Author:
Li Yiming,Wu Kaiwen,Kang Wenshuo,Zhou Yuhui,Di Fan
Abstract
AbstractAiming 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.
Funder
Scientific research project of National Language Commission
Publisher
Springer Science and Business Media LLC
Reference28 articles.
1. Tian, Y. Research on object detection and classification technology in traffic video surveillance. Beijing University of Posts and Telecommunications. 02–04. (2009).
2. 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). https://doi.org/10.1109/ICCV.2019.00972
3. 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).
4. Law, H. & Deng, J. CornerNet: Detecting objects as paired keypoints. In: Proceedings of the European Conference on Computer Vision, 765–781 (2018). https://doi.org/10.1007/978-3-030-01264-9_45
5. Ren, S. et al. Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39, 1137–1149. https://doi.org/10.1109/TPAMI.2016.2577031 (2016).