Abstract
Object detection in aerial images is a challenging task due to the oriented and densely packed objects. However, densely packed objects constitute a significant characteristic of aerial images: objects are not randomly scattered around in images but in groups sharing similar orientations. Such a recurring pattern of object arrangement could enhance the rotated features and improve the detection performance. This paper proposes a novel and flexible Affinity-Aware Relation Network based on two-stage detectors. Specifically, an affinity-graph construction module is adopted to measure the affinity among objects and to select bounding boxes sharing high similarity with the reference box. Furthermore, we design a dynamic enhancement module, which uses the attention to learn neighbourhood message and dynamically determines weights for feature enhancement. Finally, we conduct experiments on several public benchmarks and achieve notable AP improvements as well as state-of-the-art performances on DOTA, HRSC2016 and UCAS-AOD datasets.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Bruna, J., Zaremba, W., Szlam, A., LeCun, Y.: Spectral networks and locally connected networks on graphs. ar**v preprint ar**v:1312.6203 (2013)
Chen, T., Saxena, S., Li, L., Fleet, D.J., Hinton, G.: Pix2seq: a language modeling framework for object detection. ar**v preprint ar**v:2109.10852 (2021)
Chen, X., Gupta, A.: An implementation of faster RCNN with study for region sampling. ar**v preprint ar**v:1702.02138 (2017)
Defferrard, M., Bresson, X., Vandergheynst, P.: Convolutional neural networks on graphs with fast localized spectral filtering. In: Advances in Neural information Processing Systems, vol. 29 (2016)
Ding, J., Xue, N., Long, Y., **a, G.S., Lu, Q.: Learning ROI transformer for oriented object detection in aerial images. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2849–2858 (2019)
Gilmer, J., Schoenholz, S.S., Riley, P.F., Vinyals, O., Dahl, G.E.: Neural message passing for quantum chemistry. In: International Conference on Machine Learning, pp. 1263–1272. PMLR (2017)
Guo, Z., Liu, C., Zhang, X., Jiao, J., Ji, X., Ye, Q.: Beyond bounding-box: convex-hull feature adaptation for oriented and densely packed object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8792–8801 (2021)
Hamilton, W., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Han, J., Ding, J., Li, J., **a, G.S.: Align deep features for oriented object detection. IEEE Trans. Geosci. Remote Sens. 60, 1–11 (2021)
Han, J., Ding, J., Xue, N., **a, G.S.: Redet: a rotation-equivariant detector for aerial object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2786–2795 (2021)
He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961–2969 (2017)
Hechtlinger, Y., Chakravarti, P., Qin, J.: A generalization of convolutional neural networks to graph-structured data. ar**v preprint ar**v:1704.08165 (2017)
Hou, L., Lu, K., Xue, J., Li, Y.: Shape-adaptive selection and measurement for oriented object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence (2022)
Huang, Z., Li, W., **a, X.G., Tao, R.: A general gaussian heatmap label assignment for arbitrary-oriented object detection. IEEE Trans. Image Process. 31, 1895–1910 (2022)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. ar**v preprint ar**v:1609.02907 (2016)
Klicpera, J., Bojchevski, A., Günnemann, S.: Predict then propagate: graph neural networks meet personalized pagerank. ar**v preprint ar**v:1810.05997 (2018)
Li, W., Chen, Y., Hu, K., Zhu, J.: Oriented reppoints for aerial object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1829–1838 (2022)
Liu, Z., Yuan, L., Weng, L., Yang, Y.: A high resolution optical satellite image dataset for ship recognition and some new baselines. In: International Conference on Pattern Recognition Applications and Methods, vol. 2, pp. 324–331. SciTePress (2017)
Lu, D.: Oskdet: Towards orientation-sensitive keypoint localization for rotated object detection. ar**v preprint ar**v:2104.08697 (2021)
Ming, Q., Miao, L., Zhou, Z., Dong, Y.: CFC-net: a critical feature capturing network for arbitrary-oriented object detection in remote-sensing images. IEEE Trans. Geosci. Remote Sensing 60, 1–14 (2021)
Ming, Q., Miao, L., Zhou, Z., Yang, X., Dong, Y.: Optimization for arbitrary-oriented object detection via representation invariance loss. IEEE Geosci. Remote Sens. Lett. 19, 1–5 (2021)
Ming, Q., Zhou, Z., Miao, L., Zhang, H., Li, L.: Dynamic anchor learning for arbitrary-oriented object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 2355–2363 (2021)
Monti, F., Boscaini, D., Masci, J., Rodola, E., Svoboda, J., Bronstein, M.M.: Geometric deep learning on graphs and manifolds using mixture model CNNs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5115–5124 (2017)
Pan, X., et al.: Dynamic refinement network for oriented and densely packed object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11207–11216 (2020)
Qian, W., Yang, X., Peng, S., Yan, J., Guo, Y.: Learning modulated loss for rotated object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 2458–2466 (2021)
Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. ar**v preprint ar**v:1804.02767 (2018)
Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211–252 (2015)
