TCE-YOLOv5: Lightweight Automatic Driving Object Detection Algorithm Based on YOLOv5
Source abstract
Abstract
In automatic driving systems, accurate and efficient object detection is essential to ensure driving safety and improve the driving experience. However, autonomous vehicles deal with large amounts of real-time data, which places extremely high demands on computing resources. Therefore, a lightweight object detection algorithm based on YOLOv5 is proposed to solve the problem of excessive network parameters in automatic driving scenarios. Firstly, the Bottleneck convolution kernel channels in the C3 module were grouped to greatly reduce the number of parameters. Secondly, the C3 module in the neck is replaced by the Res2Net module, which extracts features at different scales through multiple branches, not only ensuring rich details, but also enhancing the generalization ability of the network. Finally, the EIOU loss function is introduced to measure the overlap between the predicted box and the real box more accurately and improve the detection accuracy. The test results of KITTI and CCTSDB2021 public traffic datasets show that compared with the original YOLOv5 model, the improved algorithm reduces the number of parameters by 20%, the calculation amount by 21%, and mAP@0.5 by 1.0%. After TensorRT optimization, the inference speed of our model on Jetson Xavier NX reaches 61 frames/s, which is 15% higher than the original YOLOv5, and satisfies the requirements of real-time detection.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Neural Network Applications · Video Surveillance and Tracking Methods · Image Enhancement Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
State Key Laboratory of Intelligent Vehicle Safety Technology, Chongqing 401122, China
School of Communications and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, China
Funding
State Key Laboratory of Intelligent Vehicle Safety Technology Open Project
References (43)
Show source-provided references
1. Ning, J., and Wang, J. (2022, January 23–25). Automatic Driving Scene Target Detection Algorithm Based on Improved YOLOv5 Network. Proceedings of the 2022 International Conference on Computer Network, Electronic and Automation (ICCNEA), Xi’an, China.10.1109/ICCNEA57056.2022.00056 ↗
2. Camera as the instrument: The rising trend of vision based measurement10.1109/MIM.2014.6825388 ↗
3. A Survey of Motion Planning and Control Techniques for Self-Driving Urban Vehicles10.1109/TIV.2016.2578706 ↗
4. Cao, Z., Xu, L., Niu, Z., Zhang, C., You, G., Zhao, M., and Yang, Y. (2024, January 19–22). YOLOv7-Based Autonomous Driving Object Detection Algorithm. Proceedings of the 2024 9th International Conference on Computer and Communication Systems (ICCCS), Xi’an, China.10.1109/ICCCS61882.2024.10603214 ↗
5. A Survey of Driving Safety with Sensing, Vehicular Communications, and Artificial Intelligence-Based Collision Avoidance10.1109/TITS.2021.3083927 ↗
6. A Review on Machine Learning Styles in Computer Vision—Techniques and Future Directions10.1109/ACCESS.2022.3209825 ↗
7. Mobile Internet of Things Under Data Physical Fusion Technology10.1109/JIOT.2019.2954588 ↗
8. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
9. Driving Tasks Transfer Using Deep Reinforcement Learning for Decision-Making of Autonomous Vehicles in Unsignalized Intersection10.1109/TVT.2021.3121985 ↗
10. Ren, H., Jing, F., and Li, S. (2024). DCW-YOLO: Road Object Detection Algorithms for Autonomous Driving. IEEE Access, early access.10.1109/ACCESS.2024.3364681 ↗
11. David, G. (1999, January 20–27). Object Recognition from Local Scale-invariant Features. Proceedings of the International Conference on Computer Vision, Kerkyra, Greece.
12. Surasak, T., Takahiro, I., Cheng, C.H., Wang, C.E., and Sheng, P.Y. (2018, January 17–18). His togram of Oriented Gradients for Human Detection in Video. Proceedings of the International Conference on Business and Industrial Research (ICBIR), Bangkok, Thailand.10.1109/ICBIR.2018.8391187 ↗
13. ImageNet classification with deep convolutional neural networks
14. 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.10.1109/CVPR.2014.81 ↗
15. Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (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.10.1109/CVPR.2016.91 ↗
