A Multi-Scale Traffic Object Detection Algorithm for Road Scenes Based on Improved YOLOv5
-
Published:2023-02-09
Issue:4
Volume:12
Page:878
-
ISSN:2079-9292
-
Container-title:Electronics
-
language:en
-
Short-container-title:Electronics
Author:
Li Ang1ORCID, Sun Shijie1, Zhang Zhaoyang1, Feng Mingtao23, Wu Chengzhong3, Li Wang4
Affiliation:
1. School of Information Engineering, Chang’an University, Xi’an 710064, China 2. School of Computer Science and Technology, Xidian University, Xi’an 710000, China 3. National Engineering Laboratory of Robot Visual Perception and Control Technology, Hunan University, Changsha 410000, China 4. CRRC Zhuzhou Electric Locomotive Co., Ltd., Zhuzhou 412000, China
Abstract
Object detection in road scenes is a task that has recently become popular and it is also an important part of intelligent transportation systems. Due to the different locations of cameras in the road scenes, the size of the traffic objects captured varies greatly, which imposes a burden on the network optimization. In addition, in some dense traffic scenes, the size of the traffic objects captured is extremely small and it is easy to miss detection and to encounter false detection. In this paper, we propose an improved multi-scale YOLOv5s algorithm based on the YOLOv5s algorithm. In detail, we add a detection head for extremely small objects to the original YOLOv5s model, which significantly improves the accuracy in detecting extremely small traffic objects. A content-aware reassembly of features (CARAFE) module is introduced in the feature fusion part to enhance the feature fusion. A new SPD-Conv CNN Module is introduced instead of the original convolutional structure to enhance the overall computational efficiency of the model. Finally, the normalization-based attention module (NAM) is introduced, allowing the model to focus on more useful information during training and significantly improving detection accuracy. The experimental results demonstrate that compared with the original YOLOv5s algorithm, the detection accuracy of the multi-scale YOLOv5s model proposed in this paper is improved by 7.1% on the constructed diverse traffic scene datasets. The improved multi-scale YOLOv5s algorithm also maintains the highest detection accuracy among the current mainstream object detection algorithms and is superior in accomplishing the task of detecting traffic objects in complex road scenes.
Funder
National Natural Science Foundation of China Central Universities Basic Research Special Funds
Subject
Electrical and Electronic Engineering,Computer Networks and Communications,Hardware and Architecture,Signal Processing,Control and Systems Engineering
Reference39 articles.
1. Vehicle Detection and Recognition in Greyscale Imagery;Matthews;IFAC Proc. Vol.,1995 2. An Extended Filtered Channel Framework for Pedestrian Detection;You;IEEE Trans. Intell. Transp. Syst.,2018 3. Walk, S., Majer, N., Schindler, K., and Schiele, B. (2010, January 13–18). New features and insights for pedestrian detection. Proceedings of the 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA. 4. Ren, S., He, K., Girshick, R., and Sun, J. (2015). Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. Adv. Neural Inf. Process. Syst., 28. 5. Joseph, R., Santosh, D., Ross, G., and Ali, F. (2016, January 27–30). You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.
Cited by
24 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|