Scarselli, F., Gori, M., Tsoi, A.C., Hagenbuchner, M., Monfardini, G.: The graph neural network model. IEEE Trans. Neural Networks 20(1), 61–80 (2008)
Tian, Z., Shen, C., Chen, H., He, T.: FCOS: fully convolutional one-stage object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9627–9636 (2019)
Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Veličković, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., Bengio, Y.: Graph attention networks. ar**v preprint ar**v:1710.10903 (2017)
Wang, J., Ding, J., Guo, H., Cheng, W., Pan, T., Yang, W.: Mask OBB: a semantic attention-based mask oriented bounding box representation for multi-category object detection in aerial images. Remote Sens. 11(24), 2930 (2019)
Wang, J., Yang, W., Li, H.C., Zhang, H., **a, G.S.: Learning center probability map for detecting objects in aerial images. IEEE Trans. Geosci. Remote Sens. 59(5), 4307–4323 (2020)
Wei, H., Zhang, Y., Zhonghan, C., Li, H., Wang, H., Sun, X.: Oriented objects as pairs of middle lines. ISPRS J. Photogram. Remote Sens. 169, 268–279 (2020). https://doi.org/10.1016/j.isprsjprs.2020.09.022
Wu, F., Souza, A., Zhang, T., Fifty, C., Yu, T., Weinberger, K.: Simplifying graph convolutional networks. In: International Conference on Machine Learning, pp. 6861–6871. PMLR (2019)
**a, G.S., et al.: DOTA: a large-scale dataset for object detection in aerial images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3974–3983 (2018)
**e, X., Cheng, G., Wang, J., Yao, X., Han, J.: Oriented R-CNN for object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 3520–3529 (2021)
Xu, Y., et al.: Gliding vertex on the horizontal bounding box for multi-oriented object detection. IEEE Trans. Pattern Anal. Mach. Intell. 43(4), 1452–1459 (2020)
Yan, S., **ong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)
Yang, X., Hou, L., Zhou, Y., Wang, W., Yan, J.: Dense label encoding for boundary discontinuity free rotation detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 15819–15829 (2021)
Yang, X., Yan, J.: Arbitrary-oriented object detection with circular smooth label. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12353, pp. 677–694. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58598-3_40
Yang, X., Yan, J., Feng, Z., He, T.: R3det: refined single-stage detector with feature refinement for rotating object. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 3163–3171 (2021)
Yang, X., Yan, J., Liao, W., Yang, X., Tang, J., He, T.: Scrdet++: detecting small, cluttered and rotated objects via instance-level feature denoising and rotation loss smoothing. IEEE Trans. Pattern Anal. Mach. Intell. 45, 2384–2399 (2022)
Yang, X., Yan, J., Ming, Q., Wang, W., Zhang, X., Tian, Q.: Rethinking rotated object detection with gaussian wasserstein distance loss. In: International Conference on Machine Learning, pp. 11830–11841. PMLR (2021)
Yang, X., et al.: SCRDET: towards more robust detection for small, cluttered and rotated objects. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 8232–8241 (2019)
Yang, X., et al.: Learning high-precision bounding box for rotated object detection via kullback-leibler divergence. In: Advances in Neural Information Processing Systems, vol. 34 (2021)
Yang, X., et al.: The kfiou loss for rotated object detection. ar**v preprint ar**v:2201.12558 (2022)
Yang, Y., Chen, J., Zhong, X., Deng, Y.: Polygon-to-polygon distance loss for rotated object detection. In: AAAI Conference on Artificial Intelligence (2022)
Yi, J., Wu, P., Liu, B., Huang, Q., Qu, H., Metaxas, D.: Oriented object detection in aerial images with box boundary-aware vectors. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 2150–2159 (2021)
Zhang, S., Chi, C., Yao, Y., Lei, Z., Li, S.Z.: Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9759–9768 (2020)
Zhao, P., Qu, Z., Bu, Y., Tan, W., Guan, Q.: Polardet: a fast, more precise detector for rotated target in aerial images. Int. J. Remote Sens. 42(15), 5831–5861 (2021)
Zhou, L., Wei, H., Li, H., Zhao, W., Zhang, Y., Zhang, Y.: Arbitrary-oriented object detection in remote sensing images based on polar coordinates. IEEE Access 8, 223373–223384 (2020)
Zhu, H., Chen, X., Dai, W., Fu, K., Ye, Q., Jiao, J.: Orientation robust object detection in aerial images using deep convolutional neural network. In: 2015 IEEE International Conference on Image Processing (ICIP), pp. 3735–3739 (2015)
Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable detr: deformable transformers for end-to-end object detection. ar**v preprint ar**v:2010.04159 (2020)
Acknowledgements
This work is supported by the Natural Resources Science and Technology Project of Anhui Province (Grant No. 2021-K-14).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Fang, T., Liu, B., Zhao, Z., Chu, Q., Yu, N. (2023). Affinity-Aware Relation Network for Oriented Object Detection in Aerial Images. In: Wang, L., Gall, J., Chin, TJ., Sato, I., Chellappa, R. (eds) Computer Vision – ACCV 2022. ACCV 2022. Lecture Notes in Computer Science, vol 13845. Springer, Cham. https://doi.org/10.1007/978-3-031-26348-4_22
Download citation
DOI: https://doi.org/10.1007/978-3-031-26348-4_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-26347-7
Online ISBN: 978-3-031-26348-4
eBook Packages: Computer ScienceComputer Science (R0)