Skip to main content

Advertisement

Springer Nature Link
Log in

Traffic target detection based on context enhancement and feature purification

  • Published:
The Journal of Supercomputing Aims and scope Submit manuscript

Abstract

The multiscale feature fusion strategy has made substantial strides in object detection; however, it may result in feature loss or boundary distortion for larger objects when optimized for small object detection. In order to capture additional contextual information, this paper suggests a novel feature pyramid composite network structure that improves object feature extraction by incorporating residual feature extraction. In order to mitigate feature loss during the fusion process, a unified module is implemented to collect and combine global data. Furthermore, in order to optimize inter-layer information flow and mitigate interference from conflicting information, feature refinement is implemented in both channel and spatial dimensions. This method enhances the detection performance of small objects and maintains the critical features of larger objects. Experimental results indicate that this method surpasses other object detection models in terms of detection precision and achieves a 2.3% higher detection accuracy on the KITTI dataset than YOLOv9.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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
Fig. 9
Fig. 10

Similar content being viewed by others

Explore related subjects

Discover the latest articles and news from researchers in related subjects, suggested using machine learning.

Data availability

No datasets were generated or analysed during the current study.

References

  1. Zaidi SSA, Ansari MS, Aslam A, Kanwal N, Asghar M, Lee B (2022) A survey of modern deep learning based object detection models. Digit Signal Process 126:103514

    Article  Google Scholar 

  2. Zou Z, Chen K, Shi Z, Guo Y, Ye J (2023) Object detection in 20 years: a survey. Proc IEEE 111(3):257–276

    Article  MATH  Google Scholar 

  3. Jiao L, Wang M, Liu X, Li L, Liu F, Feng Z, Yang S, Hou B (2024) Multiscale deep learning for detection and recognition: a comprehensive survey. IEEE Trans Neural Netw Learn Syst

  4. Xiao J, Guo H, Zhou J, Zhao T, Yu Q, Chen Y, Wang Z (2023) Tiny object detection with context enhancement and feature purification. Expert Syst Appl 211:118665

    Article  Google Scholar 

  5. Chen S, Zhang Z, Zhang L, He R, Li Z, Xu M, Ma H (2024) A semi-supervised learning framework combining cnn and multi-scale transformer for traffic sign detection and recognition. IEEE Internet Things J

  6. Gao X, Chen L, Wang K, Xiong X, Wang H, Li Y (2022) Improved traffic sign detection algorithm based on faster r-cnn. Appl Sci 12(18):8948

    Article  MATH  Google Scholar 

  7. Liu Y, Sun P, Wergeles N, Shang Y (2021) A survey and performance evaluation of deep learning methods for small object detection. Expert Syst Appl 172:114602

    Article  Google Scholar 

  8. Chen J, Wang Q, Peng W, Xu H, Li X, Xu W (2022) Disparity-based multiscale fusion network for transportation detection. IEEE Trans Intell Transp Syst 23(10):18855–18863

    Article  MATH  Google Scholar 

  9. Lian J, Yin Y, Li L, Wang Z, Zhou Y (2021) Small object detection in traffic scenes based on attention feature fusion. Sensors 21(9):3031

    Article  MATH  Google Scholar 

  10. Ge Z (2021) Yolox: Exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430

  11. Terven J, Córdova-Esparza D-M, Romero-González J-A (2023) A comprehensive review of yolo architectures in computer vision: from yolov1 to yolov8 and yolo-nas. Mach Learn Knowl Extr 5(4):1680–1716

    Article  Google Scholar 

  12. Luo Y, Zhang C, Lin W, Yang X, Sun J (2022) Sequential attention-based distinct part modeling for balanced pedestrian detection. IEEE Trans Intell Transp Syst 23(9):15644–15654

    Article  MATH  Google Scholar 

  13. Zhou H, Yu G (2021) Research on pedestrian detection technology based on the svm classifier trained by hog and ltp features. Futur Gener Comput Syst 125:604–615

