An object detection research method based on CARLA simulation. Issue 1 (June 2021)

• Record Type: Journal Article
• Authors: Gao, Weihua; Tang, Jiakai; Wang, Taotao
• Is Part Of: Journal of physics. Volume 1948:Issue 1(2021)
• Publication Date: 2021-06
• Subjects: Physics -- Congresses; 530.5
• DOI: 10.1088/1742-6596/1948/1/012163
• Languages: English
• ISSNs: 1742-6588

Abstract

Abstract: At present, the research of object detection in automatic driving is mainly based on the actual automatic driving vehicle. This method is expensive, less feasible, and difficult to test. Based on CARLA, we proposed an efficient and low-cost object detection method, which can overcome the shortcomings of the actual vehicle research. In this paper, firstly, we obtained images from CARLA, and then the data set is obtained by cleaning and labeling the image. Finally, based on the data set established in this paper, we train the models of YOLOv4, CenterNet and Faster-RCNN respectively, and make a comparative study on the test set. The results show that YOLOv4 has the best detection effect without special optimization method.