Affiliation:
1. Electronics Information Engineering College, Changchun University, Changchun 130022, China
Abstract
Due to the limited memory and computing resources in the real application of target detection, the method is challenging to implement on mobile and embedded devices. In order to achieve the balance between detection accuracy and speed in pedestrian-intensive scenes, an improved lightweight dense pedestrian detection algorithm GS-YOLOv5 (GhostNet GSConv- SIoU) is proposed in this paper. In the Backbone section, GhostNet is used to replace the original CSPDarknet53 network structure, reducing the number of parameters and computation. The CBL module is replaced with GSConv in the Head section, and the CSP module is replaced with VoV-GSCSP. The SloU loss function is used to replace the original IoU loss function to improve the prediction box overlap problem in dense scenes. The model parameters are reduced by 40% and the calculation amount is reduced by 64% without losing the average accuracy, and the detection accuracy is improved by 0.5%. The experimental results show that the GS-YOLOv5 can detect pedestrians more effectively under limited hardware conditions to cope with dense pedestrian scenes, and it is suitable for the online real-time detection of pedestrians.
Funder
Jilin Provincial Department of Education
Jilin Provincial Natural Science Foundation of China
Subject
Fluid Flow and Transfer Processes,Computer Science Applications,Process Chemistry and Technology,General Engineering,Instrumentation,General Materials Science
Reference33 articles.
1. Lan, X., Zhang, S., and Yuen, P.C. (2016, January 9–15). Robust Joint Discriminative Feature Learning for Visual Tracking. Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence (IJCAI-16), New York, NY, USA.
2. Cross-domain person reidentification using domain adaptation ranking svms;Ma;IEEE Trans. Image Process.,2015
3. Supervised spatio-temporal neighborhood topology learning for action recognition;Ma;IEEE Trans. Circuits Syst. Video Technol.,2013
4. Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014, January 23–28). Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.
5. Girshick, R. (2015, January 7–13). Fast r-cnn. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.
Cited by
7 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