Skip to main content
SpringerLink
Log in

Vehicle detection algorithm based on lightweight YOLOX

  • Original Paper
  • Published:
Signal, Image and Video Processing Aims and scope Submit manuscript

Abstract

Nowadays, accurate and fast vehicle detection technology is of great significance for constructing intelligent transportation systems in the context of the era of big data. This paper proposes an improved lightweight YOLOX real-time vehicle detection algorithm. Compared with the original network, the detection speed and accuracy of the new algorithm have been improved with fewer parameters. First, referring to the GhostNet, we make a lightweight design of the backbone extraction network, which significantly reduces the network parameters, training cost, and inference time. Furthermore, by introducing the α-CIoU loss function, the regression accuracy of the bounding box (bbox) is improved, while the convergence speed of the model is also accelerated. The experimental results show that the mAP of the improved algorithm on the BIT-Vehicle dataset can reach up to 99.21% with 41.2% fewer network parameters and 12.7% higher FPS than the original network and demonstrate the effectiveness of our proposed method.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

Availability of data and materials

This article uses a public dataset: BIT-Vehicle dataset.

References

  1. Qi, L.: Research on intelligent transportation system technologies and applications. In: 2008 Workshop on Power Electronics and Intelligent Transportation System, pp. 529–531. IEEE (2008)

  2. Navastara, D.A., et al.: Vehicle classification based on CCTV video recording using histogram of oriented gradients, local binary patterns, and hierarchical multi-SVM. In: IOP Conference Series: Materials Science and Engineering, vol. 1077, no. 1. IOP Publishing (2021)

  3. Wei, Y., et al.: Multi-vehicle detection algorithm through combining Harr and HOG features. Math. Comput. Simul. 155, 130–145 (2019)

    Article  MathSciNet  MATH  Google Scholar 

  4. Guo, E., Bai, L., Zhang, Y., et al.: Vehicle detection based on superpixel and improved hog in aerial images. In: International Conference on Image and Graphics, pp. 362–373. Springer, Cham

  5. Girshick, R., Donahue, J., Darrell, T., et al.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580–587 (2014)

  6. Girshick, R.: Fast r-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440–1448 (2015)

  7. Ren, S., He, K., Girshick, R., et al.: Faster r-CNN: towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst. 28 (2015)

  8. Redmon, J., Divvala, S., Girshick, R., et al.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779–788 (2016)

  9. Liu, W., Anguelov, D., Erhan, D., et al.: Ssd: Single shot multibox detector. In: European Conference on Computer Vision, pp. 21–37. Springer, Cham (2016)

  10. Yang, Z., Li, J., Li, H.: Real-time pedestrian and vehicle detection for autonomous driving. In: 2018 IEEE Intelligent Vehicles Symposium (IV), pp. 179–184. IEEE (2018)

  11. Redmon, J., Farhadi, A.: YOLO9000: Better, faster, stronger. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7263–7271 (2017)

  12. Yang, S., Chong, X., Li, X., et al.: Intelligent intersection vehicle and pedestrian detection based on convolutional neural network. J. Sens. 2022, 8445816 (2022)

    Google Scholar 

  13. Wang, H., Yu, Y., Cai, Y., et al.: Soft-weighted-average ensemble vehicle detection method based on single-stage and two-stage deep learning models. IEEE Trans. Intell. Veh. 6(1), 100–109 (2020)

    Article  Google Scholar 

  14. Lin, T.Y., Goyal, P., Girshick, R., et al.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980–2988 (2017)

  15. Cai, Z., Vasconcelos, N.: Cascade r-CNN: Delving into high quality object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6154–6162 (2018)

  16. Taheri Tajar, A., Ramazani, A., Mansoorizadeh, M.: A lightweight Tiny-YOLOv3 vehicle detection approach. J. Real-Time Image Proc. 18(6), 2389–2401 (2021)

    Article  Google Scholar 

  17. Wang, X., Zhang, W., Wu, X., et al.: Real-time vehicle type classification with deep convolutional neural networks. J. Real-Time Image Proc. 16(1), 5–14 (2019)

    Article  Google Scholar 

  18. Ge, Z., Liu, S., Wang, F., et al. Yolox: Exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430 (2021)

  19. Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)

  20. Wortsman, M., Ilharco, G., Gadre, S.Y., et al.: Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time. arXiv preprint arXiv:2203.05482 (2022)

  21. Ma, N., Zhang, X., Zheng, H.T., et al.: Shufflenet v2: practical guidelines for efficient CNN architecture design. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 116–131 (2018)

  22. Howard, A.G., Zhu, M., Chen, B., et al.: Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)

  23. Han, K., Wang, Y., Tian, Q., et al.: Ghostnet: More features from cheap operations. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1580–1589 (2020)

  24. He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)

  25. Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., Hu, Q.: ECA-net: efficient channel attention for deep convolutional neural networks. In: 2020 IEEE/CVF conference on computer vision and pattern recognition (CVPR), pp. 11531–11539 (2020)

  26. He, J., Erfani, S., Ma, X., et al.:α-IoU: a family of power intersection over union losses for bounding box regression. Adv. Neural Inf. Process. Syst. 34, 20230–20242 (2021)

    Google Scholar 

  27. Zheng, Z., Wang, P., Liu, W., et al.: Distance-IoU loss: Faster and better learning for bounding box regression. Proc. AAAI Confer. Artif. Intell. 34(07), 12993–13000 (2020)

    Google Scholar 

  28. Zheng, Z., Wang, P., Ren, D., et al.: Enhancing geometric factors in model learning and inference for object detection and instance segmentation. IEEE Trans. Cybern. 52(8), 8574–8586 (2022)

    Article  Google Scholar 

  29. Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: Yolov4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)

  30. Dong, Z., Wu, Y., Pei, M., et al.: Vehicle type classification using a semisupervised convolutional neural network. IEEE Trans. Intell. Transp. Syst. 16(4), 2247–2256 (2015)

    Article  Google Scholar 

Download references

Funding

This study was funded by Chongqing Municipal Education Commission Science and Technology Research Project(KJQN202001523); 2021 Cooperation Project between Chongqing Municipal Undergraduate Universities and Chinese Academy of Sciences(HZ2021015); Chongqing University of Science and Technology Youth Science Fund Project(CKRC2019042).

Author information

Authors and Affiliations

  1. ,*School of Intelligent Technology and Engineering, Chongqing University of Science and Technology, University Town East Road, Chongqing, 404100, China

    Cong Xiong, Anning Yu, Senhao Yuan & Xinghua Gao

Authors
  1. Cong Xiong
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Anning Yu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Senhao Yuan
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Xinghua Gao
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Yu Anning is responsible for providing experimental platform and paper review; Xiong Cong is responsible for writing the paper and completing the experiment; Senhao Yuan is responsible for the drawing of Figs. 1, 3, 4, 5, 6 and 7; Xinghua Gao is responsible for the production of all tables.

Corresponding author

Correspondence to Anning Yu.

Ethics declarations

Competing interests

The authors declare no competing interests.

Conflict of interest

The authors declare that they have no conflict of interest.

Ethical approval

Not applicable.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Xiong, C., Yu, A., Yuan, S. et al. Vehicle detection algorithm based on lightweight YOLOX. SIViP 17, 1793–1800 (2023). https://doi.org/10.1007/s11760-022-02390-1

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11760-022-02390-1

Keywords

Search

Navigation