rely on large parameter counts, while pixel-level supervision provides limited boundary guidance. We propose POCA-lite, a lightweight encoder–decoder with an inference-coupled geometry branch: three geometric prediction heads—distance transform, boundary, and center heatmap—whose outputs are fused back into the decoder via a feedback pathway active at both training and inference. On the LEVIR-CD benchmark under a unified retraining protocol, multi-seed evaluation shows that POCA-lite matches SNUNet in mean F1 while using 47% fewer parameters and 53% fewer FLOPs. Boundary F1 improves by 9.22 pp over the no-geometry baseline. Decomposition ablations reveal two complementary improvement sources: geometric supervision alone recovers 85% of the total gain, while the feedback fusion pathway recovers 92%; their combination achieves the full result. Geometry-aware targets outperform a generic multitask control. Cross-architecture transfer to SNUNet yields +1.06 pp F1. However, cross-dataset evaluation on WHU-CD shows that the method underperforms SNUNet on dense urban morphology, and zero-shot cross-dataset transfer is not established. These results indicate that inference-coupled geometric supervision is effective for lightweight, boundary-sensitive change detection on domains with well-separated building morphology, but its applicability is scope-bounded. Full article

► Show Figures

Figure 1

20 pages, 3068 KB

Open AccessArticle

Backpack LiDAR Supports Biotope-Scale Assessment of Structure, Maintenance, and Net Carbon Budget in Urban Park Plant Communities

by Zixin Zhao, Yuxi Yang, Yumeng Ma, Xiaoxu Zhang, Ling Qiu and Tian Gao

Remote Sens. 2026, 18(10), 1672; https://doi.org/10.3390/rs18101672 - 21 May 2026

Viewed by 237

Abstract

Urban parks are often regarded as carbon sinks, yet their net carbon performance depends on the balance between vegetation carbon uptake and maintenance-related emissions, as well as the accurate representation of within-park spatial heterogeneity. This study used backpack LiDAR, field vegetation surveys, and [...] Read more.

Urban parks are often regarded as carbon sinks, yet their net carbon performance depends on the balance between vegetation carbon uptake and maintenance-related emissions, as well as the accurate representation of within-park spatial heterogeneity. This study used backpack LiDAR, field vegetation surveys, and maintenance inventories to quantify annual carbon sequestration, maintenance emissions, and net carbon budget in 44 plots covering nine biotope types across 16 parks in central Xianyang, China. A four-level biotope classification incorporating canopy openness, ground cover, tree composition, and vertical stratification was applied to link LiDAR-derived three-dimensional structure with ecological-unit-level carbon accounting. Carbon sequestration and net carbon budget differed significantly among biotopes, whereas maintenance emissions did not. Closed broadleaved single-layer forest showed the highest carbon sequestration density (0.772 kg C m⁻²), while hard-surfaced partly closed broadleaved single-layer forest showed the lowest value (0.132 kg C m⁻²). Closed woody biotopes functioned as strong carbon sinks, partly closed biotopes as weak sinks, and the partly open short-grass biotope was the only carbon source. Three-dimensional green volume density was the strongest positive predictor of net carbon budget (β = 0.417, p = 0.032), followed by stem density (β = 0.276, p = 0.048), whereas irrigation-related emissions showed a significant negative coefficient (β = −0.276, p = 0.021). Carbon sequestration explained more variation in net carbon budget than maintenance emissions (adjusted R² = 0.409 vs. 0.134). These findings suggest that backpack LiDAR can support fine-scale identification of priority carbon-sink units in urban parks and that low-carbon park management should prioritize three-dimensional woody vegetation structure while reducing high-input irrigation where feasible. Full article

► Show Figures

Figure 1

42 pages, 5308 KB

Open AccessArticle

ChangeVLM: A Language-Guided Semantic Alignment Framework for Binary Remote Sensing Change Detection

by Dongxu Li, Peng Chu, Chen Yang, Zhen Wang and Chuanjin Dai

Remote Sens. 2026, 18(10), 1671; https://doi.org/10.3390/rs18101671 - 21 May 2026

Viewed by 307

Abstract

Against the backdrop of complex features and spectral heterogeneity in high-resolution remote sensing imagery, traditional methods suffer from insufficient semantic understanding, while existing vision–language change detection models face low efficiency, poor spatial localization, and decoupled detection–description pipelines. To overcome these limitations, this paper [...] Read more.

Against the backdrop of complex features and spectral heterogeneity in high-resolution remote sensing imagery, traditional methods suffer from insufficient semantic understanding, while existing vision–language change detection models face low efficiency, poor spatial localization, and decoupled detection–description pipelines. To overcome these limitations, this paper proposes ChangeVLM, a language-guided semantic alignment framework for binary remote sensing change detection, enabling end-to-end, prompt-free, highly efficient, and interpretable change detection. Its key advantages include the following, (1) Higher detection accuracy with F1 scores of 91.52%, 83.56%, and 75.29% on LEVIR-CD, SYSU-ChangeDet, and HRCUS datasets, outperforming 18 state-of-the-art methods. (2) Stronger edge integrity and small-object detection capability; (3) practical deployment efficiency: the end-to-end FLOPs is 560.7G. Additionally, under an optimized inference setting with pre-extracted features, the effective computation can be reduced to 13.05G. (4) Language-guided semantic regularization to enhance visual discrimination, without requiring external text prompts. The Asymmetric Fusion Module (AFM), lightweight ChangeHead, and Change-Aware Cross-Modal Fusion Module (CACMF) jointly enhance spatial precision, efficiency, and interpretability. Extensive experiments validate that ChangeVLM achieves a superior accuracy–efficiency trade-off. This method provides an effective, deployable solution for high-resolution remote sensing binary change detection, where the language branch acts only as a regularization signal. Full article

(This article belongs to the Special Issue Foundation Model-Based Multi-Modal Data Fusion in Remote Sensing)

► Show Figures

Figure 1

24 pages, 2264 KB

Open AccessArticle

From Generic to Adaptive: Similarity-Adaptive Receptive-Field Cross DETR for Remote-Sensing Object Detection

by Chenyu Lin, Yunzhan Fu, Hang Xu, Xuyang Teng and Tingyu Wang

Remote Sens. 2026, 18(10), 1670; https://doi.org/10.3390/rs18101670 - 21 May 2026

Viewed by 273

Abstract

Object detection in optical remote sensing imagery faces persistent challenges from severe instance overlap, extreme spatial density, and motion or atmospheric blur. These degradations cause conventional detectors to over-mix neighboring instance features and fail to separate closely packed objects. To address these limitations, [...] Read more.

Object detection in optical remote sensing imagery faces persistent challenges from severe instance overlap, extreme spatial density, and motion or atmospheric blur. These degradations cause conventional detectors to over-mix neighboring instance features and fail to separate closely packed objects. To address these limitations, we propose SARC-DETR, a detection framework that augments the RT-DETR architecture with two complementary plug-in modules: Similarity Adaptive Convolution (SAC) and Receptive Field Cross Convolution (RCC). SAC introduces a reproducing-kernel-Hilbert-space (RKHS) motivated similarity gate that selectively suppresses responses inconsistent with local feature prototypes, thereby reducing cross-instance interference in overlapped and blurred regions. RCC constructs a large directional receptive field through orthogonal strip-based aggregation and content-adaptive fusion, enabling efficient long-range context capture without quadratic complexity overhead. Both modules can be integrated into existing DETR-style detectors without modifying the detection head or training protocol. On VisDrone2019-DET, SARC-DETR improves

{AP}^{val}

from 29.7 to 34.8,

{AP}_{50}^{val}

from 49.5 to 56.2, and

{AP}_{S}^{val}

from 19.2 to 24.8. On DIOR, AP rises from 57.9 to 68.4, and on NWPU VHR-10, from 44.4 to 66.5, demonstrating robust cross-dataset generalization. After structural reparameterization, the additional overhead is less than 0.75 M parameters and 0.36 G FLOPs, confirming deployment suitability for UAV and satellite-based remote sensing applications. Full article

(This article belongs to the Special Issue Deep Learning-Based Interpretation and Processing of Remote Sensing Images)

► Show Figures

Figure 1

31 pages, 4124 KB

Open AccessArticle

Evaluating Multi-Source Soil Moisture Products for Root-Zone Soil Moisture Representation in Yunnan, China

by Ruijie Wang, Gang Zhou, Chao Li and Siyu Ma

Remote Sens. 2026, 18(10), 1669; https://doi.org/10.3390/rs18101669 - 21 May 2026

Viewed by 395

Abstract

Root zone soil moisture (RZSM) is critical for understanding hydrological processes and monitoring agricultural drought, yet its accurate representation remains challenging in topographically complex regions. Using 40 cm in situ SM observations from 19 ground stations in Yunnan Province, China, during 2008–2012 as [...] Read more.