16. Redmon, J., and Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv.
17. Bochkovskiy, A., Wang, C.Y., and Liao, H.Y.M. (2020). Yolov4: Optimal Speed and Accuracy of Object Detection. arXiv.
18. Zhu, X., Lyu, S., Wang, X., and Zhao, Q. (2021, January 11–17). TPH-YOLOv5: Improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios. Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, BC, Canada.10.1109/ICCVW54120.2021.00312 ↗
19. Wang, C.Y., Bochkovskiy, A., and Liao, H.Y.M. (2023, January 17–24). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.10.1109/CVPR52729.2023.00721 ↗
20. Vehicle Detection and Tracking Based on Improved YOLOv810.1109/ACCESS.2025.3538556 ↗
21. Yolov10: Real-time end-to-end object detection
22. Zhu, L., Geng, X., Li, Z., and Liu, C. (2021). Improving YOLOv5 with attention mechanism for detecting boulders from planetary images. Remote Sens., 13.10.3390/rs13183776 ↗
23. A lightweight vehicles detection network model based on YOLOv510.1016/j.engappai.2022.104914 ↗
24. YOLOv8-FDD: A Real-Time Vehicle Detection Method Based on Improved YOLOv810.1109/ACCESS.2024.3453298 ↗
25. Wang, H., and Ma, Z. (2024, January 12–14). Small Target Detection Algorithm of Edge Scene Based on Improved YOLOv8. Proceedings of the 2024 13th International Conference of Information and Communication Technology (ICTech), Xiamen, China.10.1109/ICTech63197.2024.00033 ↗
26. MCS-YOLO: A multiscale object detection method for autonomous driving road environment recognition10.1109/ACCESS.2023.3252021 ↗
27. Feng, J., and Yi, C. (2022). Lightweight detection network for arbitrary-oriented vehicles in UAV imagery via global attentive relation and multi-path fusion. Drones, 6.10.3390/drones6050108 ↗
28. Lai, H., Chen, L., Liu, W., Yan, Z., and Ye, S. (2023). STC-YOLO: Small object detection network for traffic signs in complex environments. Sensors, 23.10.3390/s23115307 ↗
29. Wang, X., Zhang, J., Wang, Y., Li, M., and Liu, D. (2022, January 3–5). Defect Detection of Track Fasteners Based on Pruned YOLO V5 Model. Proceedings of the 2022 IEEE 11th Data Driven Control and Learning Systems Conference (DDCLS), Chengdu, China.10.1109/DDCLS55054.2022.9858442 ↗
30. Evaluation of Thermal Imaging on Embedded GPU Platforms for Application in Vehicular Assistance Systems10.1109/TIV.2022.3158094 ↗
31. TTD-YOLO: A Real-Time Traffic Target Detection Algorithm Based on YOLOV510.1109/ACCESS.2024.3394693 ↗
32. Spatial pyramid pooling in deep convolutional networks for visual recognition10.1109/TPAMI.2015.2389824 ↗
33. Liu, S., Qi, L., Qin, H., Shi, J., and Jia, J. (2018, January 18–23). Path aggregation network for instance segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00913 ↗
34. Wang, Y., Jin, S., Yin, C., and Wu, Z. (2023, January 1–3). Target Detection Algorithm Based on Improved YOLOv5 for Edge Computing Devices. Proceedings of the 2023 5th International Conference on Robotics, Intelligent Control and Artificial Intelligence (RICAI), Hangzhou, China.10.1109/RICAI60863.2023.10488977 ↗
35. Rao, L. (2021). TreeNet: A lightweight one-shot aggregation convolutional network. arXiv.
36. Res2Net: A new multi-scale backbone architecture10.1109/TPAMI.2019.2938758 ↗
37. Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., and Savarese, S. (2019, January 15–20). Generalized intersection over union: A metric and a loss for bounding box regression. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00075 ↗
38. Focal and efficient IOU loss for accurate bounding box regression10.1016/j.neucom.2022.07.042 ↗
39. Distance-IoU loss: Faster and better learning for bounding box regression
40. Tao, J., Wang, H., Zhang, X., Li, X., and Yang, H. (2017, January 21–22). An object detection system based on YOLO in traffic scene. Proceedings of the 2017 6th International Conference on Computer Science and Network Technology (ICCSNT), Dalian, China.10.1109/ICCSNT.2017.8343709 ↗
41. Zhang, J., Zou, X., and Kuang, L.D. (2022). CCTSDB 2021: A more comprehensive traffic sign detection benchmark. Human-Centric Computing and Information Sciences, Springer.
42. Wang, X., Gao, H., Jia, Z., and Li, Z. (2023). BL-YOLOv8: An improved road defect detection model based on YOLOv8. Sensors, 23.10.3390/s23208361 ↗
43. A Lightweight Traffic Sign Recognition Model Based on Improved YOLOv510.1109/ACCESS.2023.3326000 ↗