Remote Sensing

20 pages, 7161 KiB

Open AccessArticle

FM-Net: Frequency-Aware Masked-Attention Network for Infrared Small Target Detection

by Yongxian Liu, Zaiping Lin, Boyang Li, Ting Liu and Wei An

Remote Sens. 2025, 17(13), 2264; https://doi.org/10.3390/rs17132264 - 1 Jul 2025

Infrared small target detection (IRSTD) aims to locate and separate targets from complex backgrounds. The challenges in IRSTD primarily come from extremely sparse target features and strong background clutter interference. However, existing methods typically perform discrimination directly on the features extracted by deep [...] Read more.

Infrared small target detection (IRSTD) aims to locate and separate targets from complex backgrounds. The challenges in IRSTD primarily come from extremely sparse target features and strong background clutter interference. However, existing methods typically perform discrimination directly on the features extracted by deep networks, neglecting the distinct characteristics of weak and small targets in the frequency domain, thereby limiting the improvement of detection capability. In this paper, we propose a frequency-aware masked-attention network (FM-Net) that leverages multi-scale frequency clues to assist in representing global context and suppressing noise interference. Specifically, we design the wavelet residual block (WRB) to extract multi-scale spatial and frequency features, which introduces a wavelet pyramid as the intermediate layer of the residual block. Then, to perceive global information on the long-range skip connections, a frequency-modulation masked-attention module (FMM) is used to interact with multi-layer features from the encoder. FMM contains two crucial elements: (a) a mask attention (MA) mechanism for injecting broad contextual feature efficiently to promote full-level semantic correlation and focus on salient regions, and (b) a channel-wise frequency modulation module (CFM) for enhancing the most informative frequency components and suppressing useless ones. Extensive experiments on three benchmark datasets (e.g., SIRST, NUDT-SIRST, IRSTD-1k) demonstrate that FM-Net achieves superior detection performance. Full article

(This article belongs to the Special Issue Advanced Artificial Intelligence and Deep Learning for Remote Sensing (3rd Edition))

39 pages, 4244 KiB

Open AccessArticle

Attitude Estimation of Spinning Space Targets Utilizing Multistatic ISAR Joint Observation

by Jishun Li, Canbin Yin, Can Xu, Jun He, Pengju Li and Yasheng Zhang

Remote Sens. 2025, 17(13), 2263; https://doi.org/10.3390/rs17132263 - 1 Jul 2025

Abstract

When a space target malfunctions and is no longer controlled by its attitude control system, it usually tumbles in orbit and exhibits a slow spinning state. Accurately estimating the on-orbit attitude of spinning space targets is of vital importance for ensuring the operation [...] Read more.

When a space target malfunctions and is no longer controlled by its attitude control system, it usually tumbles in orbit and exhibits a slow spinning state. Accurately estimating the on-orbit attitude of spinning space targets is of vital importance for ensuring the operation of space assets. Moreover, it plays a significant role in tasks such as reentry observation and collision avoidance. Currently, most existing methods estimate the attitude of space targets by using a single inverse synthetic aperture radar (ISAR) for long-term observation. However, this approach not only requires a long observation time but also fails to estimate the attitude of spinning targets. To address these limitations, this paper proposes a novel approach for estimating the attitude of spinning space targets, which utilizes the joint observations of a multiple-station ISAR. Specifically, the proposed method fully exploits the projection principle of ISAR imaging and uses an ISAR high-resolution network (ISAR-HRNet) to automatically extract the projection features of typical components of the target. Then, the analytical expressions for the target’s instantaneous attitude and spin vector under the multi-station observation imaging projection model are derived. Based on the extracted features of the typical components, the lengths, orientations, and spin vectors of the space target are determined. Importantly, the proposed method can achieve the attitude estimation of the spinning space targets within a single observation period, without the need for manual intervention or prior information about the target’s three-dimensional (3D) model. Additionally, the analytical method for solving the spin vector offers high efficiency and accuracy. Finally, the effectiveness of the proposed attitude estimation algorithm is verified by experiments on simulated data, and the performance of the ISAR-HRNet is also tested in the key point extraction experiments using measured data. Full article

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

24 pages, 22943 KiB

Open AccessArticle

Loss Adaptive Curriculum Learning for Ground-Based Cloud Detection

by Tianhong Qi, Yanyan Hu and Juan Wang

Remote Sens. 2025, 17(13), 2262; https://doi.org/10.3390/rs17132262 - 1 Jul 2025

Abstract

While deep learning has advanced object detection through hierarchical feature learning and end-to-end optimization, conventional random sampling paradigms exhibit critical limitations in addressing hyperspectral ambiguity and low-distinguishability challenges in ground-based cloud detection. To overcome these limitations, we propose CurriCloud, a loss-adaptive curriculum framework [...] Read more.

While deep learning has advanced object detection through hierarchical feature learning and end-to-end optimization, conventional random sampling paradigms exhibit critical limitations in addressing hyperspectral ambiguity and low-distinguishability challenges in ground-based cloud detection. To overcome these limitations, we propose CurriCloud, a loss-adaptive curriculum framework featuring three key innovations: (1) real-time sample evaluation via Unified Batch Loss (UBL) for difficulty measurement, (2) stabilized training monitoring through a sliding window queue mechanism, and (3) progressive sample selection aligned with model capability using meteorology-guided phase-wise threshold scheduling. Extensive experiments on the ALPACLOUD benchmark demonstrate CurriCloud’s effectiveness across diverse architectures (YOLOv10s, SSD, and RT-DETR-R50), achieving consistent improvements of +3.1% to +11.4% mAP50 over both random sampling baselines and existing curriculum learning methods. Full article

► Show Figures

Figure 1

21 pages, 7082 KiB

Open AccessReview

The Bright Decade of Ocean Salinity from Space

by Roberto Sabia, Jacqueline Boutin, Nicolas Reul, Tong Lee and Simon H. Yueh

Remote Sens. 2025, 17(13), 2261; https://doi.org/10.3390/rs17132261 - 1 Jul 2025

Abstract

Sea Surface Salinity is a crucial climatic variable due to its twofold role as both a passive and an active tracer of oceanic processes. Despite its relevance, however, it could not be measured from space, mainly because of technological limitations, until 2009. Since [...] Read more.

Sea Surface Salinity is a crucial climatic variable due to its twofold role as both a passive and an active tracer of oceanic processes. Despite its relevance, however, it could not be measured from space, mainly because of technological limitations, until 2009. Since then, the generation and assessment of satellite salinity has become a game-changer in physical and biogeochemical oceanography, as well as in climate science. Three satellite sensors with salinity-measuring capabilities (SMOS-Soil Moisture and Ocean Salinity, Aquarius, and SMAP-Soil Moisture Active Passive) have been launched in the previous decade, each characterized by specific measurement concepts and features and ad hoc validation approaches. The increasing usage of spaceborne salinity products has produced a variety of results and applications, which are here summarized under three specific domains: climate, scientific, and operational. Finally, short-to-mid-term perspectives, indicating both the expected improvements in terms of algorithms and also looking at novel mission concepts (that will provide continuation of these measurements in the decade to come) have been described. Full article

(This article belongs to the Special Issue Oceans from Space V)

► Show Figures

Figure 1

21 pages, 2568 KiB

Open AccessArticle

Improved Flood Insights: Diffusion-Based SAR-to-EO Image Translation

by Minseok Seo, Jinwook Jung and Dong-Geol Choi

Remote Sens. 2025, 17(13), 2260; https://doi.org/10.3390/rs17132260 - 1 Jul 2025

Abstract

Floods, exacerbated by climate change, necessitate timely and accurate situational awareness to support effective disaster response. While electro-optical (EO) satellite imagery has been widely employed for flood assessment, its utility is significantly limited under conditions such as cloud cover or nighttime. Synthetic Aperture [...] Read more.

Floods, exacerbated by climate change, necessitate timely and accurate situational awareness to support effective disaster response. While electro-optical (EO) satellite imagery has been widely employed for flood assessment, its utility is significantly limited under conditions such as cloud cover or nighttime. Synthetic Aperture Radar (SAR) provides consistent imaging regardless of weather or lighting conditions but it remains challenging for human analysts to interpret. To bridge this modality gap, we present diffusion-based SAR-to-EO image translation (DSE), a novel framework designed specifically for enhancing the interpretability of SAR imagery in flood scenarios. Unlike conventional GAN-based approaches, our DSE leverages the Brownian Bridge Diffusion Model to achieve stable and high-fidelity EO synthesis. Furthermore, it integrates a self-supervised SAR denoising module to effectively suppress SAR-specific speckle noise, thereby improving the quality of the translated outputs. Quantitative experiments on the SEN12-FLOOD dataset show that our method improves PSNR by 3.23 dB and SSIM by 0.10 over conventional SAR-to-EO baselines. Additionally, a user study with SAR experts revealed that flood segmentation performance using synthetic EO (SynEO) paired with SAR was nearly equivalent to using true EO–SAR pairs, with only a 0.0068 IoU difference. These results confirm the practicality of the DSE framework as an effective solution for EO image synthesis and flood interpretation in SAR-only environments. Full article

(This article belongs to the Special Issue Deep Learning Innovations in Remote Sensing)

► Show Figures

Figure 1

22 pages, 6735 KiB

Open AccessArticle

SFMattingNet: A Trimap-Free Deep Image Matting Approach for Smoke and Fire Scenes

by Shihui Ma, Zhaoyang Xu and Hongping Yan

Remote Sens. 2025, 17(13), 2259; https://doi.org/10.3390/rs17132259 - 1 Jul 2025

Abstract

Smoke and fire detection is vital for timely fire alarms, but traditional sensor-based methods are often unresponsive and costly. While deep learning-based methods offer promise using aerial images and surveillance images, the scarcity and limited diversity of smoke-and-fire-related image data hinder model accuracy [...] Read more.

