全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

基于自适应空间融合的遥感图像目标检测器
A Remote Sensing Image Object Detector Based on Adaptive Spatial Fusion

DOI: 10.12677/CSA.2023.134079, PP. 799-807

Keywords: 遥感图像,目标检测,自适应空间融合结构,样本标签匹配策略
Remote Sensing Image
, Object Detection, Adaptive Spatial Fusion Structure, Sample Label Assignment Strategy

Full-Text   Cite this paper   Add to My Lib

Abstract:

随着遥感技术的蓬勃发展,日益庞大的遥感数据使得传统的图像处理手段已经不足以满足需求,因此,将深度学习目标检测技术应用于遥感领域成为了最优解决方案。然而,由于遥感图像小目标排列密集、尺度变化剧烈,使得直接将适用于自然场景的目标检测算法迁移到遥感领域的效果不佳。本文选择YOLOX为基础网络进行改进,在特征提取网络后加入自适应空间特征融合结构,将深层特征信息与浅层特征信息融合,提升小目标的识别率。此外,本研究对样本标签匹配策略进行了优化,以解决高长宽比类目标物体角度偏移敏感的问题,并通过修改损失函数降低正负样本不平衡问题带来的影响。我们在遥感图像数据集DOTA上进行训练和测试,实验结果表明,改进的YOLOX算法检测效果更好,mAP达到了79.07%,比YOLOX提高了2.75%。另外,在HRSC2016数据集上也进行了实验,实验证明了模型具有优秀的鲁棒性。
With the rapid development of remote sensing technology, the increasingly large remote sensing data has rendered traditional image processing techniques inadequate to meet the demands. As a result, applying deep learning object detection techniques to the remote sensing field has become the optimal solution. However, the dense arrangement of small objects and drastic scale variations in remote sensing images make the direct migration of object detection algorithms applicable to natural scenes to the field of remote sensing ineffective. In this paper, we improve the YOLOX algorithm by incorporating an adaptive spatial feature fusion structure after the feature extraction network, which fuses deep and shallow features to enhance the recognition rate of small objects. In addition, this study optimized the sample label assignment strategy to address the issue of angle offset sensitivity for narrow class target objects with high aspect ratios. Furthermore, the impact of the imbalance between positive and negative samples was mitigated by modifying the loss function. We conduct experiments on the DOTA remote sensing image dataset for training and testing. The results demonstrate that the improved YOLOX algorithm achieves better detection performance, with a mAP of 79.07%, which is 2.75% higher than that of YOLOX. Furthermore, we conduct experiments on the HRSC2016 dataset, which confirms the model’s excellent robustness.

References

[1]  Luo, S., Yu, J., Xi, Y., et al. (2022) Aircraft Target Detection in Remote Sensing Images Based on Improved YOLOv5. IEEE Access, 10, 5184-5192. https://doi.org/10.1109/ACCESS.2022.3140876
[2]  Zhu, X., Lyu, S., Wang, X., et al. (2021) TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-Captured Scenarios. Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, 11-17 October 2021, 2778-2788. https://doi.org/10.1109/ICCVW54120.2021.00312
[3]  Fu, K., Chang, Z., Zhang, Y., et al. (2020) Rotation Aware and Multi-Scale Convolutional Neural Network for Object Detection in Remote Sensing Images. ISPRS Journal of Photogrammetry and Remote Sensing, 161, 294-308. https://doi.org/10.1016/j.isprsjprs.2020.01.025
[4]  Hou, L., Lu, K., Xue, J., et al. (2022) Shape-Adaptive Selection and Measurement for Oriented Object Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 36, 923-932. https://doi.org/10.1609/aaai.v36i1.19975
[5]  胡俊顾, 王秋红. 基于遥感图像的多模态小目标检测[J]. 图学学报, 2022, 43(2): 197-204.
[6]  Ge, Z., Liu, S., Wang, F., et al. (2021) Yolox: Exceeding Yolo Series in 2021. ArXiv: 2107.08430.
[7]  Lin, T.Y., Dollár, P., Girshick, R., et al. (2017) Feature Pyramid Networks for Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, 21-26 July 2017, 936-944. https://doi.org/10.1109/CVPR.2017.106
[8]  Lin, T.Y., Goyal, P., Girshick, R., et al. (2017) Focal Loss for Dense Ob-ject Detection. Proceedings of the IEEE International Conference on Computer Vision, Venice, 22-29 October 2017, 2980-2988. https://doi.org/10.1109/ICCV.2017.324
[9]  Yang, X., Yang, J., Yan, J., et al. (2019) SCRDet: Towards More Robust Detection for Small, Cluttered and Rotated Objects. Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, 27 October-2 November 2019, 8231-8240. https://doi.org/10.1109/ICCV.2019.00832
[10]  Wei, J., Wang, S. and Huang, Q. (2020) F3Net: Fusion, Feedback and Focus for Salient Object Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 34, 12321-12328. ,
https://doi.org/10.1609/aaai.v34i07.6916
[11]  Ding, J., Xue, N., Long, Y., et al. (2019) Learning Roi Transformer for Oriented Object Detection in Aerial Images. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, 15-20 June 2019, 2844-2853. ,
https://doi.org/10.1109/CVPR.2019.00296
[12]  Xu, Y., Fu, M., Wang, Q., et al. (2020) Gliding Ver-tex on the Horizontal Bounding Box for Multi-Oriented Object Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43, 1452-1459. ,
https://doi.org/10.1109/TPAMI.2020.2974745
[13]  Yang, X., Yan, J., Feng, Z., et al. (2021) R3Det: Refined Sin-gle-Stage Detector with Feature Refinement for Rotating Object. Proceedings of the AAAI Conference on Artificial Intel-ligence, 35, 3163-3171. ,
https://doi.org/10.1609/aaai.v35i4.16426
[14]  Ming, Q., Miao, L., Zhou, Z., et al. (2021) Sparse Label Assignment for Oriented Object Detection in Aerial Images. Remote Sensing, 13, Article 2664. ,
https://doi.org/10.3390/rs13142664
[15]  Ming, Q., Zhou, Z., Miao, L., et al. (2021) Dynamic Anchor Learning for Arbitrary Oriented Object Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 35, 2355-2363. ,
https://doi.org/10.1609/aaai.v35i3.16336

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133