A Model for Helmet-Wearing Detection of Non-Motor Drivers Based on YOLOv5s
Source abstract
Abstract
Detecting non-motor drivers’ helmets has significant implications for traffic control. Currently, most helmet detection methods are susceptible to the complex background and need more accuracy and better robustness of small object detection, which are unsuitable for practical application scenarios. Therefore, this paper proposes a new helmet-wearing detection algorithm based on the You Only Look Once version 5 (YOLOv5). First, the Dilated convolution In Coordinate Attention (DICA) layer is added to the backbone network. DICA combines the coordinated attention mechanism with atrous convolution to replace the original convolution layer, which can increase the perceptual field of the network to get more contextual information. Also, it can reduce the network’s learning of unnecessary features in the background and get attention to small objects. Second, the Rebuild Bidirectional Feature Pyramid Network (Re-BiFPN) is used as a feature extraction network. Re-BiFPN uses cross-scale feature fusion to combine the semantic information features at the high level with the spatial information features at the bottom level, which facilitates the model to learn object features at different scales. Verified on the proposed “Helmet Wearing dataset for Non-motor Drivers (HWND),” the results show that the proposed model is superior to the current detection algorithms, with the mean average precision (mAP) of 94.3% under complex background.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Advanced Neural Network Applications · Autonomous Vehicle Technology and Safety · Video Surveillance and Tracking Methods
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (39)
Show source-provided references
1. Object detection/tracking toward underwater photographs by remotely operated vehicles (ROVs)10.1016/j.future.2021.07.011 ↗
2. Hybrid transfer learning and broad learning system for wearing mask detection in the COVID-19 era10.1109/TIM.2021.3123218 ↗
3. Automatic detection of COVID-19 with bidirectional LSTM network using deep features extracted from chest X-ray images10.1007/s12539-021-00463-2 ↗
4. Weapons detection for security and video surveillance using CNN and YOLO-V5s10.32604/cmc.2022.018785 ↗
5. A utility model for photo selection in mobile crowdsensing10.1109/TMC.2019.2941927 ↗
6. Evolving block-based convolutional neural network for hyperspectral image classification
7. Rich feature hierarchies for accurate object detection and semantic segmentation
8. Fast R-CNN
9. Faster R-CNN: Towards real-time object detection with region proposal networks
10. SSD: Single shot multibox detector
11. You only look once: Unified, real-time object detection
12. YOLO9000: Better, faster, stronger
13. J. Redmon and A. Farhadi, “YOLOv3: An incremental improvement,” arXiv preprint, 2018. https://arxiv.org/abs/1804.02767
14. A. Bochkovskiy, C. -Y. Wang and H. -Y. M. Liao, “YOLOv4: Optimal speed and accuracy of object detection,” arXiv preprint, 2020. https://arxiv.org/abs/2004.10934
15. A survey of deep learning-based object detection10.1109/ACCESS.2019.2939201 ↗
16. M. Tan, R. Pang and Q. V. Le, “EfficientDet: Scalable and efficient object detection,” arXiv preprint, 2018. https://ui.adsabs.harvard.edu/abs/2019arXiv191109070T10.1109/CVPR42600.2020.01079 ↗
17. Deep learning-based helmet wear analysis of a motorcycle rider for intelligent surveillance system10.1049/iet-its.2018.5241 ↗
18. Detection of safety helmet wearing based on improved faster R-CNN
19. An advanced deep learning approach for safety helmet wearing detection
20. A. Shrivastava, A. Gupta and R. Girshick, “Training region-based object detectors with online hard example mining,” arXiv preprint, 2016. https://ui.adsabs.harvard.edu/abs/2016arXiv160403540S10.1109/CVPR.2016.89 ↗
21. Helmet detection using faster region-based convolutional neural networks and single-shot multibox detector
22. Safety helmet wearing detection in aerial images using improved yolov410.32604/cmc.2022.026664 ↗
23. Real-time automatic helmet detection of motorcyclists in urban traffic using improved YOLOv5 detector10.1049/ipr2.12295 ↗
24. Method based on the cross-layer attention mechanism and multiscale perception for safety helmet-wearing detection10.1016/j.compeleceng.2021.107458 ↗
25. Multi-scale safety helmet detection based on SAS-YOLOv3-Tiny10.3390/app11083652 ↗
26. Z. Daquan, Q. Hou, Y. Chen, J. Feng and S. Yan, “Rethinking bottleneck structure for efficient mobile network design,” arXiv preprint, 2020. https://ui.adsabs.harvard.edu/abs/2020arXiv200702269D
27. Research on the algorithm of helmet-wearing detection based on the optimized yolov410.1007/s00371-022-02471-9 ↗
28. C. -Y. Wang, H. -Y. M. Liao, I. H. Yeh, Y. -H. Wu, P. -Y. Chen et al., “CSPNet: A new backbone that can enhance learning capability of CNN,” arXiv preprint, 2019. https://ui.adsabs.harvard.edu/abs/2019arXiv191111929W10.1109/CVPRW50498.2020.00203 ↗
29. FD-YOLOv5: A fuzzy image enhancement based robust object detection model for safety helmet detection10.1007/s40815-022-01267-2 ↗
30. Investigation into recognition algorithm of helmet violation based on YOLOv5-CBAM-DCN10.1109/ACCESS.2022.3180796 ↗
31. J. Dai, H. Qi, Y. Xiong, Y. Li, G. Zhang et al., “Deformable convolutional networks,” arXiv preprint, 2017. https://ui.adsabs.harvard.edu/abs/2017arXiv170306211D10.1109/ICCV.2017.89 ↗
32. S. Woo, J. Park, J. -Y. Lee and I. S. Kweon, “CBAM: Convolutional block attention module,” arXiv preprint, 2018. https://ui.adsabs.harvard.edu/abs/2018arXiv180706521W10.1007/978-3-030-01234-2_1 ↗
33. Toward efficient safety helmet detection based on YoloV5 with hierarchical positive sample selection and box density filtering10.1109/TIM.2022.3218574 ↗
34. Bikes helmets dataset
35. J. Hu, L. Shen, S. Albanie, G. Sun and E. Wu, “Squeeze-and-excitation networks,” arXiv preprint, 2017. https://ui.adsabs.harvard.edu/abs/2017arXiv170901507H
36. J. Fu, J. Liu, H. Tian, Y. Li, Y. Bao et al., “Dual attention network for scene segmentation,” arXiv preprint, 2018. https://ui.adsabs.harvard.edu/abs/2018arXiv180902983F10.1109/CVPR.2019.00326 ↗
37. Integrating hybrid pyramid feature fusion and coordinate attention for effective small sample hyperspectral image classification10.3390/rs14102355 ↗
38. Q. Hou, D. Zhou and J. Feng, “Coordinate attention for efficient mobile network design,” arXiv preprint, 2021. https://ui.adsabs.harvard.edu/abs/2021arXiv210302907H10.1109/CVPR46437.2021.01350 ↗
39. C. -Y. Wang, A. Bochkovskiy and H. -Y. M. Liao, “YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors,” arXiv preprint, 2022. https://ui.adsabs.harvard.edu/abs/2022arXiv220702696W10.1109/CVPR52729.2023.00721 ↗