Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Oct 12;13(1):17310.
doi: 10.1038/s41598-023-43458-3.

Multi-object detection for crowded road scene based on ML-AFP of YOLOv5

Yiming Li  1 , Kaiwen Wu  1 , Wenshuo Kang  1 , Yuhui Zhou  1 , Fan Di  2   3   4
Affiliations

Multi-object detection for crowded road scene based on ML-AFP of YOLOv5

Yiming Li et al. Sci Rep. .

Abstract

Aiming at the problem of multi-object detection such as target occlusion and tiny targets in road scenes, this paper proposes an improved YOLOv5 multi-object detection model based on ML-AFP (multi-level aggregation feature perception) mechanism. Since tiny targets such as non-motor vehicle and pedestrians are not easily detected, this paper adds a micro target detection layer and a double head mechanism to improve the detection ability of tiny targets. Varifocal loss is used to achieve a more accurate ranking in the process of non-maximum suppression to solve the problem of target occlusion, and this paper also proposes a ML-AFP mechanism. The adaptive fusion of spatial feature information at different scales improves the expression ability of network model features, and improves the detection accuracy of the model as a whole. Our experimental results on multiple challenging datasets such as KITTI, BDD100K, and show that the accuracy, recall rate and mAP value of the proposed model are greatly improved, which solves the problem of multi-object detection in crowded road scenes.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing interests.

Figures

Figure 1
Figure 1
Real road scene.
Figure 2
Figure 2
The improved YOLOv5 multi-class object detection network.
Figure 3
Figure 3
Multi-level aggregation features perception.
Figure 4
Figure 4
P-R curves.
Figure 5
Figure 5
(a) The original image. (b) Detection results using Varifocal loss.
Figure 6
Figure 6
Detection performance of the proposed model.
Figure 7
Figure 7
Comparison of precision and recall.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Tian, Y. Research on object detection and classification technology in traffic video surveillance. Beijing University of Posts and Telecommunications. 02–04. (2009).
    1. Tian, Z., Shen, C., Chen, H. & T, He. FCOS: Fully convolutional one-stage object detection. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). 9627–9636 (IEEE, 2019). 10.1109/ICCV.2019.00972
    1. Zhou, X., Wang, D. & Krhenbühl, P. Objects as points. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 7263–7271 (Long Beach, 2019).
    1. Law, H. & Deng, J. CornerNet: Detecting objects as paired keypoints. In: Proceedings of the European Conference on Computer Vision, 765–781 (2018). 10.1007/978-3-030-01264-9_45
    1. Ren S, et al. Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 2016;39:1137–1149. doi: 10.1109/TPAMI.2016.2577031. - DOI - PubMed