Smoke and fire detection is vital for timely fire alarms, but traditional sensor-based methods are often unresponsive and costly. While deep learning-based methods offer promise using aerial images and surveillance images, the scarcity and limited diversity of smoke-and-fire-related image data hinder model accuracy and generalization. Alpha composition, blending foreground and background using per-pixel alpha values (transparency parameters stored in the alpha channel alongside RGB channels), can effectively augment smoke and fire image datasets. Since image matting algorithms compute these alpha values, the quality of the alpha composition directly depends on the performance of the smoke and fire matting methods. However, due to the lack of smoke and fire image matting datasets for model training, existing image matting methods exhibit significant errors in predicting the alpha values of smoke and fire targets, leading to unrealistic composite images. Therefore, to address these above issues, the main research contributions of this paper are as follows: (1) Construction of a high-precision, large-scale smoke and fire image matting dataset, SFMatting-800. The images in this dataset are sourced from diverse real-world scenarios. It provides precise foreground opacity values and attribute annotations. (2) Evaluation of existing image matting baseline methods. Based on the SFMatting-800 dataset, traditional, trimap-based deep learning and trimap-free deep learning matting methods are evaluated to identify their strengths and weaknesses, providing a benchmark for improving future smoke and fire matting methods. (3) Proposal of a deep learning-based trimap-free smoke and fire image matting network, SFMattingNet, which takes the original image as input without using trimaps. Taking into account the unique characteristics of smoke and fire, the network incorporates a non-rigid object feature extraction module and a spatial awareness module, achieving improved performance. Compared to the suboptimal approach, MODNet, our SFMattingNet method achieved an average error reduction of 12.65% in the smoke and fire matting task. Full article

(This article belongs to the Special Issue Advanced AI Technology for Remote Sensing Analysis)

► Show Figures

Figure 1

21 pages, 5785 KiB

Open AccessArticle

Impacts of the Assimilation of Radar Radial Velocity Data Using the Ensemble Kalman Filter (EnKF) on the Analysis and Forecast of Typhoon Lekima (2019)

by Jiping Guan, Jiajun Chen, Xinya Li, Mengting Liu and Mingyang Zhang

Remote Sens. 2025, 17(13), 2258; https://doi.org/10.3390/rs17132258 - 30 Jun 2025

Abstract

High-resolution radar observations are essential to improving the numerical predictions of high-impact weather systems with data assimilation techniques. The numerical simulations of the landfall of Typhoon Lekima (2019) are conducted in the framework of the WRF model, investigating the impact of assimilating radar [...] Read more.

High-resolution radar observations are essential to improving the numerical predictions of high-impact weather systems with data assimilation techniques. The numerical simulations of the landfall of Typhoon Lekima (2019) are conducted in the framework of the WRF model, investigating the impact of assimilating radar radial velocity observations via the Ensemble Kalman Filter (EnKF) on the typhoon’s analysis and forecast performance. The results demonstrate that the EnKF method significantly improves forecast accuracy for Typhoon Lekima, including track, intensity and the 24 h cumulative precipitation. To be specific, the control experiment significantly underestimated typhoon intensity, while EnKF-based radar radial velocity assimilation markedly improved near-surface winds (>48 m/s) in the typhoon core, refined vortex structure and reduced track forecast errors by 50–60%. Compared with the control and 3DVAR experiments, EnKF assimilation better captured typhoon precipitation patterns, with the highest ETS scores, especially for moderate-to-high precipitation intensities. Moreover, the detailed analysis and diagnostics of Lekima show that the warm core structure is better captured in the assimilation experiment. The typhoon system is also improved, as reflected by enhanced potential temperature and a more robust wind field analysis. Full article

(This article belongs to the Special Issue Application of Remote Sensing Data in Data Assimilation, Reanalysis and Artificial Intelligence for Mesoscale Numerical Weather Models (Second Edition))

► Show Figures

Figure 1

24 pages, 40762 KiB

Open AccessArticle

Multiscale Task-Decoupled Oriented SAR Ship Detection Network Based on Size-Aware Balanced Strategy

by Shun He, Ruirui Yuan, Zhiwei Yang and Jiaxue Liu

Remote Sens. 2025, 17(13), 2257; https://doi.org/10.3390/rs17132257 - 30 Jun 2025

Abstract

Current synthetic aperture radar (SAR) ship datasets exhibit a notable disparity in the distribution of large, medium, and small ship targets. This imbalance makes it difficult for a relatively small number of large and medium-sized ships to be effectively trained, resulting in many [...] Read more.

