An improved YOLOv3-tiny algorithm for vehicle detection in natural scenes

作     者：Bingqiang Huang Haiping Lin Zejun Hu Xinjian Xiang Jiana Yao 

作者机构：School of Automation and Electrical EngineeringZhejiang University of Science and TechnologyHangzhouChina College of Information EngineeringHangzhou Vocational&Technical CollegeHangzhouChina 

出 版 物：《IET Cyber-Systems and Robotics》 (智能系统与机器人（英文）)

年 卷 期：2021年第3卷第3期

页      面：256-264页

核心收录：

学科分类：08[工学] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：Hangzhou Science and Technology Development Plan Project Grant/Award Number:20191203B30 

主　　题：algorithm driving network 

摘      要：YOLO(You Only Look Once),as a target detection algorithm with good speed and precision,is widely used in the *** the process of driving,the vehicle image captured by the driving camera is detected and it extracts the license plate and the front part of the *** with the network structure of YOLOv3-tiny algorithm,the acquisition method of anchor box is improved by combining the Birch *** order to improve the real-time performance,the original two-scale detection is added to the multi-scale prediction of three-scale detection to ensure its ***,the experimental results show that the improved YOLOv3-tiny network structure proposed in this study can improve the performance of mean-average-precision,intersection over union and speed by 5.99%,17.52%and 48.4%,respectively,and the algorithm has certain robustness.