Improved YOLOv7 for Small Object Detection Algorithm Based on Attention and Dynamic Convolution
Source abstract
Abstract
The rapid advancement of deep learning has significantly accelerated progress in target detection. However, the detection of small targets remains challenging due to their susceptibility to size variations. In this paper, we address these challenges by leveraging the latest version of the You Only Look Once (YOLOv7) model. Our approach enhances the YOLOv7 model to improve feature preservation and minimize feature loss during network processing. We introduced the Spatial Pyramid Pooling and Cross-Stage Partial Channel (SPPCSPC) module, which combines the feature separation and merging ideas. To mitigate missed detections in small target scenarios and reduce noise impact, we incorporated the Coordinate Attention for Efficient Mobile Network Design (CA) module strategically. Additionally, we introduced a dynamic convolutional module to address misdetection and leakage issues stemming from significant target size variations, enhancing network robustness. An experimental validation was conducted on the FloW-Img sub-dataset provided by Okahublot. The results demonstrated that our enhanced YOLOv7 model outperforms the original network, exhibiting significant improvement in leakage reduction, with a mean Average Precision (mAP) of 81.1%. This represents a 5.2 percentage point enhancement over the baseline YOLOv7 model. In addition, the new model also has some advantages over the latest small-target-detection algorithms such as FCOS and VFNet in some respects.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Neural Network Applications · Infrared Target Detection Methodologies · Visual Attention and Saliency Detection
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Information and Control Engineering, Xi’an University of Architecture and Technology, Xi’an 710311, China
Funding
Natural Science Foundation of Shaanxi Province, China · National Natural Science Foundation of China
References (34)
Show source-provided references
1. Recent advances in small object detection
2. Viola, P., and Jones, M. (2001, January 8–14). Rapid object detection using a boosted cascade of simple features. Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2001, Kauai, HI, USA. Available online: http://ieeexplore.ieee.org/document/990517/.
3. 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.
4. A review of object detection study based on deep learning
5. Chen, C., Liu, M.Y., Tuzel, O., and Xiao, J. (2016, January 27–30). R-CNN for small object detection. Proceedings of the IEEE International Conference on Computer Vision, Las Vegas, NV, USA.
6. Krishna, H., and Jawahar, C.V. (2017, January 26–29). Improving small object detection. Proceedings of the 4th IAPR Conference on Pattern Recognition, Nanjing, China.10.1109/ACPR.2017.149 ↗
7. Zhang, W., Wang, S., Thachan, S., Chen, J., and Qian, Y. (2018, January 22–27). Deconv RCNN for small object detection on remote sensing images. Proceedings of the IEEE International Geoscience and Remote Sensing Symposium, Valencia, Spain.10.1109/IGARSS.2018.8517436 ↗
8. Object detection based on improved Faster RCNN for remote sensing image
9. Attention-mechanism based light single shot multiBox detector modelling improvement for small object detection on the sea surface10.11834/jig.200517 ↗
10. Han, J., Ding, J., Xue, N., and Xia, G.-S. (2021, January 20–25). ReDet: A rotationequivariant detector for aerial object detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.10.1109/CVPR46437.2021.00281 ↗
11. Oriented bounding boxes for small and freely rotated objects10.1109/TGRS.2021.3076050 ↗
12. Anchor-free arbitrary oriented object detector using box boundary-aware vectors10.1109/JSTARS.2022.3158905 ↗
13. Zhu, X.K., Lü, S.C., Wang, X., and Zhao, Q. (2021, January 11–17). TPH-YOLOv5: Improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios. Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision Workshops, Montreal, BC, Canada.10.1109/ICCVW54120.2021.00312 ↗
14. Fu, H.X., Song, G.Q., and Wang, Y.C. (2021). Improved YOLOv4 marine target detection combined with CBAM. Symmetry, 13.10.3390/sym13040623 ↗
15. Benjumea, A., Teeti, I., Cuzzolin, F., and Bradley, A. (2023, January 01). YOLO-Z: Improving Small Object Detection in YOLOv5 for Autonomous Vehicles. Available online: https://arxiv.org/abs/2112.11798.
