期刊
IEEE SENSORS JOURNAL
卷 22, 期 4, 页码 3358-3369出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JSEN.2021.3138736
关键词
Point cloud compression; Cameras; Sensors; Roads; Streaming media; Feature extraction; Visualization; Event camera; traffic detection; feature analysis; shadow removal
资金
- National Natural Science Foundation of China [61773245, 61806113, 61873048, 91848206, 61973200, 62073199]
- Taishan Scholarship Construction Engineering, Shandong Provincial Natural Science Foundation [ZR2019QF017]
- 2019 Science and Technology Project of West Coast New Area of Qingdao [2019-32]
Event cameras have wide applications in traffic flow detection due to their accurate identification of moving targets and insensitivity to stationary targets. In this study, an event camera is used in a roadside scenario to collect point cloud data, and a method for traffic target identification and shadow removal based on feature analysis is proposed. Experimental results show significant differences among different traffic targets, with the proposed method achieving a high accuracy of 96.5%.
Event cameras have a wide range of applications in the field of traffic flow detection owing to their ability to accurately identify moving targets while being insensitive to stationary targets. In this study, an event camera is installed in a roadside scenario to collect the point cloud data of moving targets. For traffic identification, the geometrical, quantitative and Gaussian projection characteristics of the point clouds for motor/non-motor vehicles and pedestrians are extracted, and their feature distributions are analyzed. Furthermore, to address the problem of shadow noise caused by sunlight, a shadow removal method based on feature similarity is proposed considering the point cloud distribution characteristics. Experimental results show that there are significant differences in the length-width ratio, pixel points, horizontal and vertical projection features among different traffic targets specified in vehicles, non-motor vehicles and pedestrians. In addition, the proposed shadow removal scheme demonstrates high accuracy of 96.5%, and the standard deviation is 1.3%.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据