Root zone soil moisture (RZSM) is critical for understanding hydrological processes and monitoring agricultural drought, yet its accurate representation remains challenging in topographically complex regions. Using 40 cm in situ SM observations from 19 ground stations in Yunnan Province, China, during 2008–2012 as the reference, this study systematically evaluated the performance of five widely used multi-source soil moisture (SM) products and their different depth layers, including ERA5-Land, GLDAS Noah, GLEAM, ASCAT H141, and CCI SM. A CCI-derived RZSM proxy generated by exponential filtering, hereafter CCI RZSM, was also included. Product performance was assessed using original and deseasonalized time series, and the effects of land-use type, long-term wetness background, and short-term dry conditions on product performance were explicitly examined. The results showed that the intermediate and deeper layers of ERA5-Land and ASCAT H141, especially the 7–28 cm layers, exhibited better performance in capturing RZSM dynamics, achieving a favorable balance among temporal correlation (r > 0.6), random error and systematic bias. Surface-layer products showed limited direct representativeness, and effective RZSM representativeness differed substantially among nominal product layers. Deseasonalization showed that original-series correlations were partly supported by the shared seasonal wet–dry cycle, whereas most products had weaker skill in tracking non-seasonal RZSM anomalies. Environmental background substantially modulated error structures: stronger positive Bias generally occurred at drier stations, Grassland showed higher positive Bias, Cropland showed greater dispersion, and Forest displayed relatively balanced performance. Under dry conditions, temporal correlations declined for nearly all products, whereas increases in random error were mainly concentrated in surface layers. Exponential filtering improved the temporal consistency of CCI SM in representing RZSM, but the filtering with a fixed characteristic time parameter (T) performed worse than filtering with station-optimized T, indicating limited generalizability in ungauged regions. Overall, RZSM representativeness in Yunnan is jointly controlled by product structure, environmental background, and wet–dry conditions. ERA5-Land and ASCAT H141 intermediate-to-deep layers are therefore more suitable for RZSM anomaly and drought applications in Yunnan Province. Full article

(This article belongs to the Special Issue Multi-Source Remote Sensing Data in Hydrology and Geophysical Processes)

► Show Figures

Figure 1

27 pages, 17545 KB

Open AccessArticle

Three-Dimensional Deformation Field Inversion Based on Fused Monitoring Data of GNSS and InSAR: A Case Study of Jinchuan No. 2 Mining Area

by Jie Guo, Yewei Song, Gaofeng Wu, Xin Hui, Fengshan Ma and Guang Li

Remote Sens. 2026, 18(10), 1668; https://doi.org/10.3390/rs18101668 - 21 May 2026

Viewed by 228

Abstract

Surface rock movement can lead to geological or environmental problems such as surface subsidence, ground fissure development, and deformation of engineering structures, and its evolution process exhibits significant spatiotemporal heterogeneity. Therefore, conducting high-precision, spatiotemporally continuous monitoring of surface deformation is of great significance [...] Read more.

Surface rock movement can lead to geological or environmental problems such as surface subsidence, ground fissure development, and deformation of engineering structures, and its evolution process exhibits significant spatiotemporal heterogeneity. Therefore, conducting high-precision, spatiotemporally continuous monitoring of surface deformation is of great significance for revealing subsidence mechanisms, assessing potential risks, and guiding disaster reduction decisions. GNSS and InSAR have become mainstream methods for monitoring surface deformation, but they still have limitations in terms of spatial sparsity, 3D deformation inversion capability, and data gaps in areas of strong deformation. To address these issues, this paper takes the Jinchuan copper-nickel mine’s No. 2 mining area as the research object and comprehensively utilizes multi-source monitoring data from GNSS and InSAR to construct a joint inversion model of the surface 3D deformation field based on posterior variance component estimation, achieving adaptive optimization of weight allocation and collaborative solution of 3D deformation. To address the issue of InSAR decorrelation in areas of strong deformation, which leads to missing deformation information, a fitting and estimation approach was applied to supplement six decorrelated points that spatially coincide with GNSS stations. These points are located in key deformation areas, and their reconstruction effectively improves the completeness and reliability of the deformation field in critical regions. Based on this, an automated solution process for the fusion model is implemented using MATLAB R2022b, and the joint inversion yields spatiotemporally continuous 3D deformation fields in the northward, eastward, and vertical directions. The results show that compared with traditional monitoring methods, the proposed fusion model exhibits higher inversion accuracy and stability under different InSAR technology conditions, effectively suppressing the impact of single data source errors on the overall solution results. Among them, SBAS-InSAR shows slightly higher accuracy in the vertical direction, while PS-InSAR achieves higher accuracy in the planar direction, as indicated by lower RMSE and MAE values. The research results improve the accuracy and reliability of surface deformation monitoring in mining areas, providing important technical support for safe mining and refined management. Full article

(This article belongs to the Special Issue Application of Advanced Remote Sensing Techniques in Mining Areas)

► Show Figures

Figure 1

23 pages, 27232 KB

Open AccessArticle

WFSCA-YOLO: Robust Object Detection for Terrestrial Optical Sensing Under Atmospheric Degradation via a Wavelet-Driven Frequency–Spatial Co-Awareness Framework

by Jiabao Yan, Qihang Xu, Zhian Zheng, Xian-Hua Han, Junjie Zhu and Yanhua Lin

Remote Sens. 2026, 18(10), 1667; https://doi.org/10.3390/rs18101667 - 21 May 2026

Viewed by 337

Abstract

Optical object detection under fog-induced atmospheric degradation remains a challenging problem for terrestrial sensing and monitoring systems. Atmospheric scattering reduces image contrast and attenuates high-frequency edge and texture features that are important for precise object localization, while standard downsampling in convolutional neural networks [...] Read more.

Optical object detection under fog-induced atmospheric degradation remains a challenging problem for terrestrial sensing and monitoring systems. Atmospheric scattering reduces image contrast and attenuates high-frequency edge and texture features that are important for precise object localization, while standard downsampling in convolutional neural networks (CNNs) further amplifies this information loss during feature extraction. Existing spatial-domain methods largely improve pixel appearance or feature refinement without explicitly preserving fog-weakened high-frequency edge and texture features during feature extraction. To address this issue, we propose WFSCA-YOLO, a frequency-aware and feature-preserving detection framework with cross-domain fusion between frequency-domain details and spatial semantic responses. The framework introduces the Wavelet-driven Frequency–spatial Co-awareness Block (WFSCA-Block) into YOLOv8, where the Discrete Wavelet Transform (DWT) is used to decompose feature maps into multi-directional high-frequency subbands and preserve high-frequency edge and texture features degraded by atmospheric scattering. A Cross-Domain Feature Selector (CDFS) is further designed to adaptively recalibrate the fusion of frequency-domain details and spatial semantic responses under varying visibility conditions. Experiments on synthetic and real-world degraded optical benchmarks from near-ground scenes, namely Foggy Cityscapes and RTTS, show that WFSCA-YOLO consistently outperforms representative state-of-the-art methods, achieving 50.3% mAP@50 on Foggy Cityscapes (2.1 percentage points above the baseline) and a mean mAP@50 of 79.28% on RTTS over three independent runs. Under a unified FP32 batch-1 inference benchmark, WFSCA-YOLO runs at 134.76 FPS on an RTX 4090D, indicating real-time capability with only a slight latency increase relative to the YOLOv8-s baseline. These results indicate that preserving high-frequency edge and texture features is an effective strategy for robust perception under degraded visibility and offers practical potential for terrestrial sensing and monitoring platforms. Full article

(This article belongs to the Section Engineering Remote Sensing)

► Show Figures

Figure 1

24 pages, 62422 KB

Open AccessArticle

GDBNet: A Three-Branch Semantic Segmentation Network Integrating CNN and Transformer for Land Cover Classification in Ski Resorts

by Zhiwei Yi, Lingjia Gu, Ruifei Zhu, Junwei Tian and He Mi

Remote Sens. 2026, 18(10), 1666; https://doi.org/10.3390/rs18101666 - 21 May 2026

Viewed by 238

Abstract

As a critical component of ice-snow tourism, land cover classification for ski resorts is crucial to ice-snow resource management. However, there is currently a scarcity of datasets and methods capable of high-precision mapping for such fine-grained scenarios. Although Transformers with long-sequence interactions and [...] Read more.

