Overview of LiDAR point cloud target detection methods based on deep learning

• Published in: Sensor review Vol. 42; no. 5; pp. 485 - 502
• Main Authors: Huang, Siyuan, Liu, Limin, Fu, Xiongjun, Dong, Jian, Huang, Fuyu, Lang, Ping
• Format: Journal Article
• Language: English
• Published: Bradford Emerald Publishing Limited 30.08.2022; Emerald Group Publishing Limited
• Subjects: Accuracy; Algorithms; Datasets; Deep learning; Digital mapping; Labeling; Lidar; Machine learning; Methods; Semantics; Target detection; Three dimensional models; Deep learning; Point cloud segmentation; Light detection and ranging; Automatic driving; Object detection
• ISSN: 0260-2288; 1758-6828; 0260-2288
• DOI: 10.1108/SR-01-2022-0022

Purpose The purpose of this paper is to summarize the existing point cloud target detection algorithms based on deep learning, and provide reference for researchers in related fields. In recent years, with its outstanding performance in target detection of 2D images, deep learning technology has been applied in light detection and ranging (LiDAR) point cloud data to improve the automation and intelligence level of target detection. However, there are still some difficulties and room for improvement in target detection from the 3D point cloud. In this paper, the vehicle LiDAR target detection method is chosen as the research subject. Design/methodology/approach Firstly, the challenges of applying deep learning to point cloud target detection are described; secondly, solutions in relevant research are combed in response to the above challenges. The currently popular target detection methods are classified, among which some are compared with illustrate advantages and disadvantages. Moreover, approaches to improve the accuracy of network target detection are introduced. Findings Finally, this paper also summarizes the shortcomings of existing methods and signals the prospective development trend. Originality/value This paper introduces some existing point cloud target detection methods based on deep learning, which can be applied to a driverless, digital map, traffic monitoring and other fields, and provides a reference for researchers in related fields.