DMS-YOLOv5: A Decoupled Multi-Scale YOLOv5 Method for Small Object Detection
Source abstract
Abstract
Small objects detection is a challenging task in computer vision due to the limited semantic information that can be extracted and the susceptibility to background interference. In this paper, we propose a decoupled multi-scale small object detection algorithm named DMS-YOLOv5. The algorithm incorporates a receptive field module into the feature extraction network for better focus on low-resolution small objects. The coordinate attention mechanism, which combines spatial and channel attention information, is introduced to reduce interference from background information and enhance the network’s attention to object information. A detection layer tailored to small-sized objects is added to compensate for the loss of small object information in multiple downsampling operations, greatly improving the detection capability of small objects. Next, The decoupled network is introduced into the detection head network for branch processing of classification and bounding box regression tasks. Finally, the bounding box loss function is improved to alleviate missed detection problems caused by the concentration of small objects and mutual occlusion between objects. The improved method achieved a mean average precision improvement of 12.1% on VisDrone2019-DET dataset compared to the original method. In comparison experiments with similar methods, our proposed method also demonstrated good performance, validating its effectiveness.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Neural Network Applications · Visual Attention and Saliency Detection · Video Surveillance and Tracking Methods
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Xinjiang Multilingual Information Technology Laboratory, Xinjiang Multilingual Information Technology Research Center, College of Information Science and Engineering, Xinjiang University, Urumqi 830017, China
Funding
Natural Science Foundation of Autonomous Region · Autonomous Region High-Level Innovative Talent Project
References (36)
Show source-provided references
1. Deep learning for computer vision: A brief review10.1155/2018/7068349 ↗
2. Object detection in 20 years: A survey10.1109/JPROC.2023.3238524 ↗
3. Histograms of oriented gradients for human detection10.1109/CVPR.2005.177 ↗
4. Speeded-up robust features (SURF)10.1016/j.cviu.2007.09.014 ↗
5. A survey and performance evaluation of deep learning methods for small object detection10.1016/j.eswa.2021.114602 ↗
6. Object detection in optical remote sensing images: A survey and a new benchmark10.1016/j.isprsjprs.2019.11.023 ↗
7. A review on object detection in unmanned aerial vehicle surveillance
8. Object detection under rainy conditions for autonomous vehicles: A review of state-of-the-art and emerging techniques10.1109/MSP.2020.2984801 ↗
9. Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., and Zitnick, C.L. (2014, January 6–12). Microsoft coco: Common objects in context. Proceedings of the Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland.10.1007/978-3-319-10602-1_48 ↗
10. A comprehensive review on deep learning based remote sensing image super-resolution methods10.1016/j.earscirev.2022.104110 ↗
11. A review on generative adversarial networks: Algorithms, theory, and applications10.1109/TKDE.2021.3130191 ↗
12. Gesture recognition algorithm based on multi-scale feature fusion in RGB-D images10.1049/ipr2.12712 ↗
13. FE-YOLOv5: Feature enhancement network based on YOLOv5 for small object detection10.1016/j.jvcir.2023.103752 ↗
14. Neural network-based fading channel prediction: A comprehensive overview10.1109/ACCESS.2019.2937588 ↗
15. Liu, T., Luo, R., Xu, L., Feng, D., Cao, L., Liu, S., and Guo, J. (2022). Spatial Channel Attention for Deep Convolutional Neural Networks. Mathematics, 10.10.3390/math10101750 ↗
16. A review of object detection models based on convolutional neural network
17. Overview of two-stage object detection algorithms10.1088/1742-6596/1544/1/012033 ↗
18. 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 ↗
19. Girshick, R. (2015, January 7–13). Fast r-cnn. Proceedings of the IEEE International Conference on Computer Vision, Washington, DC, USA.10.1109/ICCV.2015.169 ↗
20. 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 28: Annual Conference on Neural Information Processing Systems 2015, Montreal, QC, Canada.
21. 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 ↗
22. Cai, Z., and Vasconcelos, N. (2018, January 18–22). Cascade r-cnn: Delving into high quality object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00644 ↗
23. Lu, X., Li, B., Yue, Y., Li, Q., and Yan, J. (2019, January 15–20). Grid r-cnn. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00754 ↗
24. Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (July, January 26). You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.
25. 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 Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands.10.1007/978-3-319-46448-0_2 ↗
26. Redmon, J., and Farhadi, A. (2017, January 21–26). YOLO9000: Better, faster, stronger. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.690 ↗
27. Redmon, J., and Farhadi, A. (2018). YOLOv3: An incremental improvement. arXiv.
28. Bochkovskiy, A., Wang, C.Y., and Liao, H.Y.M. (2020). Yolov4: Optimal speed and accuracy of object detection. arXiv.
29. Improved YOLOv5 network for real-time multi-scale traffic sign detection10.1007/s00521-022-08077-5 ↗
30. Li, C., Li, L., Jiang, H., Weng, K., Geng, Y., Li, L., Ke, Z., Li, Q., Cheng, M., and Nie, W. (2022). YOLOv6: A single-stage object detection framework for industrial applications. arXiv.
31. 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.
32. Hou, Q., Zhou, D., and Feng, J. (June, January 20). Coordinate attention for efficient mobile network design. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.
33. Ciampiconi, L., Elwood, A., Leonardi, M., Mohamed, A., and Rozza, A. (2023). A survey and taxonomy of loss functions in machine learning. arXiv.
34. Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., and Ren, D. (2020, January 7–12). Distance-IoU loss: Faster and better learning for bounding box regression. Proceedings of the AAAI Conference on Artificial Intelligence, New York, NY, USA.10.1609/aaai.v34i07.6999 ↗
35. The pascal visual object classes challenge: A retrospective10.1007/s11263-014-0733-5 ↗
36. Du, D., Zhu, P., Wen, L., Bian, X., Ling, H., Hu, Q., Zheng, J., Peng, T., Wang, X., and Zhang, Y. (November, January 27). VisDrone-SOT2019: The vision meets drone single object tracking challenge results. Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops, Seoul, Republic of Korea.