Multi-scale Feature Enhanced Network for Remote Sensing Object Detection
DOI:
https://doi.org/10.54097/n1htyf98Keywords:
Remote Sensing Images, Target Detection, YOLO, Transformer, Deformable ConvolutionAbstract
The task of remote sensing image target detection still faces many challenges: the target scale, orientation and spatial distribution are very different. In particular, small targets are difficult to identify in complex backgrounds, and the change of target geometry will affect feature extraction and positioning accuracy. In view of the above problems, this paper builds an improved detection network MSTD-Net based on YOLO26 m. Firstly, the global context Transformer module (GCTM) is introduced into the backbone network to capture the context information between long-distance spatial regions. Secondly, the dynamic deformable convolution module (DDCN) is used to adaptively adjust the convolution sampling position according to the geometric shape of the target, so that the network can better adapt to the targets with different shapes and orientations. In addition, this paper uses the dynamic Wise-IoU loss function (DWL) to adjust the contribution of training samples with different positioning quality in the bounding box regression process. In this paper, a large number of comparative experiments are carried out on DOTA15, UCAS-AOD and HRSC2016 datasets. The experimental results show that the mAP @ 50 index of MSTD-Net on the three datasets reaches 7575 %, 9730 % and 7403 %, respectively. Compared with the baseline model YOLO26m, MSTD-Net increased mAP @ 50 by 100 %, 026 % and 792 % on DOTA15, UCAS-AOD and HRSC2016 datasets, respectively. The ablation experiment further verifies that the three improved modules all have gains in detection performance, but the improvement is different on different data sets.
Downloads
References
[1] Cheng, G., & Han, J. (2016). A survey on object detection in optical remote sensing images. ISPRS Journal of Photogrammetry and Remote Sensing, 117, 11–28. https://doi.org/10.1016/j.isprsjprs.2016.03.004. DOI: https://doi.org/10.1016/j.isprsjprs.2016.03.014
[2] Xia, G. S., Bai, X., Ding, J., Zhu, Z., Belongie, S., Luo, J., Datcu, M., Pelillo, M., & Zhang, L. (2018). DOTA: A large-scale dataset for object detection in aerial images. In Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (pp. 3974–3983). https://doi.org/10.1109/CVPR.2018.00423. DOI: https://doi.org/10.1109/CVPR.2018.00418
[3] Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster R-CNN: Towards real-time object detection with region proposal networks. Advances in Neural Information Processing Systems, 28, 91–99. https://doi.org/10.48550/arXiv.1506.01497.
[4] Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You only look once: Unified, real-time object detection. In Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (pp. 779–788). https://doi.org/10.1109/CVPR.2016.91. DOI: https://doi.org/10.1109/CVPR.2016.91
[5] Lin, T. Y., Dollár, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017). Feature pyramid networks for object detection. In Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (pp. 2117–2125). https://doi.org/10.1109/CVPR.2017.106. DOI: https://doi.org/10.1109/CVPR.2017.106
[6] Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., & Houlsby, N. (2021). An image is worth 16×16 words: Transformers for image recognition at scale. In International Conference on Learning Representations. https://doi.org/10.48550/arXiv.2010.11929.
[7] Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021). Swin Transformer: Hierarchical vision transformer using shifted windows. In Proc. IEEE/CVF Int. Conf. Comput. Vis. (pp. 10012–10022). https://doi.org/10.1109/ICCV48922.2021.00986. DOI: https://doi.org/10.1109/ICCV48922.2021.00986
[8] Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., & Wei, Y. (2017). Deformable convolutional networks. In Proc. IEEE/CVF Int. Conf. Comput. Vis. (pp. 764–773). https://doi.org/10.1109/ICCV.2017.89. DOI: https://doi.org/10.1109/ICCV.2017.89
[9] Zhu, X., Hu, H., Lin, S., & Dai, J. (2019). Deformable ConvNets v2: More deformable, better results. In Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (pp. 9308–9316). https://doi.org/10.1109/CVPR.2019.00953. DOI: https://doi.org/10.1109/CVPR.2019.00953
[10] Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., & Savarese, S. (2019). Generalized intersection over union: A metric and a loss for bounding box regression. In Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (pp. 658–666). https://doi.org/10.1109/CVPR.2019.00074. DOI: https://doi.org/10.1109/CVPR.2019.00075
[11] Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., & Ren, D. (2020). Distance-IoU loss: Faster and better learning for bounding box regression. In Proc. AAAI Conf. Artif. Intell., 34(7), 12993–13000. https://doi.org/10.1609/aaai.v34i07.6999. DOI: https://doi.org/10.1609/aaai.v34i07.6999
[12] Tong, Z., Chen, Y., Xu, Z., & Yu, R. (2023). Wise-IoU: Bounding Box Regression Loss with Dynamic Focusing Mechanism. arXiv preprint arXiv:2301.10051. https://doi.org/10.48550/arXiv.2301.10051.
[13] Liu, Z., Wang, H., Weng, L., & Yang, Y. (2016). Ship Rotated Bounding Box Space for Ship Extraction From High-Resolution Optical Satellite Images With Complex Backgrounds. IEEE Geoscience and Remote Sensing Letters, 13(8), 1074–1078. https://doi.org/10.1109/LGRS.2016.2573468. DOI: https://doi.org/10.1109/LGRS.2016.2565705
[14] Zhu, H., Chen, X., Dai, W., Fu, K., Ye, Q., & Jiao, J. (2015). Orientation Robust Object Detection in Aerial Images Using Deep Convolutional Neural Network. In Proceedings of the IEEE International Conference on Image Processing (ICIP) (pp. 3735–3739). https://doi.org/10.1109/ICIP.2015.7351491. DOI: https://doi.org/10.1109/ICIP.2015.7351502
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Frontiers in Computing and Intelligent Systems
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
