Orientation-First Strategy With Angle Attention Module for Rotated Object Detection in Remote Sensing Images

doi:10.1109/jstars.2022.3209349

CIOMP OpenIR

	Orientation-First Strategy With Angle Attention Module for Rotated Object Detection in Remote Sensing Images
	Y. X. Zhang; Y. C. Wang; N. Zhang; Z. Li; Z. K. Zhao; Y. X. Gao; D. D. Xu and G. L. Ben
	2022
发表期刊	Ieee Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN	1939-1404
卷号	15 页码:8492-8505
摘要	Recently, object detection in remote sensing images (RSIs) have received extensive attention and made significant progress. Nonetheless, the arbitrary orientations of objects in RSIs make their detection a challenging task. Most of the existing detection methods are difficult to extract the orientation features of objects due to the lack of directionality of conventional convolutions. In addition, the boundary discontinuity in angle regression affects the detection of object orientations. In response to these problems, this article proposes an orientation-first refinement detector (OFRDet), which is based on a strategy that enables the detector to detect the angle of an object ahead of others and presets oriented anchors. In OFRDet, we propose an angle encoding regression module (AERM) and an angle channel attention module (ACAM). AERM transforms angle detection into multiparameter regression, which eliminates boundary discontinuities. ACAM uses convolution kernels with different angles to extract directional features purposefully according to the preset oriented anchors. After these two modules, more accurate bounding boxes are generated and sent to the refined stage to obtain the final detection results. We evaluate our method and demonstrate the effectiveness of it by conducting experiments on two challenging and credible datasets, DOTA, HRSC2016. OFRDet achieves competitive results 79.56%, 96.29% mAP on the two datasets, respectively.
DOI	10.1109/jstars.2022.3209349
URL	查看原文
收录类别	sci ; ei
语种	英语
引用统计
文献类型	期刊论文
条目标识符	http://ir.ciomp.ac.cn/handle/181722/66964
专题	中国科学院长春光学精密机械与物理研究所
推荐引用方式 GB/T 7714	Y. X. Zhang,Y. C. Wang,N. Zhang,et al. Orientation-First Strategy With Angle Attention Module for Rotated Object Detection in Remote Sensing Images[J]. Ieee Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2022,15:8492-8505.
APA	Y. X. Zhang.,Y. C. Wang.,N. Zhang.,Z. Li.,Z. K. Zhao.,...&D. D. Xu and G. L. Ben.(2022).Orientation-First Strategy With Angle Attention Module for Rotated Object Detection in Remote Sensing Images.Ieee Journal of Selected Topics in Applied Earth Observations and Remote Sensing,15,8492-8505.
MLA	Y. X. Zhang,et al."Orientation-First Strategy With Angle Attention Module for Rotated Object Detection in Remote Sensing Images".Ieee Journal of Selected Topics in Applied Earth Observations and Remote Sensing 15(2022):8492-8505.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Orientation-First St（12938KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览请求全文