As a critical component of ice-snow tourism, land cover classification for ski resorts is crucial to ice-snow resource management. However, there is currently a scarcity of datasets and methods capable of high-precision mapping for such fine-grained scenarios. Although Transformers with long-sequence interactions and convolutional neural networks (CNNs) have emerged as mainstream solutions, their performance remains limited on high-resolution remote sensing data characterized by small datasets and high heterogeneity. Targeting land cover classification in ski resort areas, this study proposes a triple-branch segmentation framework integrating CNNs and Transformers to extract global, detail and boundary features (GDBNet), and constructs the first high-resolution ski resort land cover dataset with a resolution of 0.75 m using JiLin-1 satellite constellation (LULC_SKI). The framework employs a backbone combining SegFormer with dual CNN branches. SegFormer captures global semantic context, while dual ResNet-18 branches extract local semantics and edge details respectively. The neck integrates two specialized feature interaction modules, the proposed Pixel-Guided Feature Attention (PG-AFM) and Boundary-Guided Feature Attention (BG-AFM), which synergistically fuse these heterogeneous feature representations for enhanced multi-scale modeling. For the segmentation head, a multi-task learning approach supervises both semantic and edge outputs. LULC_SKI covers seven representative ski resorts in Jilin Province, China, comprising 10,000 multi-seasonal images annotated with six land cover classes, including roads, vegetation, built-up areas, ski runs, water bodies, and cropland. Experiments demonstrate GDBNet achieves 85.44% mIoU and 91.84% mF1 on LULC_SKI, outperforming other advanced models with particularly significant improvements for linear objects like roads and ski runs. Extensive experimental comparisons show that GDBNet delivers consistently excellent performance on both the iSAID and LoveDA datasets, underscoring the superiority of our proposed method. Ablation studies validate the effectiveness of the triple-branch architecture, attention modules, and multi-task supervision. This work proposes a modular framework for land cover classification in complex ski resort scenarios. Full article

(This article belongs to the Special Issue Signal Processing, Image Processing and Fusion Techniques in Remote Sensing)

► Show Figures

Figure 1

31 pages, 9295 KB

Open AccessArticle

Hidden Forest in Non-Forest Land: A Remote Sensing-Based Mapping Case in Lithuania

by Monika Papartė, Donatas Jonikavičius and Gintautas Mozgeris

Remote Sens. 2026, 18(10), 1665; https://doi.org/10.3390/rs18101665 - 21 May 2026

Viewed by 269

Abstract

Woody vegetation growing outside officially designated forest land represents a significant but poorly quantified resource in many countries, where institutional and methodological limitations hinder its systematic accounting. This study develops and applies a multi-stage remote sensing-based framework to identify and characterize forest-eligible areas [...] Read more.

Woody vegetation growing outside officially designated forest land represents a significant but poorly quantified resource in many countries, where institutional and methodological limitations hinder its systematic accounting. This study develops and applies a multi-stage remote sensing-based framework to identify and characterize forest-eligible areas (FEAs) in Lithuania by integrating airborne LiDAR, Sentinel-2 time series, historical orthophotos, and national geospatial datasets. The workflow combines (i) LiDAR-derived canopy height model generation and object-based segmentation, (ii) rule-based aggregation of vegetation segments according to legal forest criteria, (iii) multi-index Sentinel-2 change detection to exclude recent disturbances, and (iv) deep learning-based classification of historical orthophotos to assess stand age. Three detection approaches were evaluated—LiDAR-based, land parcel identification system (LPIS)-based, and their combination. A total of 111,754.4 ha of FEAs were identified outside official forest land, of which 76,204.6 ha meet the minimum age criterion for classification as forest land under national legislation. The designation of these areas as forest land would increase national forest cover from 33.9% to 35.0%. The LiDAR-based approach achieved the highest overall accuracy after dataset refinement (91.5%), while the combined approach yielded the highest precision (97.1%). Accuracy improved notably when reference points affected by definitional conflicts and temporal inconsistencies were excluded, indicating that apparent detection errors were largely attributable to reference data limitations rather than algorithmic failure. The proposed framework offers a scalable solution for wall-to-wall identification and monitoring of unregistered forest resources, with direct applications for national forest inventories and LULUCF reporting. Full article

(This article belongs to the Special Issue Remote Sensing-Guided Land-Use Optimization for Carbon Neutrality)

► Show Figures

Figure 1

27 pages, 3616 KB

Open AccessArticle

LiteRoadSegNet: A Lightweight Road Segmentation Framework with Semantic–Topological Contrastive Learning in High-Resolution Remote Sensing Imagery

by Tao Wu, Yu Peng, Jianxin Qin, Yiliang Wan and Yaling Hu

Remote Sens. 2026, 18(10), 1664; https://doi.org/10.3390/rs18101664 - 21 May 2026

Viewed by 313

Abstract

Deploying deep learning models for high-resolution remote sensing image segmentation remains challenging in resource-constrained scenarios due to the high computational cost of dense prediction and the structural vulnerability of thin objects such as roads. To address these challenges, we propose LiteRoadSegNet, a lightweight [...] Read more.

Deploying deep learning models for high-resolution remote sensing image segmentation remains challenging in resource-constrained scenarios due to the high computational cost of dense prediction and the structural vulnerability of thin objects such as roads. To address these challenges, we propose LiteRoadSegNet, a lightweight and deployment-oriented segmentation framework that achieves a favorable balance among efficiency, accuracy, and structural preservation. The proposed model adopts a compact encoder–decoder architecture composed of a lightweight hierarchical vision transformer and a streamlined decoder, enabling efficient multi-scale feature representation under limited computational budgets. To enhance structural consistency without increasing inference overhead, we further design a low-cost semantic–topological dual-branch contrastive learning scheme which enhances feature discriminability and preserves road connectivity during training. In addition, to improve deployment robustness in cross-region scenarios, we incorporate a lightweight test-time adaptation strategy based on Adaptive Batch Normalization (AdaBN) and sliding-window inference. This strategy enables seamless adaptation to unlabeled target domains without requiring model retraining. Extensive experiments demonstrate that LiteRoadSegNet achieves competitive segmentation performance and superior topology preservation while maintaining a small model footprint and high inference efficiency, making it well suited for large-scale remote sensing applications under resource-constrained environments. Full article

(This article belongs to the Special Issue Lightweight Artificial-Intelligence Techniques for Remote-Sensing Image Processing)

► Show Figures

Figure 1

30 pages, 37958 KB

Open AccessArticle

Real-Time Early Warning of Incipient Fire in Multiple Urban Scenarios: A Deep Learning-Based Monitoring Method

by Lingyi Meng, Mengquan Wu, Jinkun Gao, Shikuan Wang, Xiaodong Song, Jie Zhao, Hongchun Liu, Xindan Cao, Longxing Liu, Gang Chen and Jinyi Lv

Remote Sens. 2026, 18(10), 1663; https://doi.org/10.3390/rs18101663 - 21 May 2026

Viewed by 453

Abstract

Urban fire incidents in complex built environments pose severe threats to public safety. However, the unstructured nature of urban scenes presents substantial challenges for existing detection algorithms in reliably identifying incipient flames and diffuse smoke under dynamic visual interference. To address this issue, [...] Read more.

Urban fire incidents in complex built environments pose severe threats to public safety. However, the unstructured nature of urban scenes presents substantial challenges for existing detection algorithms in reliably identifying incipient flames and diffuse smoke under dynamic visual interference. To address this issue, we propose YOLO-Fire, a lightweight and high-precision detection algorithm based on YOLOv11. Specifically, a Hybrid Feature Fusion Module (HFFM) adopts a parallel dual-stream architecture to structurally decouple high-frequency flame boundaries from low-frequency smoke textures. A Dual-Scale Contextual Diffusion (DCD) mechanism establishes global contextual constraints through an additive diffusion strategy, effectively suppressing fire-like background interference while enhancing semi-transparent smoke features. In addition, a Gaussian Spatial Pyramid Pooling Fast (GSPPF) module further improves multi-scale receptive field aggregation. Evaluated on a self-constructed large-scale urban fire dataset, YOLO-Fire achieves an mAP50 of 75.7%, mAP50-95 of 53.3%, and an F1-score of 73.7%, with only 10.02 M parameters, surpassing the YOLOv11 baseline by 2.4%, 4.5%, and 2.9%, respectively. Ablation studies confirm that each proposed module contributes both independently and synergistically to the overall performance gains. Comprehensive comparisons with mainstream detectors and specialized fire detection models further demonstrate that YOLO-Fire achieves superior overall performance, outperforming YOLO-FireAD and FireSmoke-YOLO by 2.7% and 2.4% in mAP50, respectively, while maintaining lower computational complexity. Furthermore, inference evaluation on a single-core CPU achieves 17.28 FPS, validating the practical deployment potential of YOLO-Fire in resource-constrained environments and offering an efficient, lightweight solution for real-time urban fire surveillance and early warning. Full article

► Show Figures

Figure 1

21 pages, 7109 KB

Open AccessArticle

Stereo Radargrammetry Using Deep Learning-Based Image Matching with Fine-Tuned Model on Synthetic Aperture Radar Images

by Koichi Ito, Tatsuya Sasayama, Shintaro Ito, Haruki Iwasa, Takafumi Aoki and Jyunpei Uemoto

Remote Sens. 2026, 18(10), 1662; https://doi.org/10.3390/rs18101662 - 21 May 2026

Viewed by 496

Abstract

Stereo radargrammetry using Synthetic Aperture Radar (SAR) images is a powerful technique for all-weather 3D topographic measurements. However, conventional methods based on local template matching often struggle to establish accurate correspondences in mountainous or vegetated areas due to severe SAR-specific geometric modulations. In [...] Read more.

Stereo radargrammetry using Synthetic Aperture Radar (SAR) images is a powerful technique for all-weather 3D topographic measurements. However, conventional methods based on local template matching often struggle to establish accurate correspondences in mountainous or vegetated areas due to severe SAR-specific geometric modulations. In this paper, we propose a novel high-accuracy stereo radargrammetry framework by introducing RoMa, a robust Transformer-based deep learning model, for dense SAR image matching. Optical pre-trained deep learning models often suffer from a domain gap. To overcome this limitation, we develop an automated pipeline to construct a patch-based SAR image dataset using a reference Digital Surface Model (DSM) and an SAR projection model. By fine-tuning RoMa on this dataset, the model effectively adapts to the complex non-linear deformations of SAR images. Furthermore, unlike conventional methods, our approach establishes correspondences directly on the original slant-range images without requiring ground-range projection, thereby avoiding image quality degradation caused by pixel interpolation. Experimental results using airborne Pi-SAR2 images demonstrate that the fine-tuned RoMa significantly outperforms conventional methods, achieving an 82.86% matching accuracy at a 10-pixel threshold. In the 3D measurement evaluation, the proposed method achieves the lowest elevation mean error (

- 1.24

m) and the highest inlier ratio (74.1%), proving its effectiveness in generating accurate, dense, and wide-area 3D point clouds even in challenging terrains. Full article

(This article belongs to the Special Issue SAR Images Processing and Analysis (3rd Edition))

► Show Figures

Figure 1

21 pages, 26356 KB

Open AccessArticle

Fringe-Enhanced Phase Unwrapping Method Based on an Iterative Bayes–Sard Quadrature Kalman Filter

by Mingsi Lin, Xiangzhen Zeng and Xiaomao Chen

Remote Sens. 2026, 18(10), 1661; https://doi.org/10.3390/rs18101661 - 21 May 2026

Viewed by 355

Abstract

Phase unwrapping plays a vital role in interferometric synthetic aperture radar (InSAR) processing. However, the presence of noise can introduce inconsistencies in phase discontinuities, giving rise to residue points that may cause unwrapping errors. To address this challenge, this paper for the first [...] Read more.

Phase unwrapping plays a vital role in interferometric synthetic aperture radar (InSAR) processing. However, the presence of noise can introduce inconsistencies in phase discontinuities, giving rise to residue points that may cause unwrapping errors. To address this challenge, this paper for the first time applies the Bayes–Sard quadrature transform to the phase unwrapping problem and proposes an iterative Bayes–Sard quadrature Kalman filter phase unwrapping method (IBSQKF). In contrast to the conventional unscented Kalman filter algorithm, the Bayes–Sard moment transform can quantify the additional uncertainty introduced by quadrature errors. Through integration with the proposed iterative strategy, it enables more accurate calibration of state estimation and effectively reduces the root mean square error. To further enhance unwrapping accuracy, a multi-level and multi-scale feature fusion neural network (PFTNet) is developed as a pre-filtering module to independently process the real and imaginary components of the complex interferometric phase representation, which can effectively enhance the clarity of the interferometric fringes. By integrating PFTNet with IBSQKF, a complete phase unwrapping framework (PFT-IBSQKF) is constructed to further improve unwrapping accuracy. Experiments on both simulated and real data demonstrate that IBSQKF can reliably restore phase continuity, while PFT-IBSQKF can further reduce unwrapping errors, especially in low signal-to-noise-ratio or fringe-blurred scenarios. Despite the introduction of the iterative strategy, the proposed framework still maintains an acceptable computational cost while achieving high unwrapping accuracy. Full article

(This article belongs to the Special Issue Advances in InSAR Processing: Algorithmic Developments and Diverse Applications)

► Show Figures

Figure 1

21 pages, 4953 KB

Open AccessArticle

Maize LAI Retrieval Using PointNet++ and Transfer Learning with Integrated 3D Radiative Transfer Modeling and LiDAR Point Clouds

by Qiqi Li, Shengbo Chen, Liang Cui, Yaqi Zhang, Hao Chen, Jinchen Zhu, Menghan Wu, Aonan Zhang and Jiaqi Yang

Remote Sens. 2026, 18(10), 1660; https://doi.org/10.3390/rs18101660 - 21 May 2026

Viewed by 242

Abstract

Accurately estimating leaf area index (LAI) is vital for evaluating crop growth and predicting yields. Conventional approaches, however, often struggle due to the limited representativeness of available data and the complex structure of plant canopies, which reduce their reliability across diverse canopy architectures [...] Read more.

Accurately estimating leaf area index (LAI) is vital for evaluating crop growth and predicting yields. Conventional approaches, however, often struggle due to the limited representativeness of available data and the complex structure of plant canopies, which reduce their reliability across diverse canopy architectures and observation conditions. To overcome these challenges, this work introduces an LAI retrieval framework that combines a three-dimensional radiative transfer model (3D RTM) with deep learning techniques. Representative 3D maize canopy scenarios were generated using the LESS model, producing synthetic LiDAR point clouds constrained by realistic structural parameters. A deep learning model based on PointNet++ was trained, and transfer learning (TL) was employed to facilitate knowledge transfer from simulated to actual measured data. The TL-enhanced model demonstrated significant improvement, with R² rising from 0.537 to 0.842 and RMSE dropping from 0.541 to 0.288 m²·m⁻². Moreover, retrieval performance was notably affected by scanning mode, angle, and stem diameter, achieving optimal results under TLS acquisition, moderate scanning angles, and intermediate stem widths. These findings suggest that integrating 3D RTM-generated synthetic point clouds with transfer learning is an effective strategy for enhancing the robustness and generalization of LiDAR-based LAI retrieval. Full article

(This article belongs to the Special Issue Advanced Quantitative Remote Sensing for Sustainable Agriculture and Vegetation: From Multi-Sensor Fusion to AI-Driven Global Food Security)

► Show Figures

Figure 1

13 pages, 3517 KB

Open AccessTechnical Note

First Light Capabilities of UVSQ-SAT NG NanoCam: Preliminary Limb Temperature Retrieval from a CubeSat Imager

by Pedro Da Costa Louro, Mustapha Meftah, Philippe Keckhut, Christophe Dufour, André-Jean Vieau, Alain Hauchecorne, Mathieu Ratynski and Antoine Mangin

Remote Sens. 2026, 18(10), 1659; https://doi.org/10.3390/rs18101659 - 21 May 2026

Viewed by 277

Abstract

This study assesses the technical feasibility of using polar orbiting satellite constellations to generate temperature profiles in the middle atmosphere, based on image analysis from the UVSQ-Sat NG nanosatellite. We first identified the phenomena influencing the temperature of this layer of the atmosphere, [...] Read more.

