التفاصيل البيبلوغرافية
| العنوان: |
SC-CNN: LiDAR point cloud filtering CNN under slope and copula correlation constraint. |
| المؤلفون: |
Chen, Ruixing1 (AUTHOR) 19081001006@mails.guet.edu.cn, Wu, Jun1 (AUTHOR) wujun93161@163.com, Zhao, Xuemei1 (AUTHOR) zhaoxm@guet.edu.cn, Luo, Ying1 (AUTHOR), Xu, Gang2 (AUTHOR) xugang@nimte.ac.cn |
| المصدر: |
ISPRS Journal of Photogrammetry & Remote Sensing. Jun2024, Vol. 212, p381-395. 15p. |
| مصطلحات موضوعية: |
*POINT cloud, *LIDAR, *INTRACLASS correlation, *POINT set theory, *INFORMATION networks, *CONFIDENCE intervals |
| مستخلص: |
To tackle the issue of lack of semantic consistency between ground and non-ground points, as well as the damage to the integrity of terrain boundary information during network downsampling, we developed a Semantic Consistency-Convolutional Neural Network (SC-CNN) to improve the precision of point cloud filtering under complex terrain conditions. The novel aspects include: (1) farthest point sampling (FPS) with slope constraints, which enhances terrain contour preservation through adaptive subblock partitioning and slope-based sampling; (2) intra-class feature enhancement via copula correlation and attention mechanisms, improving the network's ability to distinguish between ground and non-ground points by focusing on intra-class feature consistency and inter-class differences; and (3) filter error correction using copula correlation and confidence intervals. refining filtering accuracy by adjusting for negatively correlated point sets. Tested on the ISPRS and 3D Vaihingen datasets, SC-CNN notably outperformed existing methods, reducing the mean total error (MT.E) by 0.17% and 1.93%, respectively, thereby significantly enhancing point-cloud filtering accuracy under complex terrain conditions. [ABSTRACT FROM AUTHOR] |
| قاعدة البيانات: |
Academic Search Index |