Current synthetic aperture radar (SAR) ship datasets exhibit a notable disparity in the distribution of large, medium, and small ship targets. This imbalance makes it difficult for a relatively small number of large and medium-sized ships to be effectively trained, resulting in many false alarms. Therefore, to address the issues of scale diversity, intra-class imbalance in ship data, and the feature conflict problem associated with traditional coupled detection heads, we propose an SAR image multiscale task-decoupled oriented ship target detector based on a size-aware balanced strategy. First, the multiscale target features are extracted using the multikernel heterogeneous perception module (MKHP). Meanwhile, the triple-attention module is introduced to establish the remote channel dependence to alleviate the issue of small target feature annihilation, which can effectively enhance the feature characterization ability of the model. Second, given the differences in the demand for feature information between the detection and classification tasks, a channel attention-based task decoupling dual-head (CAT2D) detector head structure is introduced to address the inherent conflict between classification and localization tasks. Finally, a new size-aware balanced (SAB) loss strategy is proposed to guide the network in focusing on the scarce targets in training to alleviate the intra-class imbalance problem during the training process. The ablation experiments on SSDD+ reflect the contribution of each component, and the results of the comparison experiments on the RSDD-SAR and HRSID datasets show that the proposed method achieves state-of-the-art performance compared to other state-of-the-art detection models. Furthermore, our approach exhibits superior detection coverage for both offshore and inshore scenarios for ship detection tasks. Full article

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

► Show Figures

Figure 1

18 pages, 5752 KiB

Open AccessArticle

Contrasting Impacts of Urbanization and Cropland Irrigation on Observed Surface Air Temperature in Northern China

by Xiaoyu Xu, Shiguang Miao, Yizhou Zhang and Jingjing Dou

Remote Sens. 2025, 17(13), 2256; https://doi.org/10.3390/rs17132256 - 30 Jun 2025

Abstract

Urbanization and cropland irrigation modify land surface water and energy budgets in different ways; however, few observational studies have explicitly quantified their contrasts. Using high-resolution observations from over 2000 surface weather stations and urban and irrigation fraction data, this study investigated the individual [...] Read more.

Urbanization and cropland irrigation modify land surface water and energy budgets in different ways; however, few observational studies have explicitly quantified their contrasts. Using high-resolution observations from over 2000 surface weather stations and urban and irrigation fraction data, this study investigated the individual and combined effects of urbanization and cropland irrigation on surface air temperature over the Beijing–Tianjin–Hebei (BTH) region in China, where highly urbanized areas and heavily irrigated croplands exist together. The results indicate that (1) the daytime irrigation cooling (with surface air temperature decreasing by ~0.1–0.5 °C at irrigated stations) was non-negligible in late autumn, early winter, and later spring months, when winter wheat irrigation mainly occurred over the BTH region, while a slight warming was observed at many irrigated stations during the nighttime. By contrast, urban warming was most pronounced in the nighttime, especially in winter, and the daytime warming at urban sites was much weaker and comparable to the magnitude of cooling induced by concurrent irrigation for winter wheat. (2) Collectively, the vast stretches of irrigated croplands helped mitigate urban warming, and their combined effect on the daytime surface air temperature over the whole region resulted in a slight cooling of ~0.2 °C in some of the winter wheat-growing months. (3) The contrasting temperature changes due to urbanization and irrigation were spatially variable. Beijing was predominantly characterized by urban warming, while Shijiazhuang, with extensive irrigation, exhibited irrigation cooling (or slight warming) during the daytime (or nighttime) in most of the winter wheat-growing months, which could be a possible contributor to the daytime cooling (or stronger nighttime warming) at urban sites. This work highlights the temperature contrasts between urban areas and surrounding irrigated croplands, as well as the potential role of extensive irrigation in mitigating (or enhancing) daytime (or nighttime) urban warming. Full article

20 pages, 11215 KiB

Open AccessArticle

Predictive Assessment of Forest Fire Risk in the Hindu Kush Himalaya (HKH) Region Using HIWAT Data Integration

by Sunil Thapa, Tek Maraseni, Hari Krishna Dhonju, Kiran Shakya, Bikram Shakya, Armando Apan and Bikram Banerjee

Remote Sens. 2025, 17(13), 2255; https://doi.org/10.3390/rs17132255 - 30 Jun 2025

Abstract

Forest fires in the Hindu Kush Himalaya (HKH) region are increasing in frequency and severity, driven by climate variability, prolonged dry periods, and human activity. Nepal, a critical part of the HKH, recorded over 22,700 forest fire events in the past decade, with [...] Read more.

