Real-Time Roadside 3-D Spatial Perception With LiDAR AIoT: An Edge-Cloud-Terminal Collaborative Sensing Prototype

作     者：Xiao, Wen Li, Peiguang Tang, Miao Song, Chengwen Yu, Dianyu Liu, Hanlin Chen, Dong Chen, Nengcheng 

作者机构：China Univ Geosci Sch Geog & Informat Engn Wuhan 430074 Peoples R China China Univ Geosci Natl Engn Res Ctr Geog Informat Syst Wuhan 430074 Peoples R China China Univ Geosci Sch Geog & Informat Engn Wuhan 430074 Peoples R China Wuhan Univ State Key Lab Informat Engn Surveying Mapping & Re Wuhan 430074 Peoples R China 

出 版 物：《IEEE INTERNET OF THINGS JOURNAL》 (IEEE Internet Things J.)

年 卷 期：2025年第12卷第9期

页      面：12624-12639页

核心收录：

学科分类：0810[工学-信息与通信工程] 0808[工学-电气工程] 08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：National Natural Science Foundation of China 

主　　题：Augmented Intelligence of Things (AIoT) edge-cloud-terminal collaboration light detection and ranging (LiDAR) spatial perception 

摘      要：In vehicle-road cooperation, the advancement of vehicle-side autonomous driving is hindered by bottlenecks, such as limited sensing range, computational power, and environmental adaptability. Collaboration with roadside units is essential for achieving more accurate and complex spatial perception. This study presents a new prototype to enhancing spatial perception in road environments within Augmented Intelligence of Things (AIoT) systems using light detection and ranging (LiDAR) technology. Unlike traditional AIoT systems, which rely on cameras and struggle in complex conditions, the proposed prototype uses an edge-cloud-terminal collaborative sensing model to enhance 3-D spatial perception. A notable feature of this prototype is the integration of the distance and density adaptive filtering (DDAF) method, which ensures efficient point cloud filtering at the edge, with an average F1-score of 96.03% and an average latency of 11.78 ms, demonstrating strong accuracy and low latency across various scenarios. The incorporation of DDAF further improves the mean average precision (mAP) of deep learning-based 3-D object detection on the cloud by 2.34%, reduces processing time by 83.54%, and decreases peak memory usage by 90.18%, facilitating precise 3-D spatial analysis. The final results are displayed in real-time on the terminal for visualization and interaction. The efficacy of this prototype is demonstrated through a real-world case study. This research highlights the role of LiDAR and AIoT in overcoming spatial perception challenges in vehicle-road cooperation, leading to safer, more efficient transportation solutions.