Single Shot Anchor Refinement Network for Oriented Object Detection in Optical Remote Sensing Imagery

IEEE Access

Xing Zhong¹  Songze Bao¹  Mengyang Li¹  Xiaonan Zhang¹  Ruifei Zhu¹  Zhuqiang Li² 

[1] Chinese Academy of Sciences, Changchun Institute of Optics, Fine Mechanics and Physics, Changchun, China;Key Laboratory of Satellite Remote Sensing Application Technology of Jilin Province, Chang Guang Satellite Technology Company Ltd., Changchun, China;

关键词: Convolutional neural network (CNN);    remote sensing;    oriented object detection;    anchor refinement;   

DOI  :  10.1109/ACCESS.2019.2924643

来源: DOAJ

【 摘 要 】

Object detection is a challenging task in the field of remote sensing applications due to the complex backgrounds and uncertain orientation of targets. Compared with the horizontal bounding box, the oriented bounding box can provide orientation information while retaining the true size. Most existing oriented object detection methods are based on Faster-RCNN and the other one-stage methods that can achieve real-time speed but have shortcomings in localization and detection accuracy. To further enhance the performance of one-stage methods, we propose an oriented object detection framework that is based on the single shot detector, namely, single shot anchor refinement network (S²ARN). The S²ARN obtains the accurate detection results by performing two consecutive regressions. More precisely, the multilevel features of the backbone are used to regress the coordinate offsets between the predefined rotated anchors and the ground-truth boxes to generate the refined anchors. The classification and regression subnetworks assigned to the output features are used to perform the second regression to determine the class labels and further adjust the location of the refined anchors. In addition, receptive field amplification modules (RFAMs) are inserted to enlarge the receptive field and extract more discriminative features. Furthermore, in the anchor matching step, angle-related Intersection over Union (ArIoU) is used to calculate the Intersection over Union (IoU) score instead of the traditional method. Benefiting from the multiple regressions and the insensitivity of the ArIoU score to the angle deviation, the angle sampling interval of the rotated anchor can be reduced. The experimental results for the two public datasets, HRSC2016 and UCAS-AOD, demonstrate the effectiveness of the proposed network.

【 授权许可】

Unknown