Submit to Special Issue Submit Abstract to Special Issue Review for Sensors Propose a Special Issue

Journal Menu

Journal Browser

► Journal Browser

Remote Sensing Image Processing, Analysis and Application

Special Issue Editors
Special Issue Information
Keywords
Benefits of Publishing in a Special Issue
Published Papers

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Sensing and Imaging".

Deadline for manuscript submissions: 1 June 2026 | Viewed by 14336

Share This Special Issue

Special Issue Editors

Dr. Yilong Han

E-Mail Website
Guest Editor

College of Geodesy and Geomatics, Shandong University of Science and Technology, Qingdao 266590, China
Interests: photogrammetry; image processing; 3D computer vision; image matching; geospatial analysis

Dr. Qi Chen

E-Mail Website
Guest Editor

School of Geography and Information Engineering, China University of Geosciences, Wuhan 430074, China
Interests: remote sensing; machine learning; building integrated photovoltaics
Special Issues, Collections and Topics in MDPI journals

Dr. Zhiling Guo

E-Mail Website
Guest Editor

Department of Building Environment and Energy Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong, China
Interests: computer vision; remote sensing; machine learning
Special Issues, Collections and Topics in MDPI journals

Dr. Hanchao Zhang

E-Mail Website
Guest Editor

Chinese Academy of Surveying and Mapping, Beijing 100036, China
Interests: deep learning; change detection; urban monitoring

Special Issue Information

Dear Colleagues,

The evolution of remote sensing technologies, alongside substantial advancements in computational methodologies, has greatly enhanced our ability to extract meaningful insights from complex remote sensing datasets. This Special Issue aims to compile and disseminate cutting-edge research that focuses on advancements in remote sensing image processing, analytical methodologies, and practical applications across various domains.

This Special Issue seeks to explore innovative approaches, including but not limited to machine learning and advanced statistical techniques, and to improve image processing and analysis. Contributions that address the progress and implementation of advanced photogrammetry techniques, alongside the integration of remote sensing data with other geospatial datasets, are particularly encouraged. Topics may include comprehensive analyses in 3D real scene generation, environmental monitoring, urbanization, agricultural practices, and disaster management. This Special Issue intends to foster interdisciplinary dialogue and collaboration among researchers, practitioners, and policy-makers in the field of remote sensing.

We cordially invite researchers, scholars, and practitioners to contribute to this Special Issue entitled "Remote Sensing Image Processing, Analysis, and Applications." We welcome original research articles, comprehensive reviews, and insightful case studies that highlight contemporary advancements and applications in remote sensing. This Special Issue presents a valuable opportunity to share your research with a diverse audience and to contribute to the evolving discourse surrounding remote sensing methodologies and applications.

Dr. Yilong Han
Dr. Qi Chen
Dr. Zhiling Guo
Dr. Hanchao Zhang
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

remote sensing
image processing
photogrammetry
geospatial analysis
meachine learning
environmental monitoring
satellite imagery
agricultural practices

Benefits of Publishing in a Special Issue

Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (10 papers)

Download All Papers

Order results

Result details

Show export options Show export options

Select all

Export citation of selected articles as:

Research

19 pages, 2149 KB

Open AccessArticle

An Unsupervised Image Stitching Framework via Joint Iterative Optimization of Deformation Estimation, Feature Registration, and Seamless Blending

