A Robust Lightweight Network for Pedestrian Detection Based on YOLOv5-x
Source abstract
Abstract
Pedestrian detection is a crucial task in computer vision, with various applications in surveillance, autonomous driving, and robotics. However, detecting pedestrians in complex scenarios, such as rainy days, remains a challenging problem due to the degradation of image quality and the presence of occlusions. To address this issue, we propose RSTDet-Lite (a robust lightweight network) for pedestrian detection on rainy days, based on an improved version of YOLOv5-x. Specifically, in order to reduce the redundant parameters of the YOLOv5-x backbone network and enhance its feature extraction capability, we propose a novel approach named CBP-GNet, which incorporates a compact bilinear pooling algorithm. This new net serves as a new backbone network, resulting in significant parameter reduction and enhancing the fine-grained feature fusion capability of the network. Additionally, we introduce the Simple-BiFPN structure as a replacement for the original feature pyramid module based on the weighted bidirectional feature pyramid to further improve feature fusion efficiency. To enhance network performance, we integrate the CBAM attention mechanism and introduce the idea of structural reparameterization. To evaluate the performance of our method, we create a new dataset named RainDet3000, which consists of 3000 images captured in various rainy scenarios. The experimental results demonstrate that, compared with YOLOv5, our proposed model reduces the network size by 30 M while achieving a 4.56% increase in mAP. This confirms the effectiveness of RSTDet-Lite in achieving excellent performance in rainy-day pedestrian detection scenarios.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Neural Network Applications · Video Surveillance and Tracking Methods · Autonomous Vehicle Technology and Safety
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
The College of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620, China
Department of Ethnic Music, Shanghai Conservatory of Music, Shanghai 200031, China
References (33)
Show source-provided references
1. Face description with local binary patterns: Application to face recognition10.1109/TPAMI.2006.244 ↗
2. Dalal, N., and Triggs, B. (2005, January 20–25). Histograms of oriented gradients for human detection. Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), San Diego, CA, USA.
3. Wu, B., and Nevatia, R. (2005, January 17–21). Detection of multiple, partially occluded humans in a single image by bayesian combination of edgelet part detectors. Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV’05), Beijing, China.
4. Ye, L., and Keogh, E. (July, January 28). Time series shapelets: A new primitive for data mining. Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Paris, France.
5. Lienhart, R., and Maydt, J. (2002, January 22–25). An extended set of haar-like features for rapid object detection. Proceedings of the International Conference on Image Processing, Rochester, NY, USA.
6. 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 ↗
7. Girshick, R. (2015, January 7–13). Fast r-cnn. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.10.1109/ICCV.2015.169 ↗
8. Faster r-cnn: Towards real-time object detection with region proposal networks
9. Redmon, J., and Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv.
10. Bochkovskiy, A., Wang, C.-Y., and Liao, H.-Y.M. (2020). Yolov4: Optimal speed and accuracy of object detection. arXiv.
11. Tian, Z., Shen, C., Chen, H., and He, T. (November, January 27). Fcos: Fully convolutional one-stage object detection. Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea.
12. Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv.
13. Zhang, Y., Zhou, A., Zhao, F., and Wu, H. (2022). A lightweight vehicle-pedestrian detection algorithm based on attention mechanism in traffic scenarios. Sensors, 22.10.3390/s22218480 ↗
14. Based on the improved YOLOv4-tiny lightweight pedestrian in school target detection algorithm
15. Han, K., Wang, Y., Tian, Q., Guo, J., Xu, C., and Xu, C. (2020, January 13–19). Ghostnet: More features from cheap operations. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.00165 ↗
16. Lightweight YOLOv4 Object Detection Algorithm
17. Roszyk, K., Nowicki, M.R., and Skrzypczyński, P. (2022). Adopting the YOLOv4 architecture for low-latency multispectral pedestrian detection in autonomous driving. Sensors, 22.10.3390/s22031082 ↗
18. Li, M.-L., Sun, G.-B., and Yu, J.-X. (2023). A pedestrian detection network model based on improved YOLOv5. Entropy, 25.10.3390/e25020381 ↗
19. Sha, M., Zeng, K., Tao, Z., Wang, Z., and Liu, Q. (2023). Lightweight Pedestrian Detection Based on Feature Multiplexed Residual Network. Electronics, 12.10.3390/electronics12040918 ↗
20. Zhao, Q., Ma, W., Zheng, C., and Li, L. (2023). Exploration of Vehicle Target Detection Method Based on Lightweight YOLOv5 Fusion Background Modeling. Appl. Sci., 13.10.3390/app13074088 ↗
21. Sun, Z., Liu, C.A., Qu, H., and Xie, G. (2022). PVformer: Pedestrian and vehicle detection algorithm based on Swin transformer in rainy scenes. Sensors, 22.10.3390/s22155667 ↗
22. Spatial pyramid pooling in deep convolutional networks for visual recognition10.1109/TPAMI.2015.2389824 ↗
23. He, K., Zhang, X., Ren, S., and Sun, J. (July, January 26). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.
24. Gao, Y., Beijbom, O., Zhang, N., and Darrell, T. (July, January 26). Compact bilinear pooling. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.
25. Lin, T.-Y., RoyChowdhury, A., and Maji, S. (2015, January 7–13). Bilinear CNN models for fine-grained visual recognition. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.10.1109/ICCV.2015.170 ↗
26. Tan, M., Pang, R., and Le, Q.V. (2020, January 13–19). Efficientdet: Scalable and efficient object detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.01079 ↗
27. Ghiasi, G., Lin, T.-Y., and Le, Q.V. (2019, January 15–20). Nas-fpn: Learning scalable feature pyramid architecture for object detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00720 ↗
28. Ding, X., Zhang, X., Ma, N., Han, J., Ding, G., and Sun, J. (2021, January 20–25). Repvgg: Making vgg-style convnets great again. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.10.1109/CVPR46437.2021.01352 ↗
29. Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., and Schiele, B. (July, January 26). The cityscapes dataset for semantic urban scene understanding. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.
30. UA-DETRAC: A new benchmark and protocol for multi-object detection and tracking10.1016/j.cviu.2020.102907 ↗
31. Dollár, P., Wojek, C., Schiele, B., and Perona, P. (2009, January 20–25). Pedestrian detection: A benchmark. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.10.1109/CVPR.2009.5206631 ↗
32. Vision meets robotics: The kitti dataset10.1177/0278364913491297 ↗
33. Yu, F., Chen, H., Wang, X., Xian, W., Chen, Y., Liu, F., Madhavan, V., and Darrell, T. (2020, January 13–19). Bdd100k: A diverse driving dataset for heterogeneous multitask learning. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.00271 ↗