Multi-Scale Safety Helmet Detection Based on SAS-YOLOv3-Tiny
Source abstract
Abstract
In the practical application scenarios of safety helmet detection, the lightweight algorithm You Only Look Once (YOLO) v3-tiny is easy to be deployed in embedded devices because its number of parameters is small. However, its detection accuracy is relatively low, which is why it is not suitable for detecting multi-scale safety helmets. The safety helmet detection algorithm (named SAS-YOLOv3-tiny) is proposed in this paper to balance detection accuracy and model complexity. A light Sandglass-Residual (SR) module based on depthwise separable convolution and channel attention mechanism is constructed to replace the original convolution layer, and the convolution layer of stride two is used to replace the max-pooling layer for obtaining more informative features and promoting detection performance while reducing the number of parameters and computation. Instead of two-scale feature prediction, three-scale feature prediction is used here to improve the detection effect about small objects further. In addition, an improved spatial pyramid pooling (SPP) module is added to the feature extraction network to extract local and global features with rich semantic information. Complete-Intersection over Union (CIoU) loss is also introduced in this paper to improve the loss function for promoting positioning accuracy. The results on the self-built helmet dataset show that the improved algorithm is superior to the original algorithm. Compared with the original YOLOv3-tiny, the SAS-YOLOv3-tiny has significantly improved all metrics (including Precision (P), Recall (R), Mean Average Precision (mAP), F1) at the expense of only a minor speed while keeping fewer parameters and amounts of calculation. Meanwhile, the SAS-YOLOv3-tiny algorithm shows advantages in accuracy compared with lightweight object detection algorithms, and its speed is faster than the heavyweight model.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Neural Network Applications · Autonomous Vehicle Technology and Safety · Fire Detection and Safety Systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Mathematics and Computer Science, Zhejiang Normal University, Jinhua 321004, China
Funding
National Natural Science Foundation of China(NSFC)
References (30)
Show source-provided references
1. Girshick, R., Donahue, J., Darrelland, T., and Malik, J. (2014, January 24–27). Rich Feature Hierarchies for Accurate Object Detection and Semantic Seg-mentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.10.1109/CVPR.2014.81 ↗
2. Spatial pyramid pooling in deep convolutional networks for visual recognition10.1109/TPAMI.2015.2389824 ↗
3. Girshick, R. (2015, January 7–13). Fast R-CNN. Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile.10.1109/ICCV.2015.169 ↗
4. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks10.1109/TPAMI.2016.2577031 ↗
5. Dai, J., Li, Y., He, K., and Sun, J. (2016, January 5–10). R-FCN: Object Detection via Region-based Fully Convolutional Networks. Proceedings of the Conference on Neural Information Processing Systems, Barcelona, Spain.
6. Lin, T.-Y., Dollar, P., Girshick, R., He, K., Hariharan, B., and Belongie, S. (2017, January 21–26). Feature Pyramid Networks for Object Detection. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.106 ↗
7. Mask R-CNN10.1109/TPAMI.2018.2844175 ↗
8. Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., and Lecun, Y. (2013). OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks. arXiv.
9. Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27–30). You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.91 ↗
10. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., and Fu, C.Y. (2016, January 8–16). SSD: Single Shot Multi Box Detector. Proceedings of the Europe Conference on Computer Vision, Amsterdam, The Netherlands.10.1007/978-3-319-46448-0_2 ↗
11. Focal Loss for Dense Object Detection10.1109/TPAMI.2018.2858826 ↗
12. Redmon, J., and Farhadi, A. (2017, January 21–26). YOLO9000: Better, Faster, Stronger. Proceedings of the 30th IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.690 ↗
13. Redmon, J., and Farhadi, A. (2018, January 18–22). YOLOv3: An Incremental Scheme. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.
14. Huang, L., Yang, Y., Deng, Y., and Yu, Y. (2015). DenseBox: Unifying Landmark Localization with End to End Object Detection. arXiv.
15. CornerNet: Detecting Objects as Paired Keypoints10.1007/s11263-019-01204-1 ↗
16. Zhou, X., Zhuo, J., and Krahenbuhl, P. (2019, January 16–20). Bottom-Up Object Detection by Grouping Extreme and Center Points. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00094 ↗
17. Duan, K., Bai, S., Xie, L., Qi, H., Huang, Q., and Tian, Q. (November, January 27). CenterNet: Keypoint Triplets for Object Detection. Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea.10.1109/ICCV.2019.00667 ↗
18. Zhu, C., He, Y., and Savvides, M. (2019, January 16–20). Feature Selective Anchor-Free Module for Single-Shot Object Detection. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00093 ↗
19. Tian, Z., Shen, C., Chen, H., and He, T. (November, January 27). FCOS: Fully Convolutional One-Stage Object Detection. Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea.10.1109/ICCV.2019.00972 ↗
20. FoveaBox: Beyound Anchor-Based Object Detection10.1109/TIP.2020.3002345 ↗
21. Wang, H., Hu, Z., Guo, Y., Yang, Z., Zhou, F., and Xu, P. (2020). A Real-Time Safety HelmetWearing Detection Approach Based on CSYOLOv3. Appl. Sci., 10.10.3390/app10196732 ↗
22. Deep Learning-Based Safety Helmet Detection in Engineering Management Based on Convolutional Neural Networks10.1155/2020/6640687 ↗
23. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.-C. (2018, January 18–23). MobileNetV2: Inverted Residuals and Linear Bottlenecks. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00474 ↗
24. Daquan, Z., Hou, Q., Chen, Y., Feng, J., and Yan, S. (2020). Rethinking Bottleneck Structure for Efficient Mobile Network Design. arXiv.
25. Hu, J., Shen, L., Albanie, S., Sun, G., and Wu, E. (2018, January 18–22). Squeeze-and-Excitation Networks. Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00745 ↗
26. Zheng, Z., Wang, P., Ren, D., Liu, W., Ye, R., Hu, Q., and Zuo, W. (2020). Enhancing Geometric Factors in Model Learning and Inference for Object Detection and Instance Segmentation. arXiv.
27. Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., and Savarese, S. (2019, January 15–20). Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00075 ↗
28. Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., and Ren, D. (2020, March 09). Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression. Available online: https://arxiv.org/abs/1911.08287.
29. Bochkovskiy, A., Wang, C.Y., and Liao, H.Y.M. (2020). YOLOv4: Optimal Speed and Accuracy of Object detection. arXiv.
30. Wang, C.-Y., Liao, H.-Y.M., Wu, Y.-H., Chen, P.-Y., Hsieh, J.-W., and Yeh, I.-H. (2020, January 23–28). CSPNet: A New Backbone that can Enhance Learning Capability of CNN. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Glasgow, UK.10.1109/CVPRW50498.2020.00203 ↗