This study assesses the technical feasibility of using polar orbiting satellite constellations to generate temperature profiles in the middle atmosphere, based on image analysis from the UVSQ-Sat NG nanosatellite. We first identified the phenomena influencing the temperature of this layer of the atmosphere, specifying their amplitudes and spatio-temporal resolutions. We then present the UVSQ-Sat NG nanosatellite and its Nanocam instrument, whose images of the Earth’s limb served as the basis for our processing. Finally, we detail the processing methodology, demonstrating its applicability to any image of the Earth’s limb acquired in the spectral range from near-UV to near-IR, subject to the following strict conditions: a measurement dynamic range greater than 1000 and rigorous control of instrumental noise. This approach paves the way for continuous, global monitoring of the middle atmosphere, which is essential for improving climate and weather models. Full article

(This article belongs to the Special Issue Satellite Observation of Middle and Upper Atmospheric Dynamics)

► Show Figures

Figure 1

27 pages, 5714 KB

Open AccessArticle

Dynamic World Shannon Entropy as a Scale-Sensitive Indicator of Surface Urban Heat Island Intensity: Evidence from Seven Romanian Cities

by Zsolt Magyari-Sáska and Ionel Haidu

Remote Sens. 2026, 18(10), 1658; https://doi.org/10.3390/rs18101658 - 21 May 2026

Viewed by 377

Abstract

Surface urban heat island intensity is shaped not only by land-cover composition but also by the spatial heterogeneity of urban surfaces. This study evaluates whether Shannon entropy derived from Dynamic World class probabilities can serve as a robust indicator of pointwise SUHI intensity [...] Read more.

Surface urban heat island intensity is shaped not only by land-cover composition but also by the spatial heterogeneity of urban surfaces. This study evaluates whether Shannon entropy derived from Dynamic World class probabilities can serve as a robust indicator of pointwise SUHI intensity across seven major Romanian cities. Summer daytime Landsat 8/9 observations for 2021–2025 were harmonized into multi-year median land surface temperature composites, while Dynamic World probabilities were used to compute normalized Shannon entropy at 90, 150, 300, and 600 m aggregation windows. SUHI was defined relative to a rural reference whose delineation was examined through a multi-parameter sensitivity analysis, after which entropy–SUHI relationships were modeled using generalized additive models with and without an additional spatial smooth. Across all seven cities, the entropy–SUHI relationship was consistently negative, with higher entropy values tending to be associated with lower local thermal excess. The best-supported models were usually obtained at 150 m and more broadly within the 150–300 m range, while very coarse aggregation weakened performance. Spatially adjusted models explained 57.2–82.4% of SUHI deviance, showing that entropy is consistently associated with a stable but partial component of intra-urban thermal variability. Alternative tied-best rural delineations mainly shifted the SUHI baseline and left the fitted entropy response essentially unchanged. Our findings support probability-based entropy as a reliable, scale-sensitive descriptor of urban surface mixture relevant to intra-urban thermal patterning across diverse geographical and climatic settings. Full article

► Show Figures

Figure 1

21 pages, 32134 KB

Open AccessArticle

What Makes the Lower Urban Land Coverage City a Deeper Ozone Trap: Implications from a Case Study in the Sichuan Basin, Southwest China

by Chenxi Wang, Yang Liu, Weijia Wang, Liantang Deng, Xiaofei Sun, Gang Liu, Huaiyong Shao and Zheng Jin

Remote Sens. 2026, 18(10), 1657; https://doi.org/10.3390/rs18101657 - 21 May 2026

Viewed by 345

Abstract

The urban–rural gradient of surface ozone concentration is closely associated with urban scale and has been widely reported in megacities globally. However, in the Sichuan Basin of southwestern China, a paradoxical asymmetric pattern between the ozone gradient and the physical urban footprint has [...] Read more.

The urban–rural gradient of surface ozone concentration is closely associated with urban scale and has been widely reported in megacities globally. However, in the Sichuan Basin of southwestern China, a paradoxical asymmetric pattern between the ozone gradient and the physical urban footprint has emerged. By integrating multi-source satellite observations (e.g., TROPOMI), reanalysis data (ERA5-Land), and a concentric-ring spatial gradient analysis, we quantify a dipole-like urban surface ozone trap pattern in two megacities (Chengdu and Chongqing) from 2013 to 2019. We found that the urban–rural ozone gradients in Chongqing were substantially steeper than those in Chengdu, despite Chongqing’s smaller physical urban footprint. Specifically, in winter, the maximum daily average 8 h ozone level in the urban core drops to 27.5 μg m⁻³ in Chongqing and 47.9 μg m⁻³ in Chengdu, with outward radial increasing rates of 6.49% and 1.88% per 10 km, respectively. Conversely, the absolute nitrogen dioxide level in Chengdu is higher, highlighting an asymmetric titration behavior between the two cities. Regarding the chemical regime, analysis of the ratio (β) of nitrogen dioxide to formaldehyde reveals that Chongqing’s core operates under a more severe VOC-limited environment (β is 2.53 and radial gradient is −6.77% per 10 km) compared to Chengdu (β is 2.43 and gradient is −5.34% per 10 km). Furthermore, vertical cross-section analyses indicate that Chongqing’s deep-valley topography induces severe boundary layer compression and aerodynamic stagnation. Thus, rather than acting independently, these localized meteorological constraints function as crucial physical modulators that trap precursor emissions and exacerbate the non-linear chemical titration. This study elucidates how synergistic interactions between basin topography, physical urban footprints, and atmospheric chemistry shape localized ozone traps, providing a referable perspective for assessing complex urban atmospheric environments. Full article

(This article belongs to the Special Issue Remote Sensing Data Refinement and Utilization for Advanced Atmospheric Observations)

► Show Figures

Figure 1

26 pages, 16141 KB

Open AccessArticle

DAAINet: Domain Adversarial Anti-Interference Network for Bi-Temporal Change Detection

by Jiyuan Yang, Kun Gao, Baiyang Hu, Zefeng Zhang, Jingyi Wang, Yuqing He and Yunpeng Feng

Remote Sens. 2026, 18(10), 1656; https://doi.org/10.3390/rs18101656 - 21 May 2026

Viewed by 516

Abstract

Bi-temporal change detection (CD) in remote sensing (RS) aims to map image pairs at different times into a shared feature space to discriminate variant regions effectively. However, factors such as cloud interference may disrupt the feature distribution of RS images and cause pseudo-change [...] Read more.

Bi-temporal change detection (CD) in remote sensing (RS) aims to map image pairs at different times into a shared feature space to discriminate variant regions effectively. However, factors such as cloud interference may disrupt the feature distribution of RS images and cause pseudo-change problems. Existing public change detection datasets also pay less attention to such pseudo-change phenomena. To address the pseudo-change problems of CD applications, we propose a Domain Adversarial Anti-Interference Change Detection Network (DAAINet), which uses ResNet to extract multi-scale features from the original input images. Semantic features are then obtained and fed into a subsequent graph convolution module after soft clustering, by introducing a domain adversarial structure to align the feature space in RS images. In the graph convolution module, the association of node context is utilized to predict the adjacency relationship between objects. We collected data and constructed a real-world dataset called “Cloud Interference Change Detection” (CICD), which focuses on real bi-temporal remote sensing image data containing cloud interference and includes pseudo-changes caused by factors such as the presence of temporary objects and illumination changes. Experimental results demonstrate that our method is more robust and efficient compared to other state-of-the-art methods on two public CD datasets, and achieves state-of-the-art performance on the noise-corrupted CICD dataset, surpassing prior methods by up to 5.67%p in IoU and 1.42%p in recall. Full article

► Show Figures

Figure 1

1 pages, 127 KB

Open AccessCorrection

Correction: Khan, M.; Chen, R. Assessing the Impact of Land Use and Land Cover Change on Environmental Parameters in Khyber Pakhtunkhwa, Pakistan: A Comprehensive Study and Future Projections. Remote Sens. 2025, 17, 170

by Mehjabeen Khan and Ruishan Chen

Remote Sens. 2026, 18(10), 1655; https://doi.org/10.3390/rs18101655 - 21 May 2026

Viewed by 189

Abstract

Error in Affiliation(s) and Email Address [...] Full article

(This article belongs to the Special Issue Advances of Remote Sensing in Land Cover and Land Use Mapping)

27 pages, 8734 KB

Open AccessArticle

Digital Landscapes: Assessing Fire Severity and Its Drivers Using Remote Sensing and Google Earth Engine Based on dNBR and NPP Indicators

by Dana El Khatib, Georgio Kallas, Joseph Bechara, Micheline Wehbe and Jean Stephan

Remote Sens. 2026, 18(10), 1654; https://doi.org/10.3390/rs18101654 - 20 May 2026

Viewed by 661

Abstract

Wildfires are an increasingly recurrent disturbance in Mediterranean forest landscapes, yet fire severity assessment remains limited in data-scarce regions such as Lebanon. This study aims to assess wildfire severity patterns and identify the main environmental drivers influencing fire severity across the forests of [...] Read more.