by Baian Ning, Junjie Liu, Haoxin Yu, Qun Lou, Fang Lin and Shanggang Lin

Sensors 2026, 26(9), 2782; https://doi.org/10.3390/s26092782 - 29 Apr 2026

Viewed by 674

Abstract

Image stitching is a computational technique designed to align and seamlessly fuse multiple overlapping images into a single panoramic image with an extended field of view. It plays a critical role in diverse domains, including mobile photography, autonomous navigation, and visual perception systems. However, most conventional image stitching pipelines implicitly assume that the input images have been pre-corrected for geometric distortions, particularly radial distortion inherent to wide-angle and fisheye lenses. This assumption often fails in practice, as many consumer-grade cameras lack built-in correction or calibration support. Consequently, applying standard image stitching methods to the uncorrected imagery frequently degrades feature correspondence reliability and introduces visible geometric misalignments and seam discontinuities in the final panorama. To overcome these limitations, this paper introduces a task-driven joint iterative optimization framework for image stitching that unifies unsupervised radial distortion correction, distortion-aware feature registration, and seam-aware blending within a single cohesive optimization objective. Specifically, lens distortion parameters are explicitly modeled as learnable variables and embedded into both the geometric registration and seam optimization sub-problems. An efficient closed-loop optimization strategy is then employed to jointly refine distortion parameters, homography estimates, and optimal seam paths in an alternating, mutually reinforcing manner. Implementation-wise, we first propose a calibration-free initial radial distortion estimation method which leverages intrinsic image gradients and epipolar consistency to provide physically plausible initialization for subsequent optimization. During iteration, distortion parameters are progressively refined by integrating robust geometric constraints derived from current feature matches (via RANSAC-based consensus filtering) with photometric consistency cues. Extensive experiments on multiple public benchmarks featuring pronounced radial distortion demonstrate that our method achieves superior stitching fidelity using metrics including PSNR and SSIM. It also confirms enhanced feature matching stability, which outperforms both distortion-agnostic approaches and two-stage pipelines that decouple distortion correction from registration. Furthermore, comprehensive ablation studies quantitatively and qualitatively validate the functional necessity and synergistic contribution of each core module, confirming the design rationale and effectiveness of the proposed joint optimization architecture. Full article

(This article belongs to the Special Issue Remote Sensing Image Processing, Analysis and Application)

► Show Figures

Figure 1

15 pages, 4391 KB

Open AccessArticle

Secondary Imaging Architecture for Fast and Ultra-Wide LWIR Optics with Low Rectilinear Distortion

by Kuo-Chuan Wang and Cheng-Huan Chen

Sensors 2026, 26(8), 2334; https://doi.org/10.3390/s26082334 - 9 Apr 2026

Viewed by 355

Abstract

Wide-swath longwave infrared (LWIR) imaging from Low Earth Orbit (LEO) demands fast optics and rectilinear (F-tan) mapping for thermal mapping and multi-frame registration. Achieving an F/1.2 aperture with a 112° diagonal field of view (FOV) and distortion within ±5% is challenging, as mapping constraints and field-dominant off-axis aberrations become strongly coupled at large chief-ray angles. The low-distortion target is not only a geometric specification, but also a practical requirement that reduces peripheral compression, helps maintain edge-detail consistency, and lowers digital de-warping effort in the processing pipeline. While traditional LWIR secondary imaging is predominantly restricted to narrow-field cooled systems for cold-stop constraints, the proposed architecture utilizes a curved intermediate image to effectively decouple mapping formation in the field-dominant front objective from aperture-dominant correction in the rear group. Using chalcogenide glasses, the lens achieves a 5.7 mm effective focal length within a 186.9 mm total track. Analysis over the 8–12 μm band confirms performance approaching the diffraction limit at the 50 lp/mm Nyquist frequency alongside stable geometric fidelity across the full field. Thermal analysis from −40 °C to 80 °C and Monte Carlo tolerance analysis demonstrate stable imaging performance and manufacturing feasibility, confirming the effectiveness of the proposed design approach. Full article

(This article belongs to the Special Issue Remote Sensing Image Processing, Analysis and Application)

► Show Figures

Figure 1

23 pages, 4575 KB

Open AccessArticle

Simulation of Dense Star Map in Deep Space Based on Gaia Catalogue

by Puzhen Li, Guangzhen Bao, Ziwei Zhou and Jinnan Gong

Sensors 2026, 26(6), 1945; https://doi.org/10.3390/s26061945 - 19 Mar 2026

Viewed by 384

Abstract

High-fidelity star field simulation is paramount for target detection and space situational awareness (SSA) in geostationary and deep-space environments. However, accurately modeling the synergistic effects of ultra-dense stellar backgrounds and complex platform perturbations remains a formidable challenge. This paper proposes an integrated simulation framework that leverages the Gaia catalog to generate high-precision stellar environments. The core methodological novelty lies in the end-to-end coupling of a full optoelectronic imaging chain with dynamic platform disturbances, effectively bridging the gap between theoretical orbital dynamics and realistic sensor responses. Distinguishing itself from conventional models, our approach uniquely integrates radiative transfer and high-fidelity noise suites—including photon shot noise and non-uniform stray light—while utilizing the Gaia catalog to achieve unprecedented precision in simulating dim stars at low magnitudes. The fidelity of the proposed model was quantitatively validated against empirical data from a ground-based wide-field telescope (GTC). Experimental results, derived from multiple simulation realizations, demonstrate high consistency with real-world observations, achieving a Signal-to-Noise Ratio (SNR) error of less than 10% and a sub-pixel centroiding accuracy exceeding 0.01 pixels. This work provides a robust, high-fidelity data synthesis tool that significantly advances the development of target detection algorithms and the performance optimization of space-based optical sensors. Full article

