A Lightweight Improved YOLOv5s Model for Vehicle Detection

Si Shen; Shimin Qu; Xingfeng Wang; Wei Zheng; Ziqi Wang

doi:10.6919/ICJE.202409_10(9).0005

Authors

Si Shen
Shimin Qu
Xingfeng Wang
Wei Zheng
Ziqi Wang

DOI:

https://doi.org/10.6919/ICJE.202409_10(9).0005

Keywords:

Object Detection; YOLOv5s; Lightweight Network; GhostNet; CBAM.

Abstract

With the rapid development of computer vision and deep learning methods, object detection has emerged as a hot research topic in fields such as autonomous driving, robot navigation, and intelligent transportation. To address the issues of numerous parameters and slow detection speed associated with traditional vehicle target detection algorithms, this article introduces a lightweight YOLOv5s-based algorithm, which emphasizes its efficiency and accuracy in real-time scenarios. First, a lightweight GhostNet is incorporated for feature extraction. Subsequently, the streamlined MBConv layers are utilized to replace the traditional convolutional layers in the backbone, thus achieving a more efficient and less complex model. Finally, by integrating the CBAM attention mechanism into the neck network of YOLOv5s, the image feature information is fully utilized, thereby enhancing detection accuracy. Experimental results show that the average accuracy of this algorithm reaches 91.5%, with a 30.9% reduction in parameters. Clearly, the method proposed in this paper fulfills the real-time requirements for vehicle detection.

Downloads

Download data is not yet available.

References

Su J, An Y, Wu J, et al. Pedestrian Detection Based on Feature Enhancement in Complex Scenes[J]. Algorithms, 2024, 17(1): 39.

Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2014: 580-587.

Girshick R. Fast r-cnn[C]//Proceedings of the IEEE international conference on computer vision. 2015: 1440-1448.

Ren S, He K, Girshick R, et al. Faster r-cnn: Towards real-time object detection with region proposal networks[J]. Advances in neural information processing systems, 2015, 28.

Liu W, Anguelov D, Erhan D, et al. Ssd: Single shot multibox detector[C]//Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part I 14. Springer International Publishing, 2016: 21-37.

Redmon J, Divvala S, Girshick R, et al. You only look once: Unified, real-time object detection[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 779-788.

Redmon J, Farhadi A. YOLO9000: better, faster, stronger[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 7263-7271.

Redmon J, Farhadi A. Yolov3: An incremental improvement[J]. arxiv preprint arxiv:1804.02767, 2018.

Bochkovskiy A, Wang C Y, Liao H Y M. Yolov4: Optimal speed and accuracy of object detection[J]. arxiv preprint arxiv:2004.10934, 2020.

Zhang S, **e M. Real-time recognition and localization based on improved YOLOv5s for robot’s picking clustered fruits of chilies[J]. Sensors, 2023, 23(7): 3408.

Zhao J, Liu Y. Research on Road Sign Detection and Visual Depth Perception Technology for Mobile Robots[J]. Electronics, 2023, 12(14): 3202.

Xu Z, Meng Y, Yin Z, et al. Enhancing autonomous driving through intelligent navigation: A comprehensive improvement approach[J]. Journal of King Saud University-Computer and Information Sciences, 2024: 102108.

Zhang Q, Yu W, Liu W, et al. A Lightweight Visual Simultaneous Localization and Map** Method with a High Precision in Dynamic Scenes[J]. Sensors, 2023, 23(22): 9274.

Wang Y. Improved Traffic Sign Recognition Algorithm for YOLOv5[J]. International Core Journal of Engineering, 2024, 10(5): 63-76.

Han K, Wang Y, Tian Q, et al. Ghostnet: More features from cheap operations[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020: 1580-1589.

Wang T, Huang D, Tang X, et al. Aerial Photo Insulator Defect Detection based on Lightweight YOLOv5s[J]. International Core Journal of Engineering, 2024, 10(2): 96-108.

Tan M, Le Q. Efficientnet: Rethinking model scaling for convolutional neural networks[C]//International conference on machine learning. PMLR, 2019: 6105-6114.

Tan M, Le Q. Efficientnetv2: Smaller models and faster training[C]//International conference on machine learning. PMLR, 2021: 10096-10106.

Woo S, Park J, Lee J Y, et al. Cbam: Convolutional block attention module[C]//Proceedings of the European conference on computer vision (ECCV). 2018: 3-19.

Ma N, Zhang X, Zheng H T, et al. Shufflenet v2: Practical guidelines for efficient cnn architecture design[C]//Proceedings of the European conference on computer vision (ECCV). 2018: 116-131.

Howard A, Sandler M, Chu G, et al. Searching for mobilenetv3[C]//Proceedings of the IEEE/CVF international conference on computer vision. 2019: 1314-1324.

Chollet F. Xception: Deep learning with depthwise separable convolutions[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 1251-1258.

Nascimento M G, Fawcett R, Prisacariu V A. Dsconv: Efficient convolution operator[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. 2019: 5148-5157.

Hu J, Shen L, Sun G. Squeeze-and-excitation networks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 7132-7141.

Hou Q, Zhou D, Feng J. Coordinate attention for efficient mobile network design[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2021: 13713-13722.

Ouyang D, He S, Zhang G, et al. Efficient multi-scale attention module with cross-spatial learning[C]// ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2023: 1-5.

Zhang Y F, Ren W, Zhang Z, et al. Focal and efficient IOU loss for accurate bounding box regression[J]. Neurocomputing, 2022, 506: 146-157.

Zheng Z, Wang P, Liu W, et al. Distance-IoU loss: Faster and better learning for bounding box regression[C]//Proceedings of the AAAI conference on artificial intelligence. 2020, 34(07): 12993-13000.

Gevorgyan Z. SIoU loss: More powerful learning for bounding box regression[J]. arXiv preprint arXiv:2205.12740, 2022.

Tong Z, Chen Y, Xu Z, et al. Wise-IoU: bounding box regression loss with dynamic focusing mechanism[J]. arXiv preprint arXiv:2301.10051, 2023.