    Article  MATH  Google Scholar 

  14. Yucong S, Shuqing G (2021) Traffic sign recognition based on hog feature extraction. J Meas Eng 9(3):142–155

    Article  MATH  Google Scholar 

  15. Ren X, Wang R (2023) A target detection algorithm in traffic scenes based on deep reinforcement learning. arXiv preprint arXiv:2312.15606

  16. Shen L, You L, Peng B, Zhang C (2021) Group multi-scale attention pyramid network for traffic sign detection. Neurocomputing 452:1–14

    Article  MATH  Google Scholar 

  17. Guo Q, Zhang J, Zhu S, Zhong C, Zhang Y (2021) Deep multiscale siamese network with parallel convolutional structure and self-attention for change detection. IEEE Trans Geosci Remote Sens 60:1–12

    MATH  Google Scholar 

  18. Li S, Yan Q, Liu P (2020) An efficient fire detection method based on multiscale feature extraction, implicit deep supervision and channel attention mechanism. IEEE Trans Image Process 29:8467–8475

    Article  MATH  Google Scholar 

  19. Mahaur B, Mishra K (2023) Small-object detection based on yolov5 in autonomous driving systems. Pattern Recognit Lett 168:115–122

    Article  MATH  Google Scholar 

  20. Wei H, Zhang Q, Qian Y, Xu Z, Han J (2023) Mtsdet: multi-scale traffic sign detection with attention and path aggregation. Appl Intell 53(1):238–250

    Article  MATH  Google Scholar 

  21. Xia J, Li M, Liu W, Chen X (2023) Dsra-detr: an improved detr for multiscale traffic sign detection. Sustainability 15(14):10862

    Article  MATH  Google Scholar 

  22. Wang C, He W, Nie Y, Guo J, Liu C, Wang Y, Han K (2024) Gold-yolo: Efficient object detector via gather-and-distribute mechanism. Advances in Neural Information Processing Systems, vol 36

  23. Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 7132–7141

  24. Fu J, Liu J, Tian H, Li Y, Bao Y, Fang Z, Lu H (2019) Dual attention network for scene segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 3146–3154

  25. Zhang J, Li X, Li J, Liu L, Xue Z, Zhang B, Jiang Z, Huang T, Wang Y, Wang C (2023) Rethinking mobile block for efficient attention-based models. In: 2023 IEEE/CVF International Conference on Computer Vision (ICCV). IEEE Computer Society, pp 1389–1400

  26. Geiger A, Lenz P, Urtasun R (2012) Are we ready for autonomous driving? The Kitti vision benchmark suite. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, pp 3354–3361

  27. Zhang J, Zou X, Kuang L-D, Wang J, Sherratt RS, Yu X (2022) Cctsdb 2021: a more comprehensive traffic sign detection benchmark. Human-centric Computing and Information Sciences, vol 12

Download references

Author information

Authors and Affiliations

  1. Xinjiang University, Ürümqi, China

    Tao Liu, Chenyoukang Lin, Yunteng Hu, Ruyi Cao & Wendong Zhang

Authors
  1. Tao Liu
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Chenyoukang Lin
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Yunteng Hu
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Ruyi Cao
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Wendong Zhang
    View author publications

    You can also search for this author inPubMed Google Scholar

Contributions

Tao Liu: Conceptualization, Data curation, Formal analysis, Investigation, Methodology, Validation, Writing—original draft. Wendong Zhang: Resources, Supervision, Chenyoukang Lin:data curation Yunteng Hu: data curation Ruyi Cao: Formal analysis.

Corresponding author

Correspondence to Wendong Zhang.

Ethics declarations

Competing interests

The authors declare no competing interests.

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

Liu, T., Lin, C., Hu, Y. et al. Traffic target detection based on context enhancement and feature purification. J Supercomput 81, 413 (2025). https://doi.org/10.1007/s11227-025-06944-1

Download citation

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s11227-025-06944-1

Keywords