Anchor-Free Arbitrary-Oriented Object Detector Using Box Boundary-Aware Vectors

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

Haitao Guo¹  Donghang Yu¹  Qing Xu¹  Yuzhun Lin¹  Xiangyun Liu¹  Jun Lu¹  Junfeng Xu² 

[1] PLA Strategic Support Force Information Engineering University, Zhengzhou, China;School of Non-Commissioned Officer, Space Engineering University, Beijing, China;

关键词: Boundary-aware vectors;    convolutional neural network (CNN);    oriented object detection;    remote sensing image;   

DOI  :  10.1109/JSTARS.2022.3158905

来源: DOAJ

【 摘 要 】

Characterized by complicated backgrounds, various types, large size variations, and arbitrary orientations, the detection and recognition of arbitrary-oriented objects in remote sensing images are challenging. To address the aforementioned problem, an anchor-free arbitrary-oriented object detector using box boundary-aware vectors is proposed. With the idea of CenterNet to detect objects as points, oriented object detection is achieved by predicting the center, the box boundary-aware vectors, the size, and the type of the bounding box. In the feature extraction stage of the designed architecture, Res2Net, a multiscale convolutional neural network, is used to extract feature maps of different scales and adaptively spatial feature fusion is adopted to improve the detector's adaptability to objects of different sizes. In the detector, a context enhancement module with a multibranch network is designed to enhance the contextual information of the objects and improve the detector's robustness to the complicated backgrounds. Experiments are carried on three challenging benchmarks (i.e., HRSC2016, UCAS-AOD, and DOTA) and our method achieves state-of-the-art performance with 90.30%, 89.70%, and 77.18% mAP, respectively.

【 授权许可】

Unknown