Wildfires are an increasingly recurrent disturbance in Mediterranean forest landscapes, yet fire severity assessment remains limited in data-scarce regions such as Lebanon. This study aims to assess wildfire severity patterns and identify the main environmental drivers influencing fire severity across the forests of Akkar, northern Lebanon, within a Digital Landscapes framework. Fire severity was mapped using the Differenced Normalized Burn Ratio (dNBR) derived from multi-temporal Landsat-8 imagery (2013–2024) processed in Google Earth Engine. Vegetation productivity was assessed through annual Net Primary Productivity (NPP), while topographic variables (elevation, slope, and aspect) were derived from a Digital Elevation Model. The results reveal heterogeneous fire severity patterns over the study period and pronounced spatial variability in NPP, with no consistent linear relationship between productivity and fire severity. Principal Component Analysis (PCA) was applied to explore multivariate relationships between fire severity, productivity, and terrain. PCA results show that the first two components explain 77.4% of the total variance, indicating that fire severity is primarily structured by topographic factors, particularly elevation and solar exposure, while vegetation productivity plays a secondary role. These findings highlight the dominant influence of terrain on wildfire severity in Mediterranean mountainous landscapes, and demonstrate the value of integrating remote sensing, cloud-based platforms, and multivariate analysis for fire assessment in data-scarce regions. The study contributes to the advancement of Digital Landscapes approaches by providing a scalable and data-driven framework for understanding fire dynamics and supporting future landscape management and risk assessment strategies. Full article

(This article belongs to the Special Issue Advances in Remote Sensing for Burned Area Mapping)

► Show Figures

Figure 1

28 pages, 12160 KB

Open AccessArticle

Temporal Sensitivity of In-Season Crop Classification: An Explainable Multi-Year Sentinel-2 Analysis in Western Australia

by Sneha Sharma, Harry Eslick, Rodrigo Pires, Balwinder Singh and Hasnein Tareque

Remote Sens. 2026, 18(10), 1653; https://doi.org/10.3390/rs18101653 - 20 May 2026

Viewed by 582

Abstract

Accurate in-season crop type mapping is critical for agricultural monitoring and yield assessment, yet most operational products remain proprietary, post-seasonal or insufficiently tested across contrasting seasons. This study presents an open and transferable framework that quantifies how in-season crop classification skills evolve through [...] Read more.

Accurate in-season crop type mapping is critical for agricultural monitoring and yield assessment, yet most operational products remain proprietary, post-seasonal or insufficiently tested across contrasting seasons. This study presents an open and transferable framework that quantifies how in-season crop classification skills evolve through the growing season across the southwest agricultural region of Western Australia (WA) using a multi-temporal (2020–2024) Sentinel-2 derived vegetation indices (VIs) time-series. Six crop classes (i.e., wheat, barley, canola, lupins, pasture, and fallow) were evaluated using extreme gradient boosting (XGBoost) and long short-term memory (LSTM) models under a leave-one-year-out cross-validation (LOYOCV) design. Classification performance increased progressively through the season, with a marked improvement in late winter (late August to early September). In LOYOCV, overall agreement with the reference dataset exceeded 90% once vegetation-index observations through August were included, indicating that reliable in-season mapping was achievable before harvest. Canola was separated consistently from mid-season onwards, whereas reliable discrimination between wheat and barley required later phenological information. Independent field-based testing was used to assess true crop identification accuracy for the three externally observed classes: wheat, barley, and canola. In this test set, precision was highest for canola (0.93), followed by wheat (0.82) and barley (0.71). These field-based results supported the main temporal pattern observed in the LOYOCV analysis, particularly the strong mid-season separability of canola and the persistent confusion between wheat and barley. SHapley Additive exPlanations (SHAP) showed thatVIs centred on late winter contributed most strongly to model predictions, consistent with peak phenological divergence among crop types. These results identify a phenologically meaningful decision window for in-season crop mapping and provide a multi-year benchmark for evaluating temporal transferability in Mediterranean broadacre systems. Full article

(This article belongs to the Special Issue Advances in the Remote Sensing of Crop Phenology and Production Monitoring Under Environmental Constraints)

► Show Figures

Figure 1

30 pages, 26441 KB

Open AccessArticle

SARM: Scene-Aware Retinex Mamba for Underwater Image Enhancement

by Zhanbo Fu, Shuang Yang, Aiguo Sun, Rongjun Xiong and Nengcheng Chen

Remote Sens. 2026, 18(10), 1652; https://doi.org/10.3390/rs18101652 - 20 May 2026

Viewed by 422

Abstract

Underwater image enhancement is essential for marine visual perception tasks. However, the highly heterogeneous optical degradations in real-world waters, the scarcity of paired training data, and the inherent dilemma for existing models in balancing long-range dependency modeling with computational overhead pose significant challenges. [...] Read more.

Underwater image enhancement is essential for marine visual perception tasks. However, the highly heterogeneous optical degradations in real-world waters, the scarcity of paired training data, and the inherent dilemma for existing models in balancing long-range dependency modeling with computational overhead pose significant challenges. To address these issues, this paper proposes a prior-guided, self-supervised underwater image enhancement framework called Scene-Aware Retinex Mamba (SARM). This framework seamlessly integrates Retinex theoretical priors with state space models (SSMs) and operates without paired supervision by employing a prior-guided pseudo-labeling strategy to guide network optimization. Architecturally, SARM deeply couples the physical Retinex prior with SSM. Its core module integrates multi-color space features and leverages a 2D selective scan mechanism to achieve global context modeling with linear complexity

O (H W)

, effectively removing complex color casts and suppressing non-uniform scattering noise. To further overcome the generalization bottlenecks in cross-domain underwater testing, this paper introduces a Scene-Aware Adapter (SAA), which facilitates dynamic loss scheduling and adaptive feature gating by quantifying scene-specific degradation characteristics. Comprehensive evaluations on multiple benchmark datasets, including UIEB, EUVP, and UCCS, demonstrate that SARM achieves state-of-the-art subjective and objective enhancement quality (e.g., yielding a URanker score of 2.491 and a CCF score of 35.76), while maintaining an ultra-fast inference speed of 136.52 FPS on the UIEB dataset. Furthermore, extended experiments reveal that SARM can significantly boost the performance of downstream vision tasks, validating its potential as a robust preprocessing module for various practical marine vision applications. Full article

(This article belongs to the Section AI Remote Sensing)

► Show Figures

Figure 1

28 pages, 9854 KB

Open AccessArticle

A Single-Transformation Model for Fisheye Image Orthorectification

by Qingyang Wang, Guoqing Zhou, Tao Yue, Bo Song, Jianwu Jiang, Zhen Cao and Xing Zhang

Remote Sens. 2026, 18(10), 1651; https://doi.org/10.3390/rs18101651 - 20 May 2026

Viewed by 212

Abstract

Fisheye lenses can capture surrounding spatial information at once, making them widely applied in various fields. However, the imaging principle of fisheye lenses does not satisfy the collinearity equation, so the theory of orthorectification using traditional differential orthorectification is no longer applicable for [...] Read more.

