In this study, small baseline subsets interferometric synthetic aperture radar (SBAS-InSAR) was used to monitor the surface deformation of an area of 88 km 2 centered on the Xiwang Road ground fissure in Shunyi District, Beijing, to clarify the relationship between the surface deformation and the factors affecting the ground fissure activity. To reduce the errors due to overlap and contraction caused by radar-side looking imaging, we used a combination of ascending and descending orbit data to carry out the inversion of surface deformation in the study area. Thirty-seven images of Sentinel-1 ascending data from May 2017 to May 2020 and 12 images of descending data from December 2018 to December 2019 were selected. We also selected two Landsat 8 OLI images to detect the land cover changes in the study area based on support vector machine (SVM)-supervised classification, so as to examine the effects of human engineering activities on the ground fissure displacement activity. Finally, combining the results of SBAS-InSAR and land cover change detection, we explored in detail the factors affecting the activity of the Xiwang Road ground fissure to provide a scientific basis and technical reference for the prevention and treatment of ground fissures.
Predicting an agent's future trajectory is a challenging task given the complicated stimuli (environmental/inertial/social) of motion. Prior works learn individual stimulus from different modules and fuse the representations in an end-to-end manner, which makes it hard to understand what are actually captured and how they are fused. In this work, we borrow the notion of potential field from physics as an interpretable and unified representation to model all stimuli. This allows us to not only supervise the intermediate learning process, but also have a coherent method to fuse the information of different sources. From the generated potential fields, we further estimate future motion direction and speed, which are modeled as Gaussian distributions to account for the multi-modal nature of the problem. The final prediction results are generated by recurrently moving past location based on the estimated motion direction and speed. We show state-of-the-art results on the ETH, UCY, and Stanford Drone datasets.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.