In this paper, we present a client-server system for 3D scene change detection. A 3D scene point cloud which stored on the server is reconstructed by (structure-from-motion) SfM technique in advance. On the other hand...In this paper, we present a client-server system for 3D scene change detection. A 3D scene point cloud which stored on the server is reconstructed by (structure-from-motion) SfM technique in advance. On the other hand, the client system in tablets captures query images and sent them to the server to estimate the change area. In order to find region of change, an existing change detection method has been applied into our system. Then the server sends detection result image back to mobile device and visualize it. The result of system test shows that the system could detect change cor- rectly.展开更多
In this paper, we proposed a method for semi-rigid changed 3D point clouds registration. We first segment the point clouds into individual segments and then the alignment energy costs of each segment are calculated. T...In this paper, we proposed a method for semi-rigid changed 3D point clouds registration. We first segment the point clouds into individual segments and then the alignment energy costs of each segment are calculated. The rough initial transformation is estimated by minimizing the energy cost using integer programming. The final registration results are obtained by rigid alignments of separated corresponded segments. Experimental result with simulated point clouds demonstrate that the concept of semi-rigid registration works well.展开更多
文摘In this paper, we present a client-server system for 3D scene change detection. A 3D scene point cloud which stored on the server is reconstructed by (structure-from-motion) SfM technique in advance. On the other hand, the client system in tablets captures query images and sent them to the server to estimate the change area. In order to find region of change, an existing change detection method has been applied into our system. Then the server sends detection result image back to mobile device and visualize it. The result of system test shows that the system could detect change cor- rectly.
文摘In this paper, we proposed a method for semi-rigid changed 3D point clouds registration. We first segment the point clouds into individual segments and then the alignment energy costs of each segment are calculated. The rough initial transformation is estimated by minimizing the energy cost using integer programming. The final registration results are obtained by rigid alignments of separated corresponded segments. Experimental result with simulated point clouds demonstrate that the concept of semi-rigid registration works well.