Fisheye lenses can capture surrounding spatial information at once, making them widely applied in various fields. However, the imaging principle of fisheye lenses does not satisfy the collinearity equation, so the theory of orthorectification using traditional differential orthorectification is no longer applicable for a fisheye image in practice. Therefore, this paper develops a single-spherical-geometry-transformation model for fisheye image orthorectification. This model directly establishes the relationship between spatial ground points and image plane coordinates through spherical geometry, and then combines the digital surface model (DSM) to correct points in the fisheye image to their correct positions on a pixel-by-pixel basis, thereby achieving fisheye image orthorectification. To validate the feasibility of the proposed orthorectification model, an indoor calibration field was established. Experimental validation was then conducted using two fisheye image datasets: an indoor dataset acquired in the calibration field with a digital single-lens reflex (DSLR) camera and an outdoor dataset acquired with an unmanned aerial vehicle (UAV). The results of the two groups of experiments demonstrate that the proposed model can effectively orthorectify fisheye images with ground accuracies of 0.055 m and 0.097 m in x and y direction, respectively. Full article

► Show Figures

Figure 1

28 pages, 15799 KB

Open AccessArticle

Fire Radiative Power Correction and Spatiotemporal Fusion Based on MYD14 and VNP14IMG

by Yang Zheng, Ke Ding, Lian Xue, Zilin Wang, Guanjie Jiao, Yifan Zhu, Jinying Zhang and Qianyu Ren

Remote Sens. 2026, 18(10), 1650; https://doi.org/10.3390/rs18101650 - 20 May 2026

Viewed by 233

Abstract

Moderate Resolution Imaging Spectroradiometer (MODIS) and Visible Infrared Imaging Radiometer Suite (VIIRS) active fire products are widely used for global fire monitoring, but single-sensor records are limited by differences in observation geometry, spatial resolution, detection sensitivity, and swath coverage. To combine the long-term [...] Read more.

Moderate Resolution Imaging Spectroradiometer (MODIS) and Visible Infrared Imaging Radiometer Suite (VIIRS) active fire products are widely used for global fire monitoring, but single-sensor records are limited by differences in observation geometry, spatial resolution, detection sensitivity, and swath coverage. To combine the long-term continuity of Aqua MODIS with the higher sensitivity of Suomi NPP VIIRS, this study developed a correction-before-fusion framework for MYD14 and VNP14IMG and generated a daily fused fire radiative power (FRP) dataset at the native MODIS footprint scale. MYD14 and VNP14IMG observations from 2012 to 2024 were processed using duplicate-detection correction, footprint-scale near-synchronous matching, area-based VIIRS cloud correction, and anomalous-sample screening. Cloud-corrected VIIRS FRP was then used as the reference to develop an empirical viewing zenith angle (VZA)-dependent correction model for MODIS FRP. Finally, VZA-corrected MODIS FRP and cloud-corrected VIIRS FRP were integrated using a quality-prioritized fusion strategy. The correction model achieved high fitting accuracy (

R^{2} \geq 98.18 %

) and reduced MODIS underestimation under large-VZA conditions. Compared with the original MODIS product, the fused product increased detected fire pixels by approximately 3.82-fold, improved spatial continuity, and reduced temporal data gaps. Landsat-based validation showed improved low-intensity fire detection while maintaining low commission error. This framework provides a harmonized long-term FRP dataset for fire monitoring, emission estimation, and fire-climate studies. Full article

(This article belongs to the Section Remote Sensing Image Processing)

► Show Figures

Figure 1

19 pages, 5961 KB

Open AccessArticle

Application of LiDAR-Based Technology to Construction Material Volume Estimation

by Yu-Wen Chen, Chi-Feng Chen, Lih-Jen Kau and Jen-Yang Lin

Remote Sens. 2026, 18(10), 1649; https://doi.org/10.3390/rs18101649 - 20 May 2026

Viewed by 380

Abstract

Accurate stockpile volume estimation is crucial for material quantification and inventory management in civil engineering, directly affecting cost assessment and on-site decision-making. Traditional manual methods suffer from subjective bias and limitations in handling irregular geometries, resulting in reduced accuracy and efficiency. This study [...] Read more.

Accurate stockpile volume estimation is crucial for material quantification and inventory management in civil engineering, directly affecting cost assessment and on-site decision-making. Traditional manual methods suffer from subjective bias and limitations in handling irregular geometries, resulting in reduced accuracy and efficiency. This study presents a Light Detection and Ranging (LiDAR)-based workflow integrated with Robot Operating System (ROS) for point cloud processing, enabling accurate volume estimation of irregular stockpiles. The core innovation lies in the integration of multi-station scanning, point cloud registration, boundary extraction, layered slicing, and numerical integration using the trapezoidal rule, thereby enabling geometrically precise volume estimation of irregular stockpiles. The proposed system was validated through three experimental scenarios: (1) controlled experiments, showing strong agreement with theoretical volumes; (2) verification experiments, demonstrating high stability and consistency; and (3) field experiments, yielding a volume of 124.93 m³ compared to 130–135 m³ obtained by manual measurement. The results indicate that the proposed approach reduces processing time by over 80% while significantly decreasing labor requirements and improving operational safety. Overall, the proposed method provides a reliable and efficient solution for volume estimation in practical engineering applications. Full article

(This article belongs to the Section Engineering Remote Sensing)

► Show Figures

Figure 1

29 pages, 3512 KB

Open AccessArticle

BGE-ICMER: Bare-Ground-Echo-Based Iterative Correction of Multi-Echo Reflectance for Hyperspectral LiDAR

by Xinyi Pan, Binhui Wang, Jiahang Wan, Shalei Song and Shuo Shi

Remote Sens. 2026, 18(10), 1648; https://doi.org/10.3390/rs18101648 - 20 May 2026

Viewed by 439

Abstract

Full-waveform hyperspectral LiDAR offers a new approach for precise forest ecological monitoring by simultaneously acquiring the three-dimensional structure and continuous spectral information of targets. However, uncertainty in the backscattering cross-section and the inseparability of the reflectance coefficient lead to systematic underestimation of multi-echo [...] Read more.

Full-waveform hyperspectral LiDAR offers a new approach for precise forest ecological monitoring by simultaneously acquiring the three-dimensional structure and continuous spectral information of targets. However, uncertainty in the backscattering cross-section and the inseparability of the reflectance coefficient lead to systematic underestimation of multi-echo reflectance retrieved using traditional methods. This limitation significantly hinders quantitative applications. The existing multi-echo reflectance correction using neighborhood single-echo reflectance (MCNS) method provides an effective solution by establishing proportional models between similar targets, laying an important foundation for the extraction of multi-echo reflectance. However, its applicability in complex forest scenes is limited due to its dependence on specific vegetation single-echo samples. To address this, an iterative correction method based on ground reflectance baseline, namely Bare-Ground-Echo-Based Iterative Correction of Multi-Echo Reflectance for Hyperspectral LiDAR (BGE-ICMER), is proposed. Using ground single-echo reflectance as a stable baseline, a multi-target energy distribution model is constructed based on energy conservation, and backscattering cross-section proportions for each echo are iteratively solved to recover true reflectance. Validation using a high-fidelity dataset generated by the Large-Scale remote sensing data and image Simulation framework (LESS) confirmed the effectiveness of the proposed method. This dataset encompasses three typical tree species with vegetation layers ranging from two to four, incorporates micro-topographic ground surfaces and ten spectral channels from 500 to 1000 nm, thereby capturing the structural and spectral complexity of real forests. The results showed that coefficients of determination (R²) between the corrected and true reflectance exceeded 0.9560, with an RMSE below 0.0418 and MAE below 0.0360. The average relative error was reduced from 26.66% to 10.07%, representing a 62.22% improvement in accuracy. Even in the most challenging scenarios with four-layer vegetation occlusion within this dataset, no significant error accumulation occurred. These results demonstrate the robustness and effectiveness of the proposed method for multi-echo reflectance extraction. This study lays a foundation for more accurate forest biochemical attribute assessment and enables the vertical characterization of multiple targets using high-resolution spectral reflectance. Full article

(This article belongs to the Special Issue Vegetation Biophysical Variables and Remote Sensing Applications (Second Edition))

► Show Figures

Figure 1

27 pages, 5223 KB

Open AccessArticle

Learning Structured Distance Mappings for Spacecraft Pose Estimation with Feature Degradation

by Chuan Yan, Hongfeng Long, Zifei Cao, Yuebo Ma, Jiayu Suo, Xiangying Lu, Rujin Zhao and Zhenming Peng

Remote Sens. 2026, 18(10), 1647; https://doi.org/10.3390/rs18101647 - 20 May 2026

Viewed by 220

Abstract

Pose estimation of non-cooperative spacecraft remains challenging under feature degradation. Motion blur, self-occlusion, and weak texture can cause structural line disappearance, correspondence ambiguity, and localization drift, which destabilize conventional point- and line-based analytic pose estimation pipelines relying on discrete feature detection and post-hoc [...] Read more.

Pose estimation of non-cooperative spacecraft remains challenging under feature degradation. Motion blur, self-occlusion, and weak texture can cause structural line disappearance, correspondence ambiguity, and localization drift, which destabilize conventional point- and line-based analytic pose estimation pipelines relying on discrete feature detection and post-hoc 2-D-to-3-D association. To address these issues, we propose a two-stage framework for line-based 6-DoF pose estimation built upon a structure-bound multi-channel spatial distance mapping (SDM), where each SDM channel is uniquely associated with one predefined 3-D model line. By explicitly binding each SDM channel to a predefined 3-D model line, the proposed representation encodes 2-D-to-3-D line correspondence directly in the network output, thereby avoiding unstable line matching after prediction and providing solver-consistent geometric constraints for Perspective-n-Line (PnL) estimation. To reduce localization blur around the SDM zero-level set, a cross-scale self-attention (CSSA) mechanism is introduced to couple high-resolution localization features with low-resolution structural context through window-level cross-scale attention. Based on the predicted SDMs, explicit 2-D structural lines are recovered through weighted robust fitting in narrow bands around the zero-level sets, enabling the completion of partially or fully occluded lines and yielding solver-ready observations for PnL pose recovery. Experiments on a close-range non-cooperative spacecraft dataset with simulated observation distances of 10–30 m show that SDMNet achieves translation/rotation errors of 0.8%/0.0372 rad, 0.91%/0.0394 rad, and 1.38%/0.0579 rad under original, motion-blur, and occlusion conditions, respectively. These results indicate that the proposed framework can robustly recover correspondence-aware structural observations from degraded images and improve the accuracy and stability of spacecraft pose estimation. Full article

(This article belongs to the Special Issue Advances in the Study of Intelligent Aerospace)

► Show Figures

Figure 1

24 pages, 9740 KB

Open AccessArticle

Adaptive Sliding-Window Filtering for GNSS SPP-Aided Orbit Determination in Earth–Moon Space

by Jinru Lin, Ying Xu, Ran Li, Ming Gao, Chao Yuan, Ye Feng and Xiang Li

Remote Sens. 2026, 18(10), 1646; https://doi.org/10.3390/rs18101646 - 20 May 2026

Viewed by 306

Abstract

Orbit determination in Earth–Moon space is challenged by dynamic-model mismatch and unstable GNSS observation conditions, especially under weak and intermittent signals. To address this issue, this paper proposes a GNSS single-point positioning (SPP)-aided orbit determination method based on adaptive sliding-window filtering. A tightly [...] Read more.

Orbit determination in Earth–Moon space is challenged by dynamic-model mismatch and unstable GNSS observation conditions, especially under weak and intermittent signals. To address this issue, this paper proposes a GNSS single-point positioning (SPP)-aided orbit determination method based on adaptive sliding-window filtering. A tightly coupled framework is constructed by integrating orbital dynamics propagation with SPP pseudo-range observations, allowing propagation errors to be corrected in real time through measurement updates. To enhance adaptability under time-varying observation conditions, a dynamic sliding-window strategy is introduced, in which the observation-noise covariance is adjusted according to carrier-to-noise ratio (

C / N_{0}

) variations. Simulations for three representative Earth–Moon trajectories, including a near-rectilinear halo orbit (NRHO), a distant retrograde orbit (DRO), and a Halo orbit, show that the proposed method significantly outperforms the conventional tightly coupled solution. The three-dimensional RMS position error is reduced from 6.65 m to 1.27 m for NRHO, from 6.57 m to 1.27 m for DRO, and from 5.91 m to 1.44 m for Halo, corresponding to improvements of 80.9%, 80.4%, and 75.4%, respectively. Under a simulated 200-epoch GNSS interruption in the Halo case, the method also improves outage robustness and post-recovery performance, reducing the three-dimensional RMS error by 23.2% in the interruption-centered interval and by 26.1% over the full arc. Full article

► Show Figures

Figure 1

24 pages, 1303 KB

Open AccessArticle

Spatial–Frequency Inductive Bias-Guided Cross-Domain Representation Learning for Infrared Small Object Detection

by Quanrun Cheng, Cao Zeng, Qi He, Yuhong Zhang and Hailong Ning

Remote Sens. 2026, 18(10), 1645; https://doi.org/10.3390/rs18101645 - 20 May 2026

Viewed by 286

Abstract

Infrared small object detection (ISOD) plays a crucial role in military reconnaissance, security surveillance, and remote sensing monitoring, where weak thermal responses and complex backgrounds impose significant challenges. The recent self-supervised vision foundation model DINOv3 has demonstrated remarkable generalization ability across various visual [...] Read more.

Infrared small object detection (ISOD) plays a crucial role in military reconnaissance, security surveillance, and remote sensing monitoring, where weak thermal responses and complex backgrounds impose significant challenges. The recent self-supervised vision foundation model DINOv3 has demonstrated remarkable generalization ability across various visual tasks. However, directly transferring it to ISOD still remains challenging due to substantial cross-domain discrepancy between visible and infrared imagery, as well as the limited granularity of foundation features in capturing subtle thermal variations. To address these issues, this study proposes a spatial–frequency inductive bias-guided network (SFI-Net) based on DINOv3 for cross-domain representation learning in infrared small object detection. Instead of conventional domain adaptation strategies, SFI-Net explicitly models infrared-specific inductive biases in both spatial and frequency domains to enhance transferred representations. First, a spatio-frequency hybrid adapter (SFHA) is designed and embedded across multiple layers of the frozen backbone to learn infrared-specific inductive biases within distinct subspaces. Second, a feature compensation strategy with an auxiliary convolutional branch is devised to compensate for the limitation of DINOv3 in capturing multi-scale fine-grained features. Extensive experiments on the IRSTD-1K and NUDT-SIRST datasets demonstrate that the proposed SFI-Net outperforms state-of-the-art methods in both detection accuracy and computational efficiency while exhibiting strong cross-scenario generalization capability. Full article

► Show Figures

Figure 1

25 pages, 67694 KB

Open AccessArticle

Physics Informed Time–Frequency Dual Branch Target Detection Method for Early-Warning Radar

by Yao Ni, Shengbo Ma, Kai Jing, Biyang Wen and Dongxiao Yang

Remote Sens. 2026, 18(10), 1644; https://doi.org/10.3390/rs18101644 - 20 May 2026

Viewed by 298

Abstract

Early-Warning Radar (EWR) is an advanced detection system capable of monitoring aerial targets over long distances with high precision, providing critical information support for defense security. However, EWR faces challenges such as a limited number of pulses, low coherent integration gain, small target [...] Read more.

Early-Warning Radar (EWR) is an advanced detection system capable of monitoring aerial targets over long distances with high precision, providing critical information support for defense security. However, EWR faces challenges such as a limited number of pulses, low coherent integration gain, small target Radar Cross Section (RCS), and complex clutter and electromagnetic interference environments. Conventional Constant False Alarm Rate (CFAR) detection algorithms struggle to effectively detect weak targets while maintaining an acceptable false alarm rate. To address these issues, this paper introduces a deep learning approach. A high target-clutter/interference/noise discriminative feature spectrum is obtained through phase difference transformation, upon which a dual-branch collaborative architecture network is constructed. In this architecture, the main network focuses on extracting spatiotemporal amplitude–phase characteristics, while the auxiliary branch implicitly mines the target’s physical boundary features from frequency-domain echoes. Through a self-attention mechanism, the features from both branches are semantically aligned and fused. This method significantly enhances the weak target detection capability of EWR under the constraint of a controlled false alarm rate. Test results show that under the false alarm rate ranging from

10^{- 3}

to

10^{- 4}

, the SNR gain of the proposed algorithm is about 2∼5 dB, which is equivalent to increasing the radar detection range by 10∼30%. Full article

► Show Figures

Figure 1

Journal Menu

Journal Browser

Remote Sens., Volume 18, Issue 10 (May-2 2026) – 226 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI