Multi-source remote sensing images (RSIs) can capture the complementary information of ground objects for use in semantic segmentation. However, there can be inconsistency and interference noise among the multimodal data from different sensors. Therefore, it is a challenge to effectively reduce the differences and noise between the different modalities and fully utilize their complementary features. In this paper, we propose a universal cross-fusion transformer framework (CFFormer) for the semantic segmentation of multi-source RSIs, adopting a parallel dual-stream structure to extract features separately from the different modalities. We introduce a feature correction module (FCM) that corrects the features of the current modality by combining features from the other modalities in both the spatial and channel dimensions. In the feature fusion module (FFM), we employ a multi-head cross-attention mechanism to interact globally and fuse features from the different modalities, enabling the comprehensive utilization of the complementary information in multi-source RSIs. Finally, comparative experiments demonstrate that the proposed CFFormer framework not only achieves a state-of-the-art accuracy but also exhibits outstanding robustness when compared to the current advanced networks for semantic segmentation of multi-source RSIs. Specifically, CF-Former achieves a mean intersection over union (mIOU) of 58% and an overall accuracy (OA) of 85.35% on the WHU-OPT-SAR dataset, outperforming the second-ranked network by 4.71% and 1.74%, respectively. On the Vaihingen and Potsdam datasets, CFFormer also achieves the best results, with mIoU and OA values of 84.31%/91.88% and 88.62%/92.64%, respectively. The source code is available at https://github.com/masurq/CFFormer.

Synthetic aperture radar (SAR) technology has become an important means of flood monitoring because of its large coverage, repeated observation, and all-weather and all-time working capabilities. The commonly used thresholding and change detection methods in emergency monitoring can quickly and simply detect floods. However, these methods still have some problems: (1) thresholding methods are easily affected by low backscattering regions and speckle noise; (2) changes from multi-temporal information include urban renewal and seasonal variation, reducing the precision of flood monitoring. To solve these problems, this paper presents a new flood mapping framework that combines semi-automatic thresholding and change detection. First, multiple lines across land and water are drawn manually, and their local optimal thresholds are calculated automatically along these lines from two ends towards the middle. Using the average of these thresholds, the low backscattering regions are extracted to generate a preliminary inundation map. Then, the neighborhood-based change detection method combined with entropy thresholding is adopted to detect the changed areas. Finally, pixels in both the low backscattering regions and the changed regions are marked as inundated terrain. Two flood datasets, one from Sentinel-1 in the Wharfe and Ouse River basin and another from GF-3 in Chaohu are chosen to verify the effectiveness and practicality of the proposed method.

The GaoFen-3 (GF-3) satellite is the first fully polarimetric synthetic aperture radar (SAR) satellite designed for civil use in China. The satellite operates in the C-band and has 12 imaging modes for various applications. Three fully polarimetric SAR (PolSAR) imaging modes are provided with a resolution of up to 8 m. Although polarimetric calibration (PolCAL) of the SAR system is periodically undertaken, there is still some residual distortion in the images. In order to assess the polarimetric accuracy of this satellite and improve the image quality, we analyzed the polarimetric distortion errors and performed a PolCAL experiment based on scattering properties and corner reflectors. The experiment indicates that the GF-3 images can meet the satellite’s polarimetric accuracy requirements, i.e., a channel imbalance of 0.5 dB in amplitude and ±10 degrees in phase and a crosstalk accuracy of −35 dB. However, some images still contain residual polarimetric distortion. The experiment also shows that the residual errors of the GF-3 standard images can be diminished after further PolCAL, with a channel imbalance of 0.26 dB in amplitude and ±0.2 degrees in phase and a crosstalk accuracy of −42 dB.

Most of the traditional supervised classification methods using full-polarimetric synthetic aperture radar (PolSAR) imagery are dependent on sufficient training samples, whereas the results of pixel-based supervised classification methods show a high false alarm rate due to the influence of speckle noise. In this paper, to solve these problems, an object-based supervised classification method with an active learning (AL) method and random forest (RF) classifier is presented, which can enhance the classification performance for PolSAR imagery. The first step of the proposed method is used to reduce the influence of speckle noise through the generalized statistical region merging (GSRM) algorithm. A reliable training set is then selected from the different polarimetric features of the PolSAR imagery by the AL method. Finally, the RF classifier is applied to identify the different types of land cover in the three PolSAR images acquired by different sensors. The experimental results demonstrate that the proposed method can not only better suppress the influence of speckle noise, but can also significantly improve the overall accuracy and Kappa coefficient of the classification results, when compared with the traditional supervised classification methods.

Synthetic aperture radar (SAR) is a significant application in maritime monitoring, which can provide SAR data throughout the day and in all weather conditions. With the development of artificial intelligence and big data technologies, the data-driven convolutional neural network (CNN) has become widely used in ship detection. However, the accuracy, feature visualization, and analysis of ship detection need to be improved further, when the CNN method is used. In this letter, we propose a two-stage ship detection for land-contained sea area without a traditional sea-land segmentation process. First, to decrease the possibly existing false alarms from the island, an island filter is used as the first step, and then threshold segmentation is used to quickly perform candidate detection. Second, a two-layer lightweight CNN model-based classifier is built to separate false alarms from the ship object. Finally, we discuss the CNN interpretation and visualize in detail when the ship is predicted in vertical–horizontal (VH) and vertical–vertical (VV) polarization. Experiments demonstrate that the proposed method can reach an accuracy of 99.4% and an F1 score of 0.99 based on the Sentinel-1 images for a ship with a size of less than 32 × 32.

Frequent mining activities create a series of geological and environmental problems resulting in an immeasurable loss of life and property. Adopting effective technologies that monitor the surface subsidence of mining areas reliably and accurately is necessary. Targeting problems associated with conventional distributed scatterers interferometric synthetic aperture radar (DS-InSAR) technology, we propose a DS-InSAR technology integrating unmanned aerial vehicle (UAV) photogrammetry products divided into two key technical contents: generating an external reference digital elevation model (DEM) fused with UAV DEM and refining distributed scatterers candidates (DSCs) fused with an UAV digital orthophoto map (DOM). We selected two mining areas, one in Wu’an, Hebei, and the other in Inner Mongolia, with different surface cover types, mining depths, and topographies as the research area. We used Sentinel-1A SAR images covering a mine in Wu’an from 4 November 2018 to 4 March 2019 and a mining area in Inner Mongolia from 11 June 2018 to 21 October 2018 to compare and analyze the subsidence results. We also combined these results with data from their respective field observation stations to assess accuracy. We could apply DS-InSAR technology integrated with UAV photogrammetry products to the subsidence monitoring of two mining areas with different landforms and mining characteristics. Comparing with the leveling and total station, the experimental results show that the RMSE was reduced by about 2 mm in both mining areas, and accuracy for the Wu’an region improved to a higher degree than Inner Mongolia did. Furthermore, the refinement method of DS eliminated 965 and 2948 lower-quality DSCs in the two mining areas. These demonstrate that our proposed method can effectively improve the accuracy and reliability of subsidence results from two mining areas.