Forest fires in the Hindu Kush Himalaya (HKH) region are increasing in frequency and severity, driven by climate variability, prolonged dry periods, and human activity. Nepal, a critical part of the HKH, recorded over 22,700 forest fire events in the past decade, with fire incidence nearly doubling in 2023. Despite this growing threat, operational early warning systems remain limited. This study presents Nepal’s first high-resolution early fire risk outlook system, developed by adopting the Canadian Fire Weather Index (FWI) using meteorological forecasts from the High-Impact Weather Assessment Toolkit (HIWAT). The system generates daily and two-day forecasts using a fully automated Python-based workflow and publishes results as Web Map Services (WMS). Model validation against MODIS, VIIRS, and ground fire records for 2023 showed that over 80% of fires occurred in zones classified as Moderate to Very High risk. Spatiotemporal analysis confirmed fire seasonality, with peaks in mid-April and over 65% of fires occurring in forested areas. The system’s integration of satellite data and high-resolution forecasts improves the spatial and temporal accuracy of fire danger predictions. This research presents a novel, scalable, and operational framework tailored for data-scarce and topographically complex regions. Its transferability holds substantial potential for strengthening anticipatory fire management and climate adaptation strategies across the HKH and beyond. Full article

(This article belongs to the Section Environmental Remote Sensing)

18 pages, 1566 KiB

Open AccessArticle

Synthesizing Remote Sensing Images from Land Cover Annotations via Graph Prior Masked Diffusion

by Kai Deng, Siyuan Wei, Shiyan Pang, Huiwei Jiang and Bo Su

Remote Sens. 2025, 17(13), 2254; https://doi.org/10.3390/rs17132254 - 30 Jun 2025

Abstract

Semantic image synthesis (SIS) in remote sensing aims to generate high-fidelity satellite imagery from land use/land cover (LULC) labels, supporting applications such as map updating, data augmentation, and environmental monitoring. However, the existing methods typically focus on pixel-level semantic-to-image translation, neglecting the spatial [...] Read more.

Semantic image synthesis (SIS) in remote sensing aims to generate high-fidelity satellite imagery from land use/land cover (LULC) labels, supporting applications such as map updating, data augmentation, and environmental monitoring. However, the existing methods typically focus on pixel-level semantic-to-image translation, neglecting the spatial and semantic relationships among land cover objects, which hinders accurate scene structure modeling. To address this challenge, we propose GMDiT, an enhanced conditional diffusion model that extends the masked DiT architecture with graph-prior modeling. By jointly incorporating relational graph structures and semantic labels, GMDiT explicitly captures the object-level spatial and semantic dependencies, thereby improving the contextual coherence and structural fidelity of the synthesized images. Specifically, to effectively capture inter-object dependencies, we first encode the semantics of each node using CLIP and then employ a simple yet effective graph transformer to model the spatial interactions among nodes. Additionally, we design a scene similarity sampling strategy for the reverse diffusion process, improving contextual alignment while maintaining generative diversity. Experiments on the OpenEarthMap dataset show that GMDiT achieves superior performance in terms of FID and other metrics, demonstrating its effectiveness and robustness in the generation of structured remote sensing images. Full article

(This article belongs to the Special Issue Fifth Anniversary of “AI Remote Sensing” Section)

► Show Figures

Figure 1

31 pages, 31711 KiB

Open AccessArticle

On the Usage of Deep Learning Techniques for Unmanned Aerial Vehicle-Based Citrus Crop Health Assessment

by Ana I. Gálvez-Gutiérrez, Frederico Afonso and Juana M. Martínez-Heredia

Remote Sens. 2025, 17(13), 2253; https://doi.org/10.3390/rs17132253 - 30 Jun 2025

Abstract

This work proposes an end-to-end solution for leaf segmentation, disease detection, and damage quantification, specifically focusing on citrus crops. The primary motivation behind this research is to enable the early detection of phytosanitary problems, which directly impact the productivity and profitability of Spanish [...] Read more.

This work proposes an end-to-end solution for leaf segmentation, disease detection, and damage quantification, specifically focusing on citrus crops. The primary motivation behind this research is to enable the early detection of phytosanitary problems, which directly impact the productivity and profitability of Spanish and Portuguese agricultural developments, while ensuring environmentally safe management practices. It integrates an onboard computing module for Unmanned Aerial Vehicles (UAVs) using a Raspberry Pi 4 with Global Positioning System (GPS) and camera modules, allowing the real-time geolocation of images in citrus croplands. To address the lack of public data, a comprehensive database was created and manually labelled at the pixel level to provide accurate training data for a deep learning approach. To reduce annotation effort, we developed a custom automation algorithm for pixel-wise labelling in complex natural backgrounds. A SegNet architecture with a Visual Geometry Group 16 (VGG16) backbone was trained for the semantic, pixel-wise segmentation of citrus foliage. The model was successfully integrated as a modular component within a broader system architecture and was tested with UAV-acquired images, demonstrating accurate disease detection and quantification, even under varied conditions. The developed system provides a robust tool for the efficient monitoring of citrus crops in precision agriculture. Full article

