Edge-YOLO: Lightweight Infrared Object Detection Method Deployed on Edge Devices
Source abstract
Abstract
Existing target detection algorithms for infrared road scenes are often computationally intensive and require large models, which makes them unsuitable for deployment on edge devices. In this paper, we propose a lightweight infrared target detection method, called Edge-YOLO, to address these challenges. Our approach replaces the backbone network of the YOLOv5m model with a lightweight ShuffleBlock and a strip depthwise convolutional attention module. We also applied CAU-Lite as the up-sampling operator and EX-IoU as the bounding box loss function. Our experiments demonstrate that, compared with YOLOv5m, Edge-YOLO is 70.3% less computationally intensive, 71.6% smaller in model size, and 44.4% faster in detection speed, while maintaining the same level of detection accuracy. As a result, our method is better suited for deployment on embedded platforms, making effective infrared target detection in real-world scenarios possible.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Neural Network Applications · Infrared Target Detection Methodologies · Video Surveillance and Tracking Methods
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Information Science and Engineering, East China University of Science and Technology, Shanghai 200237, China
References (22)
Show source-provided references
1. A local contrast method for small infrared target detection10.1109/TGRS.2013.2242477 ↗
2. Infrared point target detection with improved template matching10.1016/j.infrared.2012.01.006 ↗
3. Teutsch, M., Muller, T., Huber, M., and Beyerer, J. (2014, January 23–28). Low resolution person detection with a moving thermal infrared camera by hot spot classification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Columbus, OH, USA.10.1109/CVPRW.2014.40 ↗
4. Ren, S., He, K., Girshick, R., and Sun, J. (2015, January 7–12). Faster r-cnn: Towards real-time object detection with region proposal networks. Proceedings of the Advances in Neural Information Processing Systems, Montreal, QC, Canada.
5. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., and Berg, A.C. (2016, January 11–14). Ssd: Single shot multibox detector. Proceedings of the 14th European Conference on Computer Vision, Amsterdam, The Netherlands.10.1007/978-3-319-46448-0_2 ↗
6. Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 11–14). You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Amsterdam, The Netherlands.10.1109/CVPR.2016.91 ↗
7. Redmon, J., and Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv.
8. Wang, C.Y., Liao HY, M., Wu, Y.H., Chen, P.Y., Hsieh, J.W., and Yeh, I.H. (2020, January 14–19). CSPNet: A new backbone that can enhance the learning capability of CNN. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Seattle, WA, USA.10.1109/CVPRW50498.2020.00203 ↗
9. Spatial pyramid pooling in deep convolutional networks for visual recognition10.1109/TPAMI.2015.2389824 ↗
10. YOLO-FIRI: Improved YOLOv5 for Infrared Image Object Detection10.1109/ACCESS.2021.3120870 ↗
11. Fan, Y., Qiu, Q., Hou, S., Li, Y., Xie, J., Qin, M., and Chu, F. (2022). Application of Improved YOLOv5 in Aerial Photographing Infrared Vehicle Detection. Electronics, 11.10.3390/electronics11152344 ↗
12. TIRNet: Object detection in thermal infrared images for autonomous driving10.1007/s10489-020-01882-2 ↗
13. Dense nested attention network for infrared small target detection10.1109/TIP.2022.3199107 ↗
14. You, S., Ji, Y., Liu, S., Mei, C., Yao, X., and Feng, Y. (2022). A thermal infrared pedestrian-detection method for edge computing devices. Sensors, 22.10.3390/s22176710 ↗
15. Distance-IoU loss: Faster and better learning for bounding box regression
16. Focal and efficient IOU loss for accurate bounding box regression10.1016/j.neucom.2022.07.042 ↗
17. Alpha-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression
18. Lin, T.Y., Dollár, P., Girshick, R., He, K., Hariharan, B., and Belongie, S. (2017, January 21–26). Feature pyramid networks for object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.106 ↗
19. Wang, J., Chen, K., Xu, R., Liu, Z., Loy, C.C., and Lin, D. (November, January 27). Carafe: Content-aware reassembly of features. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Seoul, Republic of Korea.
20. Ma, N., Zhang, X., Zheng, H.T., and Sun, J. (2018, January 8–14). Shufflenet v2: Practical guidelines for efficient cnn architecture design. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01264-9_8 ↗
21. Hu, J., Shen, L., and Sun, G. (2018, January 18–23). Squeeze-and-excitation networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00745 ↗
22. Wang, C.Y., Bochkovskiy, A., and Liao, H.Y.M. (2022). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv.