OA-YOLOv8: A Multiscale Feature Optimization Network for Remote Sensing Object Detection
Source abstract
Abstract
Object recognition in remote sensing images is essential for applications such as land resource monitoring, maritime vessel detection, and emergency disaster assessment. However, detection accuracy is often limited by complex backgrounds, densely distributed targets, and multiscale variations. To address these challenges, this study aims to improve the detection of small-scale and densely distributed objects in complex remote sensing scenes. An improved object detection network is proposed, called omnidirectional and adaptive YOLOv8 (OA-YOLOv8), based on the YOLOv8 architecture. Two targeted enhancements are introduced. First, an omnidirectional perception refinement (OPR) network is embedded into the backbone to strengthen multiscale feature representation through the incorporation of receptive-field convolution with a triplet attention mechanism. Second, an adaptive channel dynamic upsampling (ACDU) module is designed by combining DySample, the Haar wavelet transform, and a self-supervised equivariant attention mechanism (SEAM) to dynamically optimize channel information and preserve fine-grained features during upsampling. Experiments on the satellite imagery multi-vehicle dataset (SIMD) demonstrate that OA-YOLOv8 outperforms the original YOLOv8 by 4.6%, 6.7%, and 4.1% in terms of mAP@0.5, precision, and recall, respectively. Visualization results further confirm its superior performance in detecting small and dense targets, indicating strong potential for practical remote sensing applications.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Neural Network Applications · Remote-Sensing Image Classification · Advanced Image and Video Retrieval Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Naval University of Engineering, Wuhan 430030, China
References (42)
Show source-provided references
1. Application status and prospects of remote sensing technology in land and resources management
2. Spaceborne remote sensing and its impact on the economy
3. Application of remote sensing technology in smart city construction and planning10.1088/1742-6596/2608/1/012052 ↗
4. Zhang, H. (2018). A Gaofen-1 Remote-Sensing Image Segmentation Method Based on Fully Convolutional Networks. [Master’s Thesis, Shandong Agricultural University].10.1117/1.JRS.12.042804 ↗
5. Region-based convolutional networks for accurate object detection and segmentation10.1109/TPAMI.2015.2437384 ↗
6. Ren, S. (2015). Faster R-CNN: Towards real-time object detection with region proposal networks. arXiv.
7. 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 (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.91 ↗
8. Redmon, J., and Farhadi, A. (2017, January 21–26). YOLO9000: Better, faster, stronger. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.690 ↗
9. Dai, J.F., Li, Y., He, K.M., and Sun, J. (2016, January 27–30). R-FCN: Object detection via region-based fully convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.
10. Redmon, J., and Farhadi, A. (2018). YOLOv3: An incremental improvement. arXiv.
11. Bochkovskiy, A., Wang, C.-Y., and Liao, H.-Y.M. (2020). YOLOv4: Optimal speed and accuracy of object detection. arXiv.
12. Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., and Ren, D. (2019). Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression. arXiv.10.1609/aaai.v34i07.6999 ↗
13. (2024, September 01). YOLOv5: V6.0. 12, Ultralytics. Available online: https://github.com/ultralytics/yolov5.
14. 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.
15. 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.10.1109/CVPR52729.2023.00721 ↗
16. Template matching-based target recognition algorithm development and verification using SAR images10.9766/KIMST.2014.17.3.364 ↗
17. Ship rotated bounding box space for ship extraction from high-resolution optical satellite images with complex backgrounds10.1109/LGRS.2016.2565705 ↗
18. A new method on inshore ship detection in high-resolution satellite images using shape and context information10.1109/LGRS.2013.2272492 ↗
19. Zhang, W., Zhang, J., and Zhang, L. (2025). Saliency-guided adaptive random diffusion for remote sensing images restoration with cloud and haze. Proceedings of the 33rd ACM International Conference on Multimedia (MM ‘25), Dublin, Ireland, 27–31 October 2025, ACM.10.1145/3746027.3755584 ↗
20. Zhou, K., Zhang, M., Wang, H., and Tan, J. (2022). Ship detection in SAR images based on multi-scale feature extraction and adaptive feature fusion. Remote Sens., 14.10.3390/rs14030755 ↗
21. Haze removal algorithm for optical remote sensing image based on multi-scale model and histogram characteristic10.1109/ACCESS.2019.2929591 ↗
22. Drone-based RGB-infrared cross-modality vehicle detection via uncertainty-aware learning10.1109/TCSVT.2022.3168279 ↗
23. Cao, Y. (2024). Intelligent Surveillance with Multimodal Object Detection in Complex Environments. [Master’s Thesis, University of British Columbia].