16. Akyon, F.C., Altinuc, S.O., and Temizel, A. (2022, January 16–19). Slicing Aided Hyper Inference and Fine-Tuning for Small Object Detection. Proceedings of the 2022 IEEE International Conference on Image Processing (ICIP), Bordeaux, France.10.1109/ICIP46576.2022.9897990 ↗
17. Cheng, G., Yuan, X., Yao, X., Yan, K., Zeng, Q., and Xie, X. (2023). Towards Large-Scale Small Object Detection: Survey and Benchmarks. IEEE Trans. Pattern Anal. Mach. Intell., 1–20.10.1109/TPAMI.2023.3290594 ↗
18. Wang, C.Y., Bochkovskiy, A., and Liao, H.Y.M. (2023, January 01). YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Realtime Object Detectors. Available online: https://arxiv.org/abs/2207.02696.10.1109/CVPR52729.2023.00721 ↗
19. Song, Q., Li, S., Bai, Q., Yang, J., Zhang, X., Li, Z., and Duan, Z. (2021). Object detection method for grasping robot based on improved YOLOv5. Micromachines, 12.10.3390/mi12111273 ↗
20. Matnet: Motion-attentive transition network for zero-shot video object segmentation10.1109/TIP.2020.3013162 ↗
21. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, Ł., and Polosukhin, I. (2017, January 4–9). Attention is all you need. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA.
22. Hu, J., Shen, L., and Sun, G. (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 ↗
23. Woo, S., Park, J., Lee, J.Y., and Kweon, I.S. (2018, January 8–14). Cbam: Convolutional block attention module. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01234-2_1 ↗
24. Research on Underwater Small Target Detection Algorithm Based on Improved YOLOv710.1109/ACCESS.2023.3290903 ↗
25. Yu, C., Feng, Z., Wu, Z., Wei, R., Song, B., and Cao, C. (2023). HB-YOLO: An Improved YOLOv7 Algorithm for Dim-Object Tracking in Satellite Remote Sensing Videos. Remote Sens., 15.10.3390/rs15143551 ↗
26. Hou, Q., Zhou, D., and Feng, J. (2021, January 20–25). Coordinate attention for efficient mobile network design. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.10.1109/CVPR46437.2021.01350 ↗
27. Chen, Y., Dai, X., Liu, M., Chen, D., Yuan, L., and Liu, Z. (2020, January 13–19). Dynamic convolution: Attention over convolution kernels. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR42600.2020.01104 ↗
28. Cheng, Y., Zhu, J., Jiang, M., Fu, J., Pang, C., Wang, P., Sankaran, K., Onabola, O., Liu, Y., and Liu, D. (2021, January 10–17). FloW: A Dataset and Benchmark for Floating Waste Detection in Inland Waters. Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada.10.1109/ICCV48922.2021.01077 ↗
29. Leibe, B., Matas, J., Sebe, N., and Welling, M. (2016, January 11–14). SSD: Single Shot MultiBox Detector. Proceedings of the Computer Vision—ECCV 2016, Amsterdam, The Netherlands. Lecture Notes in Computer Science.10.1007/978-3-319-46454-1 ↗
30. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks10.1109/TPAMI.2016.2577031 ↗
31. Redmon, J., and Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv.
32. AugFCOS: Augmented fully convolutional one-stage object detection network10.1016/j.patcog.2022.109098 ↗
33. Zhang, H., Wang, Y., Dayoub, F., and Sünderhauf, N. (2021, January 20–25). VarifocalNet: An IoU-aware Dense Object Detector. Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.10.1109/CVPR46437.2021.00841 ↗
34. Feng, C., Zhong, Y., Gao, Y., Scott, M.R., and Huang, W. (2021, January 10–17). TOOD: Task-aligned one-stage object detection. Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada.10.1109/ICCV48922.2021.00349 ↗