ABSTRACT
Oriented bounding boxes are widely used for object detection in aerial images. Existing oriented object detection methods typically follow the general object detection paradigm by adding an extra rotation angle on the horizontal bounding boxes. However, the angular periodicity incurs the difficulty in angle regression and rotation sensitivity on bounding boxes. In this paper, we propose a new anchor-free oriented object detector, Polar Ray Network (PRNet), where object keypoints are represented by polar coordinates without angle regression. Our PRNet learns a set of polar rays from the object center to boundary with predefined equal-distributed angles. We introduce a dynamic PointConv module to optimize the regression of polar ray by incorporating object corner features. Furthermore, a classification feature guidance module is presented to improve the classification accuracy by incorporating more spatial contents from polar rays. Experimental results on two public datasets, i.e., DOTA and HRSC2016, demonstrate that the proposed PRNet significantly outperforms existing anchor-free detectors, and shows highly competitiveness with the state-of-the-art two-stage anchor-based methods.
- Kean Chen, Jianguo Li, Weiyao Lin, John See, Ji Wang, Lingyu Duan, Zhibo Chen, Changwei He, and Junni Zou. 2019. Towards accurate one-stage object detection with ap-loss. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 5119--5127.Google Scholar
- Zhiming Chen, Kean Chen, Weiyao Lin, John See, Hui Yu, Yan Ke, and Cong Yang. 2020. PIoU Loss: Towards Accurate Oriented Object Detection in Complex Environments. In European Conference on Computer Vision. Springer, 195--211.Google Scholar
- Jian Ding, Nan Xue, Yang Long, Gui-Song Xia, and Qikai Lu. 2019. Learning roi transformer for oriented object detection in aerial images. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2849--2858.Google ScholarCross Ref
- Mark Everingham, Luc Van Gool, Christopher KI Williams, John Winn, and Andrew Zisserman. 2007. The PASCAL visual object classes challenge 2007 (VOC2007) results. (2007).Google Scholar
- Mark Everingham and John Winn. 2011. The pascal visual object classes challenge 2012 (voc2012) development kit. Pattern Analysis, Statistical Modelling and Computational Learning, Tech. Rep, Vol. 8 (2011).Google Scholar
- Kaiming He, Georgia Gkioxari, Piotr Dollár, and Ross Girshick. 2017. Mask r-cnn. In Proceedings of the IEEE international conference on computer vision. 2961--2969.Google ScholarCross Ref
- Borui Jiang, Ruixuan Luo, Jiayuan Mao, Tete Xiao, and Yuning Jiang. 2018. Acquisition of localization confidence for accurate object detection. In Proceedings of the European Conference on Computer Vision (ECCV). 784--799.Google ScholarDigital Library
- Yingying Jiang, Xiangyu Zhu, Xiaobing Wang, Shuli Yang, Wei Li, Hua Wang, Pei Fu, and Zhenbo Luo. 2017. R2cnn: rotational region cnn for orientation robust scene text detection. arXiv preprint arXiv:1706.09579 (2017).Google Scholar
- Xiang Li, Wenhai Wang, Xiaolin Hu, Jun Li, Jinhui Tang, and Jian Yang. 2020 b. Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection. arXiv preprint arXiv:2011.12885 (2020).Google Scholar
- Xiang Li, Wenhai Wang, Lijun Wu, Shuo Chen, Xiaolin Hu, Jun Li, Jinhui Tang, and Jian Yang. 2020 c. Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection. arXiv preprint arXiv:2006.04388 (2020).Google Scholar
- Yangyang Li, Qin Huang, Xuan Pei, Licheng Jiao, and Ronghua Shang. 2020 a. RADet: Refine feature pyramid network and multi-layer attention network for arbitrary-oriented object detection of remote sensing images. Remote Sensing, Vol. 12, 3 (2020), 389.Google ScholarCross Ref
- Minghui Liao, Baoguang Shi, Xiang Bai, Xinggang Wang, and Wenyu Liu. 2017. Textboxes: A fast text detector with a single deep neural network. In Proceedings of the AAAI conference on artificial intelligence, Vol. 31. Google ScholarDigital Library
- Minghui Liao, Zhen Zhu, Baoguang Shi, Gui-song Xia, and Xiang Bai. 2018. Rotation-sensitive regression for oriented scene text detection. In Proceedings of the IEEE conference on computer vision and pattern recognition. 5909--5918.Google ScholarCross Ref
