Accelerate Point Cloud Structuring for Deep Neural Networks via Fast Spatial-Searching Tree

doi:10.1109/TCSVT.2024.3491495

	Accelerate Point Cloud Structuring for Deep Neural Networks via Fast Spatial-Searching Tree
	Zhan, Jinyu 1; Zou, Shiyu 1; Jiang, Wei 1; Zhang, Youyuan 1; Peng, Suidi 1; Wang, Ying 2
	2025-03-01
发表期刊	IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
ISSN	1051-8215
卷号	35 期号:3 页码:2570-2585
摘要	Due to the disorder of points, point clouds need to be structured by sampling and neighbor query before feeding to Deep Neural Networks (DNNs). Structuring point clouds costs high computation overhead, which limits the deployment of DNNs on embedded devices such as autonomous vehicles and robots. To address this problem, we design a novel data structure, i.e., Fast Spatial-Searching Tree (FSSTree), to accelerate point cloud structuring for DNNs on embedded devices. The FSSTree is constructed based on density distribution of point clouds to achieve semantic segmentation, which can guarantee that points with similar spatial positions are stored in adjacent storage sets. Based on FSSTree, we propose a point-sparsity-aware sampling method and a leafwise k-nearest neighbor query method to reduce the computation overhead of structuring point clouds. Meanwhile, the point-sparsity-aware sampling method achieves fair sampling on both dense and sparse parts, which can overcome the nonuniform distribution of point clouds caused by occlusion, lighting and other factors. The leafwise k-nearest neighbor query method skips a large number of dissimilar points to quickly obtain the neighbor points, which can significantly reduce the search scope. We also present a layerwise self-pruning algorithm to automatically adjust the FSSTree after each layer's operation to match the hierarchical architecture of DNNs. Finally, we conduct extensive experiments on KITTI, S3DIS and ModelNet40 datasets and three devices (including an RTX 3090 server, a Jetson AGX Xavier and an Apple M2). The experimental results demonstrate the efficiency of our approach, which can reduce the time overhead by up to 97.46% compared with the other five methods. The code is released at https://github.com/EmbeddedAILab-UESTC/fsstree.
关键词	Deep neural networks point cloud structuring fast spatial-searching tree sampling neighbor query acceleration Deep neural networks point cloud structuring fast spatial-searching tree sampling neighbor query acceleration
DOI	10.1109/TCSVT.2024.3491495
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[62072076] ; National Natural Science Foundation of China[62372087] ; Research Fund of State Key Laboratory of Processors[CLQ202310]
WOS研究方向	Engineering
WOS类目	Engineering, Electrical & Electronic
WOS记录号	WOS:001439628600011
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/40711
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Zhan, Jinyu
作者单位	1.Univ Elect Sci & Technol China, Sch Informat & Software Engn, Chengdu 610054, Peoples R China 2.Chinese Acad Sci, State Key Lab Comp Architecture, Inst Comp Technol, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Zhan, Jinyu,Zou, Shiyu,Jiang, Wei,et al. Accelerate Point Cloud Structuring for Deep Neural Networks via Fast Spatial-Searching Tree[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2025,35(3):2570-2585.
APA	Zhan, Jinyu,Zou, Shiyu,Jiang, Wei,Zhang, Youyuan,Peng, Suidi,&Wang, Ying.(2025).Accelerate Point Cloud Structuring for Deep Neural Networks via Fast Spatial-Searching Tree.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,35(3),2570-2585.
MLA	Zhan, Jinyu,et al."Accelerate Point Cloud Structuring for Deep Neural Networks via Fast Spatial-Searching Tree".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 35.3(2025):2570-2585.