SP-YOLOv8s: An Improved YOLOv8s Model for Remote Sensing Image Tiny Object Detection
Source abstract
Abstract
An improved YOLOv8s-based method is proposed to address the challenge of accurately recognizing tiny objects in remote sensing images during practical human-computer interaction. In detecting tiny targets, the accuracy of YOLOv8s is low because the downsampling module of the original YOLOv8s algorithm causes the network to lose fine-grained feature information, and the neck network feature information needs to be sufficiently fused. In this method, the strided convolution module in YOLOv8s is replaced with the SPD-Conv module. By doing so, the feature map undergoes downsampling while preserving fine-grained feature information, thereby improving the learning and expressive capabilities of the network and enhancing recognition accuracy. Meanwhile, the path aggregation network is substituted with the SPANet structure, which facilitates the acquisition of more prosperous gradient paths. This substitution enhances the fusion of feature maps at various scales, reduces model parameters, and further improves detection accuracy. Additionally, it enhances the network’s robustness to complex backgrounds. Experimental verification is conducted on the following two intricate datasets containing tiny objects: AI-TOD and TinyPerson. A comparative analysis with the original YOLOv8s algorithm reveals notable enhancements in recognition accuracy. Specifically, under real-time performance constraints, the proposed method yields a 4.9% and 9.1% improvement in mAP0.5 recognition accuracy for AI-TOD and TinyPerson datasets, respectively. Moreover, the recognition accuracy for mAP0.5:0.95 is enhanced by 3.4% and 3.2% for the same datasets, respectively. The results indicate that the proposed method enables rapid and accurate recognition of tiny objects in complex backgrounds. Furthermore, it demonstrates better recognition precision and stability than other algorithms, such as YOLOv5s and YOLOv8s.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Neural Network Applications · Advanced Image and Video Retrieval Techniques · Visual Attention and Saliency Detection
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Computer Science and Engineering, Changchun University of Technology, Changchun 130012, China
Funding
Science and Technology Department of Jilin Province
References (58)
Show source-provided references
1. Zhang, Z. (2005). A Study on Harbor Target Recognition in High Resolution Optical Remote Sensing Image, University of Science and Technology of China.
2. Li, W. (2008). Detection of Ship in Optical Remote Sensing Image of Median-Low Resolution, National University of Defense Science and Technology.
3. 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. Part V 13.10.1007/978-3-319-10602-1_48 ↗
4. 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.
5. 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.
6. Distinctive image features from scale-invariant keypoints10.1023/B:VISI.0000029664.99615.94 ↗
7. Land-cover classification with high-resolution remote sensing images using transferable deep models10.1016/j.rse.2019.111322 ↗
8. A review of researches on deep learning in remote sensing application10.4236/ijg.2019.101001 ↗
9. Deep learning-based crack damage detection using convolutional neural networks10.1111/mice.12263 ↗
10. A review of object detection based on deep learning10.1007/s11042-020-08976-6 ↗
11. Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014, January 24–27). 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 ↗
12. 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 ↗
13. 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 Neural Information Processing Systems, Montreal, QC, Canada.
14. 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. Part I 14.10.1007/978-3-319-46448-0_2 ↗
15. Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 24–30). 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 ↗
16. Lin, T.-Y., Goyal, P., Girshick, R., He, K., and Dollár, P. (2017, January 22–29). Focal loss for dense object detection. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.324 ↗
17. Zhou, X., Wang, D., and Krähenbühl, P. (2019). Objects as points. arXiv.
18. MAT: Multianchor visual tracking with selective Search region10.1109/TCYB.2020.3039341 ↗
19. S-RPN: Sampling-balanced region proposal network for small crop pest detection10.1016/j.compag.2021.106290 ↗
20. Wang, J., Yang, W., Guo, H., Zhang, R., and Xia, G.-S. (2021, January 10–15). Tiny object detection in aerial images. Proceedings of the 2020 25th International Conference on Pattern Recognition (ICPR), Milan, Italy.10.1109/ICPR48806.2021.9413340 ↗
21. Wang, J., Xu, C., Yang, W., and Yu, L. (2021). A normalized Gaussian Wasserstein distance for tiny object detection. arXiv.
22. Liu, S., Huang, D., and Wang, Y. (2019). Learning spatial fusion for single-shot object detection. arXiv.
23. Liu, S., Qi, L., Qin, H., Shi, J., and Jia, J. (2018, January 18–22). Path aggregation network for instance segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00913 ↗
24. Shuai, T., Sun, K., Shi, B., and Chen, J. (2016, January 4–6). A ship target automatic recognition method for sub-meter remote sensing images. Proceedings of the 2016 4th International Workshop on Earth Observation and Remote Sensing Applications (EORSA), Guangzhou, China.
25. Object detection in remote sensing imagery using a discriminatively trained mixture model10.1016/j.isprsjprs.2013.08.001 ↗
26. Yang, X., Yang, J., Yan, J., Zhang, Y., Zhang, T., Guo, Z., Sun, X., and Fu, K. (November, January 27). Scrdet: Towards more robust detection for small, cluttered and rotated objects. Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea.