(This article belongs to the Special Issue Remote Sensing Image Processing, Analysis and Application)

► Show Figures

Figure 1

33 pages, 6678 KB

Open AccessArticle

A Systematic Study on Pretraining Strategies for Low-Label Remote Sensing Image Semantic Segmentation

by Peizhuo Liu, Hongbo Zhu, Xiaofei Mi, Jian Yang, Yuke Meng, Huijie Zhao and Xingfa Gu

Sensors 2026, 26(4), 1385; https://doi.org/10.3390/s26041385 - 22 Feb 2026

Cited by 2 | Viewed by 723

Abstract

This paper addresses the critical challenge of semantic segmentation for remote sensing images (RSIs) under extremely limited labeled data. A high-quality initial model is paramount for downstream semi-supervised or weakly supervised learning paradigms, as it mitigates error propagation from the outset. We conducted a systematic investigation into self-supervised pretraining to serve this precise need. Within the low-label regime, we identify and tackle two pivotal factors limiting performance: (1) the domain shift between large-scale pretraining data and specific target tasks, and (2) the deficiency in local feature learning caused by large-window masking in visual foundation model (VFM) pretraining. To resolve these issues, we first benchmark various pretraining strategies, demonstrating that a two-phase General-Purpose Pretraining (GPPT) followed by Domain-Adaptive Pretraining (DAPT) framework is optimal, significantly outperforming both single-phase methods and the existing two-phase paradigm initialized from ImageNet. Subsequently, we propose an Edge-Guided Masked Image Modeling (EGMIM) method for the DAPT phase, which explicitly integrates edge priors to guide the masking and reconstruction process, thereby enhancing the model’s capability to capture fine-grained local structures. Extensive experiments on four RSI benchmarks validate the effectiveness of our approach, showing consistent and substantial gains, particularly in extreme low-label scenarios. Beyond empirical results, we provide in-depth mechanistic analyses to explain the synergistic roles of GPPT and DAPT. Full article

(This article belongs to the Special Issue Remote Sensing Image Processing, Analysis and Application)

► Show Figures

Figure 1

23 pages, 4191 KB

Open AccessArticle

Estimation of Wind Turbine Heights with Shadows Using Gaofen-2 Satellite Imagery

by Jiaguo Li, Xinyue Cui, Xingfeng Chen, Hui Gong, Mei Hu, Limin Zhao, Yanping Wang, Kun Liu, Shumin Liu and Yunli Zhang

Sensors 2026, 26(4), 1330; https://doi.org/10.3390/s26041330 - 19 Feb 2026

Viewed by 587

Abstract

Using high-resolution remote sensing imagery to obtain the wind turbine height is a fast and effective method for monitoring the status of wind turbines after natural disasters such as earthquakes, landslides, and typhoons. A height estimation method tailored for wind turbines is proposed using high-resolution satellite images. First, deep learning techniques are employed to identify wind turbines and extract their shadow information from GaoFen-2 (GF-2) satellite imagery. Specifically, YOLOv5-CBAM and MSASDNet are used for target recognition and shadow extraction, achieving an identification accuracy of 96% and a shadow extraction accuracy of 82.53%. Next, the line-by-line scanning method is applied to remove blade shadow from the whole wind turbine shadow. By calculating the number of pixels occupied by the shadow length of the wind turbine after removing the blade shadow and multiplying by the image resolution, the wind turbine shadow length is obtained. Finally, a spatial geometry model involving the satellite angles, solar angles, and wind turbine shadow length is constructed to retrieve the wind turbine height. An experiment was conducted using GF-2 satellite remote sensing data from a wind farm in Huailai County of China. The actual heights of wind turbines in the estimation area were measured by the field experiment, and the average absolute error was verified to be 2.2 m, demonstrating the effectiveness of the proposed method. The experimental results show that this method can detect the post-disaster status of wind turbines. Full article

(This article belongs to the Special Issue Remote Sensing Image Processing, Analysis and Application)

