P. Jiang, X. Deng, L. Wang, Z. Chen and S. Zhang, "Hypergraph Representation for Detecting 3D Objects from Noisy Point Clouds," in IEEE Transactions on Knowledge and Data Engineering, doi: 10.1109/TKDE.2022.3179608. (CCF A类)
发布时间：2024-03-13
点击次数：
发表刊物：IEEE Transactions on Knowledge and Data Engineering
摘要：Abstract—It is challenging to detect 3D objects from noise point clouds by Graph Neural Networks (GNNs), though graph-based methods have shown promising results in 3D classifications. Since strong robustness against noise is offered by hypergraph, a relative paradigm named HyperGraph Construction-Compression-Conversion (HG3C) is proposed for detecting 3D objects from noise point clouds. Our method presents the capacity of reducing graph redundancy and capturing the variances from multiple features, by preencoding the graph, to improve the graph representations in point clouds. A fused graph neural network is further designed to predict the shape and category of the target in converted graphs. The experiments, on both the KITTI and Nuscene, show that the proposed approach achieves leading accuracy. Our results demonstrate the potential of using the hypergraph transformation to extract and compress point cloud information from noisy point clouds.
备注：http://faculty.csu.edu.cn/dengxiaoheng/zh_CN/lwcg/10445/content/49299.htm
是否译文：否
附件：
10-Hypergraph_Representation_for_Detecting_3D_Objects_From_Noisy_Point_Clouds.pdf
上一条： X. Deng, B. Chen, X. Chen, X. Pei, S. Wan and S. K. Goudos, "Trusted Edge Computing System Based on Intelligent Risk Detection for Smart IoT," in IEEE Transactions on Industrial Informatics, doi: 10.1109/TII.2023.3245681.(中科院 1区)
下一条： X. Pei, X. Deng, S. Tian, L. Zhang and K. Xue, "A Knowledge Transfer-Based Semi-Supervised Federated Learning for IoT Malware Detection," in IEEE Transactions on Dependable and Secure Computing, vol. 20, no. 3, pp. 2127-2143, 1 May-June 2023, doi: 10.1109/TDSC.2022.3173664. (CCF A类)