- Tsung-Yi Lin, Piotr Dollár, Ross Girshick, Kaiming He, Bharath Hariharan, and Serge Belongie. 2017a. Feature pyramid networks for object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2117--2125.Google ScholarCross Ref
- Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, and Piotr Dollár. 2017b. Focal loss for dense object detection. In Proceedings of the IEEE international conference on computer vision. 2980--2988.Google ScholarCross Ref
- Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, and Alexander C Berg. 2016a. Ssd: Single shot multibox detector. In European conference on computer vision. Springer, 21--37.Google ScholarCross Ref
- Zikun Liu, Hongzhen Wang, Lubin Weng, and Yiping Yang. 2016b. Ship rotated bounding box space for ship extraction from high-resolution optical satellite images with complex backgrounds. IEEE Geoscience and Remote Sensing Letters, Vol. 13, 8 (2016), 1074--1078.Google ScholarCross Ref
- Qi Ming, Zhiqiang Zhou, Lingjuan Miao, Hongwei Zhang, and Linhao Li. 2020. Dynamic Anchor Learning for Arbitrary-Oriented Object Detection. arXiv preprint arXiv:2012.04150 (2020).Google Scholar
- Ramin Nabati and Hairong Qi. 2019. Rrpn: Radar region proposal network for object detection in autonomous vehicles. In 2019 IEEE International Conference on Image Processing (ICIP). IEEE, 3093--3097.Google ScholarCross Ref
- Xingjia Pan, Yuqiang Ren, Kekai Sheng, Weiming Dong, Haolei Yuan, Xiaowei Guo, Chongyang Ma, and Changsheng Xu. 2020. Dynamic refinement network for oriented and densely packed object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 11207--11216.Google ScholarCross Ref
- Wen Qian, Xue Yang, Silong Peng, Yue Guo, and Junchi Yan. 2019. Learning modulated loss for rotated object detection. arXiv preprint arXiv:1911.08299 (2019).Google Scholar
- Joseph Redmon and Ali Farhadi. 2017. YOLO9000: better, faster, stronger. In Proceedings of the IEEE conference on computer vision and pattern recognition. 7263--7271.Google ScholarCross Ref
- Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. arXiv preprint arXiv:1506.01497 (2015).Google Scholar
- Liu Shuai, Zhang Lu, Lu Huchuan, and He You. 2021. Center-Boundary Dual Attention for Oriented Object Detection in Remote Sensing Images. IEEE Transactions on Geoscience and Remote Sensing (2021), 1--14. https://doi.org/10.1109/TGRS.2021.3069056Google Scholar
- Zhi Tian, Chunhua Shen, and Hao Chen. 2020. Conditional convolutions for instance segmentation. arXiv preprint arXiv:2003.05664 (2020).Google Scholar
- Zhi Tian, Chunhua Shen, Hao Chen, and Tong He. 2019. Fcos: Fully convolutional one-stage object detection. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 9627--9636.Google ScholarCross Ref
- Zhi Tian, Bowen Zhang, Hao Chen, and Chunhua Shen. 2021. Instance and Panoptic Segmentation Using Conditional Convolutions. arXiv preprint arXiv:2102.03026 (2021).Google Scholar
- Yuxin Wang, Hongtao Xie, Zheng-Jun Zha, Mengting Xing, Zilong Fu, and Yongdong Zhang. 2020. Contournet: Taking a further step toward accurate arbitrary-shaped scene text detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 11753--11762.Google ScholarCross Ref
- Haoran Wei, Yue Zhang, Zhonghan Chang, Hao Li, Hongqi Wang, and Xian Sun. 2020. Oriented objects as pairs of middle lines. ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 169 (2020), 268--279.Google ScholarCross Ref
- Yue Wu, Yinpeng Chen, Lu Yuan, Zicheng Liu, Lijuan Wang, Hongzhi Li, and Yun Fu. 2020. Rethinking classification and localization for object detection. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 10186--10195.Google ScholarCross Ref
- Gui-Song Xia, Xiang Bai, Jian Ding, Zhen Zhu, Serge Belongie, Jiebo Luo, Mihai Datcu, Marcello Pelillo, and Liangpei Zhang. 2018. DOTA: A large-scale dataset for object detection in aerial images. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 3974--3983.Google ScholarCross Ref
- Zhifeng Xiao, Linjun Qian, Weiping Shao, Xiaowei Tan, and Kai Wang. 2020. Axis learning for orientated objects detection in aerial images. Remote Sensing, Vol. 12, 6 (2020), 908.Google ScholarCross Ref
- Enze Xie, Peize Sun, Xiaoge Song, Wenhai Wang, Xuebo Liu, Ding Liang, Chunhua Shen, and Ping Luo. 2020. Polarmask: Single shot instance segmentation with polar representation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 12193--12202.Google ScholarCross Ref
- Yongchao Xu, Mingtao Fu, Qimeng Wang, Yukang Wang, Kai Chen, Gui-Song Xia, and Xiang Bai. 2020. Gliding vertex on the horizontal bounding box for multi-oriented object detection. IEEE transactions on pattern analysis and machine intelligence (2020).Google ScholarCross Ref
- Brandon Yang, Gabriel Bender, Quoc V Le, and Jiquan Ngiam. 2019 a. Condconv: Conditionally parameterized convolutions for efficient inference. arXiv preprint arXiv:1904.04971 (2019). Google ScholarDigital Library
- Xue Yang, Liping Hou, Yue Zhou, Wentao Wang, and Junchi Yan. 2020. Dense Label Encoding for Boundary Discontinuity Free Rotation Detection. arXiv preprint arXiv:2011.09670 (2020).Google Scholar
- Xue Yang, Qingqing Liu, Junchi Yan, Ang Li, Zhiqiang Zhang, and Gang Yu. 2019 b. R3det: Refined single-stage detector with feature refinement for rotating object. arXiv preprint arXiv:1908.05612 (2019).Google Scholar
- Xue Yang and Junchi Yan. 2020. Arbitrary-oriented object detection with circular smooth label. In European Conference on Computer Vision. Springer, 677--694.Google ScholarDigital Library
- Xue Yang, Jirui Yang, Junchi Yan, Yue Zhang, Tengfei Zhang, Zhi Guo, Xian Sun, and Kun Fu. 2019 c. Scrdet: Towards more robust detection for small, cluttered and rotated objects. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 8232--8241.Google ScholarCross Ref
- Jingru Yi, Pengxiang Wu, Bo Liu, Qiaoying Huang, Hui Qu, and Dimitris Metaxas. 2021. Oriented object detection in aerial images with box boundary-aware vectors. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. 2150--2159.Google ScholarCross Ref
- Gongjie Zhang, Shijian Lu, and Wei Zhang. 2019. CAD-Net: A context-aware detection network for objects in remote sensing imagery. IEEE Transactions on Geoscience and Remote Sensing, Vol. 57, 12 (2019), 10015--10024.Google ScholarCross Ref
- Zenghui Zhang, Weiwei Guo, Shengnan Zhu, and Wenxian Yu. 2018. Toward arbitrary-oriented ship detection with rotated region proposal and discrimination networks. IEEE Geoscience and Remote Sensing Letters, Vol. 15, 11 (2018), 1745--1749.Google ScholarCross Ref
- Fang Zhao, Jian Zhao, Shuicheng Yan, and Jiashi Feng. 2018. Dynamic conditional networks for few-shot learning. In Proceedings of the European Conference on Computer Vision (ECCV). 19--35.Google ScholarCross Ref
- Pengbo Zhao, Zhenshen Qu, Yingjia Bu, Wenming Tan, Ye Ren, and Shiliang Pu. 2020. PolarDet: A Fast, More Precise Detector for Rotated Target in Aerial Images. arXiv preprint arXiv:2010.08720 (2020).Google Scholar
- Xingyi Zhou, Dequan Wang, and Philipp Kr"ahenbühl. 2019. Objects as points. arXiv preprint arXiv:1904.07850 (2019).Google Scholar
- Xinyu Zhou, Cong Yao, He Wen, Yuzhi Wang, Shuchang Zhou, Weiran He, and Jiajun Liang. 2017. East: an efficient and accurate scene text detector. In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. 5551--5560.Google ScholarCross Ref
- Yixing Zhu, Jun Du, and Xueqing Wu. 2020. Adaptive period embedding for representing oriented objects in aerial images. IEEE Transactions on Geoscience and Remote Sensing, Vol. 58, 10 (2020), 7247--7257.Google ScholarCross Ref
Index Terms
- Polar Ray: A Single-stage Angle-free Detector for Oriented Object Detection in Aerial Images
Recommendations
A comprehensive survey of oriented object detection in remote sensing images
AbstractWith the rapid development of object detection, it is widely used in many scenes and images. However, the dense arrangement of objects with different dimensions, orientations and aspect ratios in remote sensing and aerial images ...
Highlights- Investigated the oriented object detection method based on deep learning.
- ...
Quaternion polar harmonic Fourier moments for color images
Quaternion polar harmonic Fourier moments (QPHFM) is proposed.Complex Chebyshev-Fourier moments (CHFM) is extended to quaternion QCHFM.Comparison experiments between QPHFM and QZM, QPZM, QOFMM, QCHFM and QRHFM are conducted.QPHFM performs superbly in ...
Arbitrary-Oriented Object Detection with Circular Smooth Label
Computer Vision – ECCV 2020AbstractArbitrary-oriented object detection has recently attracted increasing attention in vision for their importance in aerial imagery, scene text, and face etc. In this paper, we show that existing regression-based rotation detectors suffer the problem ...
Comments