► Show Figures

Figure 1

22 pages, 9212 KB

Open AccessArticle

Semantic-Aware Co-Parallel Network for Cross-Scene Hyperspectral Image Classification

by Xiaohui Li, Chenyang Jin, Yuntao Tang, Kai Xing and Xiaodong Yu

Sensors 2025, 25(21), 6688; https://doi.org/10.3390/s25216688 - 1 Nov 2025

Cited by 1 | Viewed by 861

Abstract

Cross-scene classification of hyperspectral images poses significant challenges due to the lack of a priori knowledge and the differences in data distribution across scenes. While traditional studies have had limited use of a priori knowledge from other modalities, recent advancements in pre-trained large-scale language-vision models have shown strong performance on various downstream tasks, highlighting the potential of cross-modal assisted learning. In this paper, we propose a Semantic-aware Collaborative Parallel Network (SCPNet) to mitigate the impact of data distribution differences by incorporating linguistic modalities to assist in learning cross-domain invariant representations of hyperspectral images. SCPNet uses a parallel architecture consisting of a spatial–spectral feature extraction module and a multiscale feature extraction module, designed to capture rich image information during the feature extraction phase. The extracted features are then mapped into an optimized semantic space, where improved supervised contrastive learning clusters image features from the same category together while separating those from different categories. Semantic space bridges the gap between visual and linguistic modalities, enabling the model to mine cross-domain invariant representations from the linguistic modality. Experimental results demonstrate that SCPNet significantly outperforms existing methods on three publicly available datasets, confirming its effectiveness for cross-scene hyperspectral image classification tasks. Full article

(This article belongs to the Special Issue Remote Sensing Image Processing, Analysis and Application)

► Show Figures

Figure 1

22 pages, 3840 KB

Open AccessArticle

An Optical Water Type-Based Deep Learning Framework for Enhanced Turbidity Estimation in Inland Waters from Sentinel-2 Imagery

by Yue Ma, Qiuyue Chen, Kaishan Song, Qian Yang, Qiang Zheng and Yongchao Ma

Sensors 2025, 25(20), 6483; https://doi.org/10.3390/s25206483 - 20 Oct 2025

Viewed by 1345

Abstract

Turbidity is a crucial and reliable indicator that is extensively utilized in water quality monitoring through remote sensing technology. The development of accurate and applicable models for turbidity estimation is essential. While many existing studies rely on uniform models based on statistical regression or traditional machine learning techniques, the application of deep learning models for turbidity estimation remains limited. This study proposed deep learning models for turbidity estimation based on optical classification of inland waters using Sentinel-2 data. Specifically, the fuzzy c-means (FCM) clustering method was employed to classify optical water types (OWTs) based on their spectral reflectance characteristics. A weighted sum of the turbidity prediction results was generated by the OWT-based convolutional neural network-random forest (CNN-RF) model, with weights derived from the FCM membership degrees. Turbidity for four typical waters was mapped by the proposed method using Sentinel-2 images. The FCM method efficiently classified waters into three OWTs. The OWT-based weighted CNN-RF model demonstrated strong robustness and generalization performance, achieving a high prediction accuracy (R² = 0.900, RMSE = 11.698 NTU). The turbidity maps preserved the spatial continuity of the turbidity distribution and accurately reflected water quality conditions. These findings facilitate the application of deep learning models based on optical classification in turbidity estimation and enhance the capabilities of remote sensing for water quality monitoring. Full article

(This article belongs to the Special Issue Remote Sensing Image Processing, Analysis and Application)

► Show Figures

Figure 1

26 pages, 10719 KB

Open AccessArticle

MPGH-FS: A Hybrid Feature Selection Framework for Robust Multi-Temporal OBIA Classification

by Xiangchao Xu, Huijiao Qiao, Zhenfan Xu and Shuya Hu

Sensors 2025, 25(18), 5933; https://doi.org/10.3390/s25185933 - 22 Sep 2025

Viewed by 2451

Abstract

Object-Based Image Analysis (OBIA) generates high-dimensional features that frequently induce the curse of dimensionality, impairing classification efficiency and generalizability in high-resolution remote sensing images. To address these challenges while simultaneously overcoming the limitations of single-criterion feature selection and enhancing temporal adaptability, we propose a novel feature selection framework named Mutual information Pre-filtering and Genetic-Hill climbing hybrid Feature Selection (MPGH-FS), which integrates Mutual Information Correlation Coefficient (MICC) pre-filtering, Genetic Algorithm (GA) global search, and Hill Climbing (HC) local optimization. Experiments based on multi-temporal GF-2 imagery from 2018 to 2023 demonstrated that MPGH-FS could reduce the feature dimension from 232 to 9, and it achieved the highest Overall Accuracy (OA) of 85.55% and a Kappa coefficient of 0.75 in full-scene classification, with training and inference times limited to 6 s and 1 min, respectively. Cross-temporal transfer experiments further validated the method’s robustness to inter-annual variation within the same area, with classification accuracy fluctuations remaining below 4% across different years, outperforming comparative methods. These results confirm that MPGH-FS offers significant advantages in feature compression, classification performance, and temporal adaptability, providing a robust technical foundation for efficient and accurate multi-temporal remote sensing classification. Full article