27. Scrdet++: Detecting small, cluttered and rotated objects via instance-level feature denoising and rotation loss smoothing10.1109/TPAMI.2022.3166956 ↗
28. Ding, J., Xue, N., Long, Y., Xia, G.-S., and Lu, Q. (2019, January 15–20). Learning roi transformer for oriented object detection in aerial images. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00296 ↗
29. RoadCapsFPN: Capsule feature pyramid network for road extraction from VHR optical remote sensing imagery10.1109/TITS.2021.3098855 ↗
30. CoF-Net: A Progressive Coarse-to-Fine Framework for Object Detection in Remote-Sensing Imagery
31. Lightweight aerial image object detection algorithm based on improved YOLOv5s10.1038/s41598-023-34892-4 ↗
32. Wang, C., Sun, M., Cao, Y., He, K., Zhang, B., Cao, Z., and Wang, M. (2023). Lightweight Network-Based Surface Defect Detection Method for Steel Plates. Sustainability, 15.10.3390/su15043733 ↗
33. Anitha, A., Shivakumara, P., Jain, S., and Agarwal, V. (2023). Smart Computer Vision, Springer.
34. Chen, S., Cheng, T., Fang, J., Zhang, Q., Li, Y., Liu, W., and Wang, X. (2023). TinyDet: Accurate Small Object Detection in Lightweight Generic Detectors. arXiv.
35. Position detection and direction prediction for arbitrary-oriented ships via multitask rotation region convolutional neural network10.1109/ACCESS.2018.2869884 ↗
36. Van Etten, A. (2018). You only look twice: Rapid multi-scale object detection in satellite imagery. arXiv.
37. Chen, S., Zhan, R., and Zhang, J. (2018). Geospatial object detection in remote sensing imagery based on multiscale single-shot detector with activated semantics. Remote Sens., 10.10.3390/rs10060820 ↗
38. FMSSD: Feature-merged single-shot detection for multiscale objects in large-scale remote sensing imagery10.1109/TGRS.2019.2954328 ↗
39. Li, M., Guo, W., Zhang, Z., Yu, W., and Zhang, T. (2018, January 22–27). Rotated region based fully convolutional network for ship detection. Proceedings of the IGARSS 2018-2018 IEEE International Geoscience and Remote Sensing Symposium, Valencia, Spain.10.1109/IGARSS.2018.8519094 ↗
40. Fu, Y., Wu, F., and Zhao, J. (2018, January 20–24). Context-aware and depthwise-based detection on orbit for remote sensing image. Proceedings of the 2018 24th International Conference on Pattern Recognition (ICPR), Beijing, China.10.1109/ICPR.2018.8545815 ↗
41. Zhang, W., Wang, S., Thachan, S., Chen, J., and Qian, Y. (2018, January 22–27). Deconv R-CNN for small object detection on remote sensing images. Proceedings of the IGARSS 2018—2018 IEEE International Geoscience and Remote Sensing Symposium, Valencia, Spain.10.1109/IGARSS.2018.8517436 ↗
42. Detection of vehicles in multisensor data via multibranch convolutional neural networks10.1109/JSTARS.2018.2825099 ↗
43. Detection of multiclass objects in optical remote sensing images10.1109/LGRS.2018.2882778 ↗
44. Multi-attention object detection model in remote sensing images based on multi-scale10.1109/ACCESS.2019.2928522 ↗
45. Ioffe, S., and Szegedy, C. (2015, January 6–11). Batch normalization: Accelerating deep network training by reducing internal covariate shift. Proceedings of the International Conference on Machine Learning, Lille, France.
46. Klambauer, G., Unterthiner, T., Mayr, A., and Hochreiter, S. (2017, January 4–9). Self-normalizing neural networks. Proceedings of the 31stConferenceonNeuralInformationProcessingSystems(NIPS2017), LongBeach, CA, USA.
47. Spatial pyramid pooling in deep convolutional networks for visual recognition10.1109/TPAMI.2015.2389824 ↗
48. Wang, C.-Y., Liao, H.-Y.M., and Yeh, I.-H. (2022). Designing Network Design Strategies Through Gradient Path Analysis. arXiv.
49. Ge, Z., Liu, S., Wang, F., Li, Z., and Sun, J. (2021). Yolox: Exceeding yolo series in 2021. arXiv.
50. Cao, Y., Chen, K., Loy, C.C., and Lin, D. (2020, January 13–19). Prime sample attention in object detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.01160 ↗
51. Sunkara, R., and Luo, T. (2022, January 19–23). No more strided convolutions or pooling: A new CNN building block for low-resolution images and small objects. Proceedings of the Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2022, Grenoble, France. Part III.10.1007/978-3-031-26409-2_27 ↗
52. Yu, X., Gong, Y., Jiang, N., Ye, Q., and Han, Z. (2020, January 1–5). Scale match for tiny person detection. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, Snowmass Village, CO, USA.10.1109/WACV45572.2020.9093394 ↗
53. Xia, G.-S., Bai, X., Ding, J., Zhu, Z., Belongie, S., Luo, J., Datcu, M., Pelillo, M., and Zhang, L. (2018, January 18–22). DOTA: A large-scale dataset for object detection in aerial images. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00418 ↗
54. Object detection in optical remote sensing images: A survey and a new benchmark10.1016/j.isprsjprs.2019.11.023 ↗
55. Redmon, J., and Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv.
56. Zhang, S., Chi, C., Yao, Y., Lei, Z., and Li, S.Z. (2020, January 14–19). Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.00978 ↗
57. 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 ↗
58. 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.