Improving the Vehicle Small Object Detection Algorithm of Yolov5

Yuanyuan Liu; Jianlin Zhu; Haili Ma

doi:10.46604/ijeti.2024.13717

Authors

Yuanyuan Liu Engineering Innovation College (Engineering Training Center), Shanghai Institute of Technology, Shanghai, 201418, China
Jianlin Zhu Engineering Innovation College (Engineering Training Center), Shanghai Institute of Technology, Shanghai, 201418, China
Haili Ma Engineering Innovation College (Engineering Training Center), Shanghai Institute of Technology, Shanghai, 201418, China

DOI:

https://doi.org/10.46604/ijeti.2024.13717

Keywords:

object detection, yolov5, autonomous driving, deep learning, attention mechanism

Abstract

To address the problems of low accuracy and poor robustness in vehicle small object detection for autonomous driving tasks, this study aims to propose an improved vehicle small object detection algorithm model based on YOLOv5. Firstly, some convolutions in the backbone network are replaced with receptive field attention convolutions, and the weights of the convolution kernels are dynamically assigned based on the importance of image features to ensure the extraction of important features. Secondly, adding a channel attention mechanism to the backbone network enhances the attention to small target features. Finally, the Focal-EIoU loss function is introduced to increase the attention on high-quality samples in the regression stage of object detection boxes. When the model is applied to the small object test set of the KITTI dataset, the precision rate, recall rate and mean average precision are 88.5%, 82.8%, and 84.9%, respectively, and the frame processing rate reaches 87.83FPS.

References

J. F. Yang, X. Q. Wang, H. Lin, L. X. Li, Y. Y. Yang, K. C. Li, et al., “Review of One-Stage Vehicle Detection Algorithms Based on Deep Learning,” Computer Engineering and Applications, vol. 58, no. 7, pp. 55-67, 2022.

S. Zhai, D. Shang, S. Wang, and S. Dong, “DF-SSD: An Improved SSD Object Detection Algorithm Based on DenseNet and Feature Fusion,” IEEE Access, vol. 8, pp. 24344-24357, 2020.

U. Sirisha, S. P. Praveen, P. N. Srinivasu, P. Barsocchi, and A. K. Bhoi, “Statistical Analysis of Design Aspects of Various YOLO-Based Deep Learning Models for Object Detection,” International Journal of Computational Intelligence Systems, vol. 16, article no. 126, 2023.

G. Oreski, “YOLO* C—Adding Context Improves YOLO Performance,” Neurocomputing, vol. 555, article no. 126655, August 2023.

C. H. Kang and S.Y. Kim, “Real-time Object Detection and Segmentation Technology: An Analysis of the YOLO Algorithm,” JMST Advances, vol. 5, no. 2, pp. 69-76, 2023.

A. Bochkovskiy, C. Y. Wang, and H. Y. M. Liao, “YOLOv4:Optimal Speed and Accuracy of Object Detection,” arXiv preprint arXiv:2004.10934, 2004.

N. Arora, Y. Kumar, R. Karkra, and M. Kumar, “Automatic Vehicle Detection System in Different Environment Conditions Using Fast R-CNN,” Multimedia Tools and Applications, vol. 81, no. 13, pp. 18715-18735, 2022.

R. X. Li, J. Y. Yu, F. Li, R. T. Yang, Y. D. Wang, and Z. H. Peng, “Automatic Bridge Crack Detection Using Unmanned Aerial Vehicle and Faster R-CNN,” Construction and Building Materials, vol. 362, article no. 129659, January 2023.

Y. J. Ma, Y. T. Ma, S. S. Cheng, and Y. D. Ma, “Road Vehicle Detection Method Based on Improved YOLO v3 Model and Deep-SORT Algorithm,” Journal of Traffic and Transportation Engineering, vol. 21, no. 2, pp. 222-231, August 2021.

X. D. Dong, S. Yan, and C. Q. Duan, “A Lightweight Vehicles Detection Network Model Based on YOLOv5,” Engineering Applications of Artificial Intelligence, vol. 113, article no. 104914, August 2022.

J. R. Liang, Z. Chen, G. J. Dong, Q. Chen, and Y. L. Xu, “Vehicle Detection Based on Ghost Convolution and Channel Attention Mechanism Cascade Structure,” Journal of Tianjin University (Science and Technology), vol. 56, no. 02, pp. 193-199, Feburary 2023.

M. A. Ahmed, S. A. Althubiti, V. H. C. de Albuquerque, M. C. dos Reis, C. Shashidhar, T. S. Murthy, et al., “Fuzzy Wavelet Neural Network Driven Vehicle Detection on Remote Sensing Imagery,” Computers and Electrical Engineering, vol. 109, Part A, article no. 108765, July 2023.

X. H. Kong, Y, Zhang, S. T. Tu, C. Xu and W. Yang, “Vehicle Detection in High-Resolution Aerial Images with Parallel RPN and Density-Assigner,” Remote Sensing, vol. 15, no. 6, article no. 1659, March 2023.

X. D. Dong, S. Yan, and C. Q. Duan, “A Lightweight Vehicles Detection Network Model Based on YOLOv5,” Engineering Applications of Artificial Intelligence, vol. 113, article no. 104914, August 2022.

C. Y. Wang, H. Y. M. Liao, Y. H. Wu, P. Y. Chen, J. W. Hsieh, and I. H. Yeh, “CSPNet:A New Backbone That Can Enhance Learning Capability of CNN,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, IEEE Press, pp. 390-391, 2020.

Y. S. Tan, K. M. Lim, C. Tee, C. P. Lee, and C. Y. Low, “Convolutional Neural Network with Spatial Pyramid Pooling for Hand Gesture Recognition,” Neural Computing and Applications, vol. 33, pp. 5339-5351, 2021.

Y. Zhang, H. F. Zhang, Q. Q. Huang, Y. Han, and M. H. Zhao, “DsP-YOLO: An Anchor-Free Network with DsPAN for Small Object Detection of Multiscale Defects,” Expert Systems with Applications, vol. 241, article no. 122669, May 2024.

X. Zhang, C. Liu, D. Yang, T. Song, Y. Ye, K. Li, and Y. Song, “RFAConv: Innovating spatial attention and standard convolutional operation,” arXiv preprint arXiv:2304.03198, 2023.

J. Hu, L. Shen, S. Albanie, G. Sun, and E.H. Wu, “Squeeze-and-Excitation Networks,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 42, no. 8, pp. 2011-2023, August 2020.

Y. F. Zhang, W. Ren, Z. Zhang, Z. Jia, L.Wang, and T. Tan, “Focal and Efficient IoU Loss for Accurate Bounding Box Regression,” Neurocomputing, vol. 506, pp. 146-157, September 2022.

Improving the Vehicle Small Object Detection Algorithm of Yolov5

Authors

DOI:

Keywords:

Abstract

References

Downloads

Published

How to Cite

Issue

Section

License

Make a Submission

scopus-citescore

counter