(This article belongs to the Special Issue Remote Sensing Image Processing, Analysis and Application)

► Show Figures

Figure 1

15 pages, 4689 KB

Open AccessArticle

The Applicability of a Complete Archive of Keyhole Imagery for Land-Use Change Detection in China (1960–1984)

by Hao Li, Tao Wang and Jinyu Sun

Sensors 2025, 25(10), 3147; https://doi.org/10.3390/s25103147 - 16 May 2025

Cited by 1 | Viewed by 1145

Abstract

Declassified Keyhole imagery partially provides multi-temporal coverage that can support land-use change analysis. However, the volume of commercial (paid) Keyhole data is much larger than that of free imagery, and the extent to which commercial data can enhance the application of Keyhole imagery for land-use change analysis remains unknown. In this work, the full archive of Keyhole images for China was obtained from the USGS to identify regions with repeated coverage automatically by using the ArcPy library in Python. The years from 1960 to 1984 were divided into five 5-year periods (T1, 1960~1964; T2, 1965~1969; T3, 1970~1974; T4, 1975~1979; and T5, 1980~1984). The Keyhole images’ metadata, including resolution, acquisition time, and image extent, were utilized to classify the images into meter level (C1), five-meter level (C2), and ten-meter level (C3). The spatial distributions of combinations of imagery at different resolutions for each period and the repeated coverage of imagery at each resolution across the five periods were investigated to extract repeated-coverage regions. The coverage proportions were nearly 100% for C1 imagery for the T3, T4, and T5 periods; C2 for T1 and T2; and C3 for T1 and T3. The T3 period featured extensive coverage at all three resolutions (66%). The T1 period was mainly covered by C2/C3 (93%), and T4 had C1/C3 coverage (68%). In contrast, T2 relied primarily on C2 imagery (100%), and T5 was only covered by C1 (96%). For C1 imagery, land-use changes in almost all areas in China in the T3/T4/T5 time span could be detected, and for C2 and C3 images, the corresponding time spans were T1/T2 and T1/T3. Although this study focused on repeated-coverage area detection within China, the methodology and Python codes provided allow for the implementation of an automated process for land-use change detection from the 1960s to the 1980s in other regions worldwide. Full article

(This article belongs to the Special Issue Remote Sensing Image Processing, Analysis and Application)

► Show Figures

Figure 1

22 pages, 21322 KB

Open AccessEditor’s ChoiceArticle

Detecting Burn Severity and Vegetation Recovery After Fire Using dNBR and dNDVI Indices: Insight from the Bosco Difesa Grande, Gravina in Southern Italy

by Somayeh Zahabnazouri, Patrick Belmont, Scott David, Peter E. Wigand, Mario Elia and Domenico Capolongo

Sensors 2025, 25(10), 3097; https://doi.org/10.3390/s25103097 - 14 May 2025

Cited by 16 | Viewed by 4364

Abstract

Wildfires serve a paradoxical role in landscapes—supporting biodiversity and nutrient cycling while also threatening ecosystems and economies, especially as climate change intensifies their frequency and severity. This study investigates the impact of wildfires and vegetation recovery in the Bosco Difesa Grande forest in southern Italy, focusing on the 2017 and 2021 fire events. Using Google Earth Engine (GEE) accessed in January 2025, we applied remote sensing techniques to assess burn severity and post-fire regrowth. Sentinel-2 imagery was used to compute the Normalized Burn Ratio (NBR) and Normalized Difference Vegetation Index (NDVI); burn severity was derived from differenced NBR (dNBR), and vegetation recovery was monitored via differenced NDVI (dNDVI) and multi-year NDVI time series. We uniquely compare recovery across four zones with different fire histories—unburned, single-burn (2017 or 2021), and repeated-burn (2017 and 2021)—providing a novel perspective on post-fire dynamics in Mediterranean ecosystems. Results show that low-severity zones recovered more quickly than high-severity areas. Repeated-burn zones experienced the slowest and least complete recovery, while unburned areas remained stable. These findings suggest that repeated fires may shift vegetation from forest to shrubland. This study highlights the importance of remote sensing for post-fire assessment and supports adaptive land management to enhance long-term ecological resilience. Full article

(This article belongs to the Special Issue Remote Sensing Image Processing, Analysis and Application)

► Show Figures

Journal Menu

Journal Browser

Remote Sensing Image Processing, Analysis and Application

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (10 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI