点击次数：

发表刊物：REMOTE SENSING

关键字：geological landslide monitoring; 3D deformation estimation; UAV; feature extraction;3D point matching; real-scene 3D model

摘要：This study proposes a three-dimensional (3D) deformation estimation framework based on the integration of shape and texture information for real-scene 3D model matching, effectively addressing the issue of deformation assessment in large-scale geological landslide areas. By extracting and merging the texture and shape features of matched points, correspondences between points in multi-temporal real-scene 3D models are established, resolving the difficulties faced by existing methods in achieving robust and high-precision 3D point matching over landslide areas. To ensure the complete coverage of the geological disaster area while enhancing computational efficiency during deformation estimation, a voxel-based thinning method to generate interest points is proposed. The effectiveness of the proposed method is validated through tests on a dataset from the Lijie north hill geological landslide area in Gansu Province, China. Experimental results demonstrate that the proposed method significantly outperforms existing classic and advanced methods in terms of matching accuracy metrics, and the accuracy of our deformation estimates is close to the actual measurements obtained from GNSS stations, with an average error of only 2.2 cm.

合写作者：Zhuangqun Niu,Xiaokun Zhu,Yansong Duan,Tao Ke,Zuxun Zhang

通讯作者：Pengjie Tao

是否译文：否

发表时间：2024-08-27

收录刊物：SCI、EI