24. Dong, W., Zhu, H., Lin, S., Luo, X., Shen, Y., Liu, X., Zhang, J., Guo, G., and Zhang, B. (2024). Fusion-Mamba for cross-modality object detection. arXiv.10.1109/TMM.2025.3599020 ↗
25. MD-YOLOv8: A multi-object detection algorithm for remote sensing satellite images10.1049/ipr2.70106 ↗
26. YOLO-Remote: An object detection algorithm for remote sensing targets10.1109/ACCESS.2024.3479320 ↗
27. Wang, Y., Xiao, H., Wang, Y., and Huang, J. (2023, January 15–17). Based on YOLOv7-tiny improved model of remote sensing image detection. Proceedings of the 16th International Conference on Advanced Computer Theory and Engineering (ICACTE), Hefei, China.10.1109/ICACTE59887.2023.10335430 ↗
28. YOLOrs: Object detection in multimodal remote sensing imagery10.1109/JSTARS.2020.3041316 ↗
29. Xiao, L., Zhang, T., Jia, Y., Nie, X., Wang, M., and Shao, X. (2025). YOLO-RS: Remote sensing enhanced crop detection methods. arXiv.
30. Wan, D., Lu, R., Wang, S., Shen, S., Xu, T., and Lang, X. (2023). YOLO-HR: Improved yolov5 for object detection in high-resolution optical remote sensing images. Remote Sens., 15.10.3390/rs15030614 ↗
31. Effectiveness of traditional augmentation methods for rebar counting using UAV imagery with Faster R-CNN and YOLOv10-based transformer architectures10.1038/s41598-025-18964-1 ↗
32. Safety helmet monitoring on construction sites using YOLOv10 and advanced transformer architectures with surveillance and body-worn cameras10.1061/JCEMD4.COENG-16760 ↗
33. (2025, June 25). Glenn-Jocher, Pre-Commit-ci[bot], AyushExel, etc. Yolov8. Available online: https://github.com/ultralytics/ultralytics.
34. Zhang, X., Liu, C., Yang, D., Song, T., Ye, Y., Li, K., and Song, Y. (2024). RFAConv: Innovating spatial attention and standard convolutional operation. arXiv.
35. Misra, D., Nalamada, T., Arasanipalai, A.U., and Hou, Q. (2021, January 3–8). Rotate to attend: Convolutional triplet attention module. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, Waikoloa, HI, USA.10.1109/WACV48630.2021.00318 ↗
36. Liu, W., Lu, H., Fu, H., and Cao, Z. (2023). Learning to upsample by learning to sample. arXiv.10.1109/ICCV51070.2023.00554 ↗
37. Zur theorie der orthogonalen funktionensysteme10.1007/BF01456927 ↗
38. Wang, Y., Zhang, J., Kan, M., Shan, S., and Chen, X. (2020). Self-supervised equivariant attention mechanism for weakly supervised semantic segmentation. arXiv.10.1109/CVPR42600.2020.01229 ↗
39. Liu, Z., Yuan, L., Weng, L., and Yang, Y. (2017, January 24–26). A high resolution optical satellite image dataset for ship recognition and some new baselines. Proceedings of the International Conference on Pattern Recognition Applications and Methods (SciTePress, 2017), Porto, Portugal.10.5220/0006120603240331 ↗
40. Li, K., Wan, G., Cheng, G., Meng, L., and Han, J. (2019). Object detection in optical remote sensing images: A survey and a new benchmark. arXiv.10.1016/j.isprsjprs.2019.11.023 ↗
41. Long, M., Cao, Y., Wang, J., and Jordan, M. (2015, January 6–11). Learning transferable features with deep adaptation networks. Proceedings of the International Conference on Machine Learning (PMLR, 2015), Lille, France.
42. Accurate object localization in remote sensing images based on convolutional neural networks10.1109/TGRS.2016.2645610 ↗