An Application of RGBD-Based Skeleton Reconstruction for Pedestrian Detection and Occlusion Handling  

作　　者：Ziyuan Liu Ziyuan Liu(James Watt School of Engineering, University of Glasgow, Glasgow, UK)

机构地区：[1]James Watt School of Engineering, University of Glasgow, Glasgow, UK

出　　处：《Journal of Computer and Communications》2024年第1期147-161,共15页电脑和通信（英文）

摘　　要：This study explores the challenges posed by pedestrian detection and occlusion in AR applications, employing a novel approach that utilizes RGB-D-based skeleton reconstruction to reduce the overhead of classical pedestrian detection algorithms during training. Furthermore, it is dedicated to addressing occlusion issues in pedestrian detection by using Azure Kinect for body tracking and integrating a robust occlusion management algorithm, significantly enhancing detection efficiency. In experiments, an average latency of 204 milliseconds was measured, and the detection accuracy reached an outstanding level of 97%. Additionally, this approach has been successfully applied in creating a simple yet captivating augmented reality game, demonstrating the practical application of the algorithm.This study explores the challenges posed by pedestrian detection and occlusion in AR applications, employing a novel approach that utilizes RGB-D-based skeleton reconstruction to reduce the overhead of classical pedestrian detection algorithms during training. Furthermore, it is dedicated to addressing occlusion issues in pedestrian detection by using Azure Kinect for body tracking and integrating a robust occlusion management algorithm, significantly enhancing detection efficiency. In experiments, an average latency of 204 milliseconds was measured, and the detection accuracy reached an outstanding level of 97%. Additionally, this approach has been successfully applied in creating a simple yet captivating augmented reality game, demonstrating the practical application of the algorithm.

关 键 词：AR Pedestrian Detection Occlusion Management RGB-D Azure Kinect UNITY 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]