(This article belongs to the Special Issue Application of Satellite and UAV Data in Precision Agriculture)

► Show Figures

Figure 1

19 pages, 8377 KiB

Open AccessArticle

Enhanced RT-DETR with Dynamic Cropping and Legendre Polynomial Decomposition Rockfall Detection on the Moon and Mars

by Panpan Zang, Jinxin He, Yongbin Yang, Yu Li and Hanya Zhang

Remote Sens. 2025, 17(13), 2252; https://doi.org/10.3390/rs17132252 - 30 Jun 2025

Abstract

The analysis of rockfall events provides critical insights for deciphering planetary geological processes and reconstructing environmental evolutionary timelines. Conventional visual interpretation methods that rely on orbiter imagery can be inefficient due to their massive datasets and subtle morphological signatures. While deep learning technologies, [...] Read more.

The analysis of rockfall events provides critical insights for deciphering planetary geological processes and reconstructing environmental evolutionary timelines. Conventional visual interpretation methods that rely on orbiter imagery can be inefficient due to their massive datasets and subtle morphological signatures. While deep learning technologies, particularly object detection models, demonstrate transformative potential, they require specific adaptation to planetary imaging constraints, including low contrast, grayscale inputs, and small-target detection. Our coordinated optimization strategy integrates dynamic cropping optimization with architectural innovations: Kolmogorov–Arnold Network based C3 module (KANC3) replaces RepC3 through Legendre polynomial decomposition to strengthen feature representation, while our dynamic cropping strategy significantly improves small-target detection in low-contrast grayscale imagery by mitigating background and target imbalance. Experimental validation on the optimized RMaM-2020 dataset demonstrates that Real-Time Detection Transformer with a ResNet-18 backbone and Kolmogorov–Arnold Network based C3 module (RT-DETR-R18-KANC3) achieves 0.982 precision, 0.955 recall, and 0.964 mAP50 under low-contrast conditions, representing a 1% improvement over the baseline model and exceeding YOLO-series models by >40% in relative performance metrics. Full article

(This article belongs to the Special Issue Remote Sensing of Target Object Detection and Identification (Third Edition))

► Show Figures

Figure 1

21 pages, 15038 KiB

Open AccessArticle

Enhancing Underwater LiDAR Accuracy Through a Multi-Scattering Model for Pulsed Laser Echoes

by Ruichun Dong, Xin Fang, Xiangqian Meng, Chengyun Yang and Tao Li

Remote Sens. 2025, 17(13), 2251; https://doi.org/10.3390/rs17132251 - 30 Jun 2025

Abstract

In airborne LiDAR measurements of shallow water bathymetry, conventional data processing often overlooks the radiative losses associated with multiple scattering events, affecting detection accuracy. This study presents a Monte Carlo-based approach to construct a mathematical model that accurately characterizes the multiple returns in [...] Read more.

In airborne LiDAR measurements of shallow water bathymetry, conventional data processing often overlooks the radiative losses associated with multiple scattering events, affecting detection accuracy. This study presents a Monte Carlo-based approach to construct a mathematical model that accurately characterizes the multiple returns in airborne laser bathymetric systems. The model enables rapid simulation of laser propagation through water, accounting for multiple scattering events. Based on the Beer–Lambert law and incorporating the parameters of typical Jerlov 1 clear coastal water, the proposed model achieves a seamless integration of the H-G phase function with a Monte Carlo random process, enabling accurate simulation and validation of pulse temporal broadening in waters with varying optical transparency. Unlike most existing studies, which primarily focus on modeling the laser emission process, this work introduces a novel perspective by analyzing the probability of light reception in LiDAR return signals, offering a more comprehensive understanding of signal attenuation and detection performance in underwater environments. The results demonstrate that, for detecting underwater targets at depths of 10 m, considering three or more scattering events improves the accuracy by ~7%. For detecting underwater targets at depths of 50 m, considering three or more scattering events improves the accuracy by 15~33%. These findings can help enhance the detection accuracy and efficiency of experimental systems. Full article

(This article belongs to the Special Issue Applications and New Trends in Metrology for Radar/LiDAR-Based Systems II)

► Show Figures

Figure 1

25 pages, 5596 KiB

Open AccessArticle

Multi-Information-Assisted Bistatic Active Sonar Target Tracking for Autonomous Underwater Vehicles in Shallow Water

by Zhanpeng Bao, Yonglin Zhang, Yupeng Tai, Jun Wang, Haibin Wang, Chao Li, Chenghao Hu and Peng Zhang

Remote Sens. 2025, 17(13), 2250; https://doi.org/10.3390/rs17132250 - 30 Jun 2025

Abstract

Bistatic active sonar enables robust and precise target position and tracking, making it a key technology for autonomous underwater vehicles (AUVs) in underwater surveillance. This paper proposes a multi-information-assisted target tracking algorithm for bistatic active sonar, leveraging spatial and temporal echo signal structures [...] Read more.

