Litao Kang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Litao Kang has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Chaoyue Liu
Department of Space Microwave Remote Sensing System, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China
3 shared publications - Huaitao Fan
Department of Space Microwave Remote Sensing System, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, China
3 shared publications Zhimin Zhang
Department of Space Microwave Remote Sensing System, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China
3 shared publications- Zhen Chen
Department of Space Microwave Remote Sensing System, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China
2 shared publications - Heng Zhang
Department of Space Microwave Remote Sensing System, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, China
1 shared publication - Jili Wang
Department of Space Microwave Remote Sensing System, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, China
1 shared publication
Latest Publications
- Open Access
- 18 March 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (6) , 925
Spatiotemporal Prediction and Pattern Analysis of Complex Ground Deformation Fields from Multi-Temporal InSAR
Ground deformation is a major geohazard in many urban areas, requiring reliable monitoring and forecasting for hazard mitigation. Although Multi-Temporal InSAR enables high-resolution deformation monitoring, most prediction approaches rely on single-point modeling and fail to exploit spatial dependencies within deformation fields. This study proposes a spatiotemporally synchronous prediction framework for large-scale InSAR deformation fields, integrating sequence preprocessing, spatiotemporal modeling, and deformation pattern analysis. First-order differencing reduces sequence non-stationarity, while a patch-based encoder-decoder structure preserves spatial topology during dimensionality reduction. The core prediction model, built on PredRNNv2, captures the long-term spatiotemporal evolution of InSAR deformation sequences. In addition, independent component analysis (ICA) combined with K-means clustering identifies dominant deformation patterns and their geological associations. The framework is evaluated using synthetic datasets simulating multiple deformation mechanisms and Sentinel-1 InSAR time-series data over the Beijing Plain from 2015 to 2025. Results show that the model accurately captures deformation evolution and identifies transitions associated with groundwater regulation. These findings demonstrate the potential of deep spatiotemporal learning for large-scale InSAR deformation prediction and geohazard mechanism interpretation.
- 18 March 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (6) , 925
Open AccessSpatiotemporal Prediction and Pattern Analysis of Complex Ground Deformation Fields from Multi-Temporal InSAR
Ground deformation is a major geohazard in many urban areas, requiring reliable monitoring and forecasting for hazard mitigation. Although Multi-Temporal InSAR enables high-resolution deformation monitoring, most prediction approaches rely on single-point modeling and fail to exploit spatial dependencies within deformation fields. This study proposes a spatiotemporally synchronous prediction framework for large-scale InSAR deformation fields, integrating sequence preprocessing, spatiotemporal modeling, and deformation pattern analysis. First-order differencing reduces sequence non-stationarity, while a patch-based encoder-decoder structure preserves spatial topology during dimensionality reduction. The core prediction model, built on PredRNNv2, captures the long-term spatiotemporal evolution of InSAR deformation sequences. In addition, independent component analysis (ICA) combined with K-means clustering identifies dominant deformation patterns and their geological associations. The framework is evaluated using synthetic datasets simulating multiple deformation mechanisms and Sentinel-1 InSAR time-series data over the Beijing Plain from 2015 to 2025. Results show that the model accurately captures deformation evolution and identifies transitions associated with groundwater regulation. These findings demonstrate the potential of deep spatiotemporal learning for large-scale InSAR deformation prediction and geohazard mechanism interpretation.
- 19 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 23 (1545598X) , 1-5
Real-Time DEtection TRansformer Enhanced by WaveFormer and WS-GD Neck
Deep learning-based methods hold significant potential for synthetic aperture radar (SAR) target detection, but they still face numerous challenges, including difficulty extracting global contextual features for large-scale targets, significant multi-scale issues, and the problem of feature extraction of SAR targets with large aspect ratios, which hinder further performance improvement. To this end, this paper proposes a WaveFormer module, which decomposes the image through wavelet convolution and uses convolution and Transformer to process the frequency domain components they are good at, respectively, to expand the receptive field with low parameter overhead and enhance the target feature extraction ability. To address cross-layer information attenuation during feature fusion, a Gather-and-Distribute(GD) mechanism is introduced to reconstruct the Neck network, enhancing multi-scale feature fusion and detection capabilities. Furthermore, given the large aspect ratio and distinct principal axis orientation of SAR targets, a Weighted Strip-Convolution(WSConv) is proposed to effectively improve detection performance. Experiments on the largest multi-class SAR target detection dataset, SARDet-100K, demonstrate that our method achieves a mean average precision (mAP) of 61.5%, reaching state-of-the-art performance and validating its effectiveness.
- 19 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 23 (1545598X) , 1-5
Real-Time DEtection TRansformer Enhanced by WaveFormer and WS-GD Neck
Deep learning-based methods hold significant potential for synthetic aperture radar (SAR) target detection, but they still face numerous challenges, including difficulty extracting global contextual features for large-scale targets, significant multi-scale issues, and the problem of feature extraction of SAR targets with large aspect ratios, which hinder further performance improvement. To this end, this paper proposes a WaveFormer module, which decomposes the image through wavelet convolution and uses convolution and Transformer to process the frequency domain components they are good at, respectively, to expand the receptive field with low parameter overhead and enhance the target feature extraction ability. To address cross-layer information attenuation during feature fusion, a Gather-and-Distribute(GD) mechanism is introduced to reconstruct the Neck network, enhancing multi-scale feature fusion and detection capabilities. Furthermore, given the large aspect ratio and distinct principal axis orientation of SAR targets, a Weighted Strip-Convolution(WSConv) is proposed to effectively improve detection performance. Experiments on the largest multi-class SAR target detection dataset, SARDet-100K, demonstrate that our method achieves a mean average precision (mAP) of 61.5%, reaching state-of-the-art performance and validating its effectiveness.
- 18 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 23 (1545598X) , 1-5
Detecting Ships With SAR Imagery Using Spatiotemporal Fusion: A Case Study of the ESA Sentinel-1 Mission
Synthetic aperture radar (SAR) ship detection faces significant challenges in nearshore scenarios due to strong backscatter interference from land and high ship density. Conventional detectors frequently fail in such environments when land mask information is unavailable. Ports, as hubs of maritime activity, have abundant and accessible SAR data archives, making them ideal testbeds for ship detection studies. Therefore, a two-step spatiotemporal fusion-based detector is proposed, which leverages the spatiotemporal characteristics of ships in SAR time series images. In the first stage, target localization is established through spatial spectrum analysis. In the second stage, difference image analysis is applied to the candidate regions to achieve precise spatiotemporal positioning, enabling effective detection without the need for land masks. An evaluation using a two-year dataset of 60 Sentinel-1A images from the Port of Santos confirmed the method’s effectiveness and superior performance.
- 18 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 23 (1545598X) , 1-5
Detecting Ships With SAR Imagery Using Spatiotemporal Fusion: A Case Study of the ESA Sentinel-1 Mission
Synthetic aperture radar (SAR) ship detection faces significant challenges in nearshore scenarios due to strong backscatter interference from land and high ship density. Conventional detectors frequently fail in such environments when land mask information is unavailable. Ports, as hubs of maritime activity, have abundant and accessible SAR data archives, making them ideal testbeds for ship detection studies. Therefore, a two-step spatiotemporal fusion-based detector is proposed, which leverages the spatiotemporal characteristics of ships in SAR time series images. In the first stage, target localization is established through spatial spectrum analysis. In the second stage, difference image analysis is applied to the candidate regions to achieve precise spatiotemporal positioning, enabling effective detection without the need for land masks. An evaluation using a two-year dataset of 60 Sentinel-1A images from the Port of Santos confirmed the method’s effectiveness and superior performance.
- Open Access
- 9 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 18 (19391404) , 26844-26862
MRFP-DBDet: A Light-Weight Ship Detection Network Based on Multireceptive Field Partial Convolution and Dual-Branch Architecture
In recent years, the deep learning-based synthetic aperture radar (SAR) ship detection technology has been rapidly developed, and has been widely used in fishery management, maritime surveillance, maritime rescue and other fields, but there are still some challenges. For instance, the feature maps extracted by the backbone network contain substantial redundant features, and repeatedly processing these redundant features introduces significant computational redundancy and inflates the model's parameter count. Furthermore, the blurred target edges caused by SAR imaging mechanisms also degrade detection accuracy. In order to solve these problems, this paper first proposes a backbone network using multi-receptive field partial convolution (MRFPconv) to extract features. While preserving the quality of backbone feature maps, our approach eliminates significant computational redundancy and reduces the parameter count. Subsequently, a Neck network with Bi-directional Concatenation (BiC) modules and reparameterizable modules, Reparameterizable Bi-directional Path Aggregation Network (RepBi-PAN), was adopted. This architecture reduces network parameters while incorporating shallower features, thereby enhancing the network's detection capabilities. Finally, this paper uses expert experience to design a ship contour extraction method based on image morphology. The extracted contours and a specially designed dual-branch network architecture with a channel attention mechanism are used to further enhance the network's detection capability. A lot of experiments are carried out on the SAR ship detection data sets HRSID and SSDD. MRFP-DBDet achieves a mAP value of 69.3% and an ${F_{1}}$ of 0.895 on the HRSID dataset, and a mAP value of 74.6% and an ${F_{1}}$ of 0.975 on the SSDD dataset, with a model parameter size of only 4.135M. The experimental results demonstrate that the algorithm achieves state-of-the-art detection performance among SAR ship detection methods with comparable parameter counts.
- 9 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 18 (19391404) , 26844-26862
Open AccessMRFP-DBDet: A Light-Weight Ship Detection Network Based on Multireceptive Field Partial Convolution and Dual-Branch Architecture
In recent years, the deep learning-based synthetic aperture radar (SAR) ship detection technology has been rapidly developed, and has been widely used in fishery management, maritime surveillance, maritime rescue and other fields, but there are still some challenges. For instance, the feature maps extracted by the backbone network contain substantial redundant features, and repeatedly processing these redundant features introduces significant computational redundancy and inflates the model's parameter count. Furthermore, the blurred target edges caused by SAR imaging mechanisms also degrade detection accuracy. In order to solve these problems, this paper first proposes a backbone network using multi-receptive field partial convolution (MRFPconv) to extract features. While preserving the quality of backbone feature maps, our approach eliminates significant computational redundancy and reduces the parameter count. Subsequently, a Neck network with Bi-directional Concatenation (BiC) modules and reparameterizable modules, Reparameterizable Bi-directional Path Aggregation Network (RepBi-PAN), was adopted. This architecture reduces network parameters while incorporating shallower features, thereby enhancing the network's detection capabilities. Finally, this paper uses expert experience to design a ship contour extraction method based on image morphology. The extracted contours and a specially designed dual-branch network architecture with a channel attention mechanism are used to further enhance the network's detection capability. A lot of experiments are carried out on the SAR ship detection data sets HRSID and SSDD. MRFP-DBDet achieves a mAP value of 69.3% and an ${F_{1}}$ of 0.895 on the HRSID dataset, and a mAP value of 74.6% and an ${F_{1}}$ of 0.975 on the SSDD dataset, with a model parameter size of only 4.135M. The experimental results demonstrate that the algorithm achieves state-of-the-art detection performance among SAR ship detection methods with comparable parameter counts.