Bistatic active sonar enables robust and precise target position and tracking, making it a key technology for autonomous underwater vehicles (AUVs) in underwater surveillance. This paper proposes a multi-information-assisted target tracking algorithm for bistatic active sonar, leveraging spatial and temporal echo signal structures to address the challenges of AUVs in shallow water. First, broadened cluster formations in sonar echoes are analyzed, leading to the integration of a spatial clustering-based data association. This paper departs from conventional methods by fusing target position, echo amplitude, and Doppler information during the movement of AUVs, which can improve the efficiency of association probability computation. The re-derived multi-information-assisted association probability calculation method and algorithmic workflow are explicitly designed for real-time implementation in AUV systems. Simulation experiments verify the feasibility of integrating Doppler and amplitude information. The sea trial data from simulated AUV-deployed bistatic sonar contained only amplitude information due to experimental limitations. By utilizing this amplitude information, the algorithm proposed in this paper demonstrates a 23.95% performance improvement over the traditional probabilistic data association algorithm. The proposed algorithm provides AUVs with enhanced tracking autonomy, significantly advancing their capability in ocean engineering applications. Full article

(This article belongs to the Special Issue Ocean Remote Sensing Based on Radar, Sonar and Optical Techniques (Second Edition))

► Show Figures

Figure 1

20 pages, 1263 KiB

Open AccessArticle

Remote Sensing Image-Based Building Change Detection: A Case Study of the Qinling Mountains in China

by Lei Fu, Yunfeng Zhang, Keyun Zhao, Lulu Zhang, Ying Li, Changjing Shang and Qiang Shen

Remote Sens. 2025, 17(13), 2249; https://doi.org/10.3390/rs17132249 - 30 Jun 2025

Abstract

With the widespread application of deep learning in Earth observation, remote sensing image-based building change detection has achieved numerous groundbreaking advancements. However, differences across time periods caused by temporal variations in land cover, as well as the complex spatial structures in remote sensing [...] Read more.

With the widespread application of deep learning in Earth observation, remote sensing image-based building change detection has achieved numerous groundbreaking advancements. However, differences across time periods caused by temporal variations in land cover, as well as the complex spatial structures in remote sensing scenes, significantly constrain the performance of change detection. To address these challenges, a change detection algorithm based on spatio-spectral information aggregation is proposed, which consists of two key modules: the Cross-Scale Heterogeneous Convolution module (CSHConv) and the Spatio-Spectral Information Fusion module (SSIF). CSHConv mitigates information loss caused by scale heterogeneity, thereby enhancing the effective utilization of multi-scale features. Meanwhile, SSIF models spatial and spectral information jointly, capturing interactions across different spatial scales and spectral domains. This investigation is illustrated with a case study conducted with the real-world dataset QL-CD (Qinling change detection), acquired in the Qinling region of China. The work includes the construction of QL-CD, which includes 12,724 pairs of images captured by the Gaofen-1 satellite. Experimental results demonstrate that the proposed approach outperforms a wide range of state-of-the-art algorithms. Full article

(This article belongs to the Special Issue Artificial Intelligence Remote Sensing for Earth Observation)

25 pages, 845 KiB

Open AccessArticle

A Lightweight Method for Road Defect Detection in UAV Remote Sensing Images with Complex Backgrounds and Cross-Scale Fusion

by Wenya Zhang, Xiang Li, Lina Wang, Danfei Zhang, Pengfei Lu, Lei Wang and Chuanxiang Cheng

Remote Sens. 2025, 17(13), 2248; https://doi.org/10.3390/rs17132248 - 30 Jun 2025

Abstract

The accuracy of road damage detection models based on UAV remote sensing images is generally low, mainly due to the challenges posed by the complex background of road damage, diverse forms, and necessary computational requirements. To tackle the issue, this paper presents CSGEH-YOLO, [...] Read more.

The accuracy of road damage detection models based on UAV remote sensing images is generally low, mainly due to the challenges posed by the complex background of road damage, diverse forms, and necessary computational requirements. To tackle the issue, this paper presents CSGEH-YOLO, a lightweight model tailored for UAV-based road damage detection in intricate environments. (1) The star operation from StarNet is integrated into the C2f backbone network, enhancing its capacity to capture intricate details in complex scenes. Moreover, the CAA attention mechanism is employed to strengthen the model’s global feature extraction abilities; (2) a cross-scale feature fusion strategy known as GFPN is developed to tackle the problem of diverse target scales in road damage detection; (3) to reduce computational resource consumption, a lightweight detection head called EP-Detect has been specifically designed to decrease the model’s computational complexity and the number of parameters; and (4) the model’s localization capability for road damage targets is enhanced by integrating an optimized regression loss function called WiseIoUv3. Experimental findings indicate that the CSGEH-YOLO algorithm surpasses the baseline YOLOv8s, achieving a 3.1% improvement in mAP. It also reduces model parameters by 4% and computational complexity to 78%. In contrast to alternative methods, the model proposed in this paper significantly reduces computational complexity while improving accuracy. It offers robust support for deploying UAV-based road damage detection models. Full article

(This article belongs to the Special Issue Road Detection, Monitoring and Maintenance Using Remotely Sensed Data (2nd Edition))

20 pages, 4400 KiB

Open AccessArticle

Fast Intrinsic–Extrinsic Calibration for Pose-Only Structure-from-Motion

by Xiaoyang Tian, Yangbing Ge, Zhen Tan, Xieyuanli Chen, Ming Li and Dewen Hu

Remote Sens. 2025, 17(13), 2247; https://doi.org/10.3390/rs17132247 - 30 Jun 2025

Abstract

Structure-from-motion (SfM) is a foundational technology that facilitates 3D scene understanding and visual localization. However, bundle adjustment (BA)-based SfM is usually very time-consuming, especially when dealing with numerous unknown focal length cameras. To address these limitations, we proposed a novel SfM system based [...] Read more.

Structure-from-motion (SfM) is a foundational technology that facilitates 3D scene understanding and visual localization. However, bundle adjustment (BA)-based SfM is usually very time-consuming, especially when dealing with numerous unknown focal length cameras. To address these limitations, we proposed a novel SfM system based on pose-only adjustment (PA) for intrinsic and extrinsic joint optimization to accelerate computing. Firstly, we propose a base frame selection method based on depth uncertainty, which integrates the focal length and parallax angle under a multi-camera system to provide more stable depth estimation for subsequent optimization. We explicitly derive a global PA of joint intrinsic and extrinsic parameters to reduce the high dimensionality of the parameter space and deal with cameras with unknown focal lengths, improving the efficiency of optimization. Finally, a novel pose-only re-triangulation (PORT) mechanism is proposed for enhanced reconstruction completeness by recovering failed triangulations from incomplete point tracks. The proposed framework has been demonstrated to be both faster and comparable in accuracy to state-of-the-art SfM systems, as evidenced by public benchmarking and analysis of the visitor photo dataset. Full article

► Show Figures

Figure 1

26 pages, 92114 KiB

Open AccessArticle

Multi-Modal Remote Sensing Image Registration Method Combining Scale-Invariant Feature Transform with Co-Occurrence Filter and Histogram of Oriented Gradients Features

by Yi Yang, Shuo Liu, Haitao Zhang, Dacheng Li and Ling Ma

Remote Sens. 2025, 17(13), 2246; https://doi.org/10.3390/rs17132246 - 30 Jun 2025

Abstract

Multi-modal remote sensing images often exhibit complex and nonlinear radiation differences which significantly hinder the performance of traditional feature-based image registration methods such as Scale-Invariant Feature Transform (SIFT). In contrast, structural features—such as edges and contours—remain relatively consistent across modalities. To address this [...] Read more.

Multi-modal remote sensing images often exhibit complex and nonlinear radiation differences which significantly hinder the performance of traditional feature-based image registration methods such as Scale-Invariant Feature Transform (SIFT). In contrast, structural features—such as edges and contours—remain relatively consistent across modalities. To address this challenge, we propose a novel multi-modal image registration method, Cof-SIFT, which integrates a co-occurrence filter with SIFT. By replacing the traditional Gaussian filter with a co-occurrence filter, Cof-SIFT effectively suppresses texture variations while preserving structural information, thereby enhancing robustness to cross-modal differences. To further improve image registration accuracy, we introduce an extended approach, Cof-SIFT_HOG, which extracts Histogram of Oriented Gradients (HOG) features from the image gradient magnitude map of corresponding points and refines their positions based on HOG similarity. This refinement yields more precise alignment between the reference and image to be registered. We evaluated Cof-SIFT and Cof-SIFT_HOG on a diverse set of multi-modal remote sensing image pairs. The experimental results demonstrate that both methods outperform existing approaches, including SIFT, COFSM, SAR-SIFT, PSO-SIFT, and OS-SIFT, in terms of robustness and registration accuracy. Notably, Cof-SIFT_HOG achieves the highest overall performance, confirming the effectiveness of the proposed structural-preserving and corresponding point location refinement strategies in cross-modal registration tasks. Full article

► Show Figures

Figure 1

Journal Description

Remote Sensing

Latest Articles

Journal Menu

Journal Browser

Highly Accessed Articles

Latest Books

E-Mail Alert

News

Topics

Conferences

Special Issues

Topical Collections

Further Information

Guidelines

MDPI Initiatives

Follow MDPI