Abstract
Ships in remote sensing images are usually arranged in arbitrary direction, with small objects and dense distribution, and are easily interfered by background noise, which makes the existing object detection methods have a certain missed detection rate and false detection rate in this kind of complex scene. In order to solve the above problems, a neural network for ship detection is proposed. The network is composed of symmetrical deformation feature pyramid network, multi-scale attention network, multi-scale local context network and rotation branch. Firstly, in order to fully extract the features of ships with arbitrary directions and small objects in remote sensing images, an adaptive deformable convolution unit is designed and a symmetrical deformation feature pyramid network is constructed with it as core. Secondly, a multi-scale attention module is designed to guide the network to focus on ship areas of different scales and suppress background noise. Then, a multi-scale local context network is designed to capture the correlation between ships and local nearby objects, and to learn multi-scale co-occurrence features. Finally, a rotation bounding box is generated by the rotation branch, which is used to mark ships in arbitrary direction. The experimental results on two remote sensing public datasets DOTA, HRSC2016 show that the proposed method achieves state-of-the-art accuracy.
Similar content being viewed by others
References
Lu HL, Li YN, Li H (2019) Ship detection by an airborne Passive Interferometric Microwave Sensor (PIMS). IEEE Trans Geosci Remote Sens 58(4):2682–2694
Zhang T, Yang Z, Gan HP (2020) PolSAR ship detection using the joint polarimetric information. IEEE Trans Geosci Remote Sens 58(11):8225–8241
Wang CL, Bi FK, Zhang WP (2017) An intensity-space domain CFAR method for ship detection in HR SAR images. IEEE Geosci Remote Sens Lett 14(4):529–533
Leng X, Ji K, Zhou S (2016) An adaptive ship detection scheme for spaceborne SAR imagery. Sensors 16(9):1345
Li QP, Mou LC, Liu QJ (2018) HSF-Net: Multiscale deep feature embedding for ship detection in optical remote sensing imagery. IEEE Trans Geosci Remote Sens 56(12):7147–7161
Zhang ZH, Guo WW, Zhu SN (2018) Toward arbitrary-oriented ship detection with rotated region proposal and discrimination networks. IEEE Geoscience Remote Sensing Letters 15(11):1745–1749
Cui ZY, Li Q, Cao ZJ (2019) Dense attention pyramid networks for multi-scale ship detection in SAR images. IEEE Trans Geosci Remote Sens 57(11):8983–8997
Guo HY, Yang X, Wang NN (2020) A Rotational Libra R-CNN Method for Ship Detection. IEEE Trans Geosci Remote Sens 58(8):5772–5781
Wang JW, Yang WH, Li HC, Zhang HJ, Xia GS (2021) Learning center probability map for detecting objects in aerial images. IEEE Trans Geosci Remote Sens 59(5):4307–4323
Girshick R, Donahue J, Darrell T, Malik J, Vision, Recognition P (2014) (CVPR), Columbus, OH, 580-587. https://doi.org/10.1109/CVPR.2014.81
He K, Zhang X, Ren S, Sun J (2015) Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Pattern Anal Mach Intell 37(9):1904–1916
Girshick R (2015) Fast R-CNN. IEEE International Conference on Computer Vision (ICCV), Santiago, 1440-1448. https://doi.org/10.1109/ICCV.2015.169
He K, Gkioxari G, Dollár P (2017) R. Girshick, Mask R-CNN. IEEE International Conference on Computer Vision (ICCV), Venice, 2980-2988. https://doi.org/10.1109/ICCV.2017.322
Redmon J, Farhadi A (2017) YOLO9000: Better, Faster, Stronger. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, 6517-6525. https://doi.org/10.1109/CVPR.2017.690
Redmon J, Farhadi A (2018) YOLOv3: An incremental improvement. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). arXiv:1804.02767. Available: https://www.arxiv.org/abs/1804.02767
Bochkovskiy A, Wang CY, Liao HYM (2020) YOLOv4: Optimal speed and accuracy of object detection. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). arXiv preprint arXiv:2004.10934
Reed S, Fu CY, Berg AC (2016) Ssd: Single shot multibox detector. European conference on computer vision (ECCV), 9905, 21-37. https://doi.org/10.1007/978-3-319-46448-0_2
Jiang Y, Zhu X, Wang X (2017) R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection. IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Ma JQ (2020) RRPN++: Guidance towards more accurate scene text detection. IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Li C, Cong RM, Guo CL (2020) A parallel down-up fusion network for salient object detection in optical remote sensing images. Neurocomputing 415(20):411–420
Ding J, Xue N, Long Y, Xia G, Lu Q (2019) Learning RoI transformer for oriented object detection in aerial images. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2844-2853. https://doi.org/10.1109/CVPR.2019.00296
Yang X (2019) SCRDet: Towards more robust detection for small, cluttered and rotated objects. IEEE International Conference on Computer Vision (ICCV), 8231-8240. https://doi.org/10.1109/ICCV.2019.00832
Ming Q, Miao L, Zhou Z (2021) Cfc-net: A critical feature capturing network for arbitrary-oriented object detection in remote sensing images. arXiv preprint arXiv:2101.06849
Han J, Ding J, Xue N (2021) Redet: A rotation-equivariant detector for aerial object detection. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2786-2795
Yang X, Sun H, Fu K, Yang J, Sun X, Yan M, Guo Z (2018) Automatic ship detection in remote sensing images from google earth of complex scenes based on multiscale rotation dense feature pyramid networks. Remote Sens 10(1):132
Han X, Dai Q (2018) Batch-normalized Mlpconv-wise supervised pre-training network in network. Appl Intell 48:142–155. https://doi.org/10.1007/s10489-017-0968-2
Cui Z, Sun HM, Yu JT (2021) Fast detection method of green peach for application of picking robot. Appl Intell. https://doi.org/10.1007/s10489-021-02456-6
Ma N, Zhang X, Zheng HT, Sun J (2018) ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design. European conference on computer vision (ECCV), 11218, 116-131. https://doi.org/10.1007/978-3-030-01264-9_8
Ma J, Shao W, Ye H (2018) Arbitrary-oriented scene text detection via rotation proposals. IEEE Trans Multimed 20(11):3111–3122
Xia GS (2017) DOTA: A large-scale dataset for object detection in aerial images. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 3974-3983. https://doi.org/10.1109/CVPR.2018.00418
Liu ZK, Yuan L, Weng LB, Yang YP (2017) A high resolution optical satellite image dataset for ship recognition and some new baselines. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 324–331
Yedida R, Saha S, Prashanth T (2021) LipschitzLR: Using theoretically computed adaptive learning rates for fast convergence. Appl Intell 51:1460–1478. https://doi.org/10.1007/s10489-020-01892-0
Lin T, Goyal P, Girshick R, He K (2020) Focal loss for dense object detection. IEEE Trans Pattern Anal Mach Intell 42(2):318–327. https://doi.org/10.1109/TPAMI.2018.2858826
Tian Z, Shen C, Chen H, He T (2019) FCOS: Fully convolutional one-stage object detection. IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea (South), 9626-9635. https://doi.org/10.1109/ICCV.2019.00972
Ren S, He K, Girshick R, Sun J (2016) Faster r-cnn: Towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137–1149
Dai J, Li Y, He K, Sun J (2016) R-fcn: Object detection via region-based fully convolutional networks. Conference and Workshop on Neural Information Processing Systems (NIPS), 379-387
Pang J, Chen K, Shi J, Feng H, Ouyang W, Lin D (2019) Libra R-CNN: Towards balanced learning for object detection. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, 821-830. https://doi.org/10.1109/CVPR.2019.00091
Zhang H, Chang H, Ma B (2020) Dynamic R-CNN: Towards high quality object detection via dynamic training. Proceedings of the European conference on computer vision (ECCV), 2. arXiv preprint arXiv:2004.06002
Zhang G, Lu S, Zhang W (2019) CAD-Net: a context-aware detection network for objects in remote sensing imagery. IEEE Trans Geosci Remote Sens 57(12):10015–10024
Yu Y, Yang X, Li J, Gao X (2020) A cascade rotated anchor-aided detector for ship detection in remote sensing images. IEEE Trans Geosci Remote Sens. https://doi.org/10.1109/TGRS.2020.3040273
Cui ZY, Leng JX, Liu Y (2021) SKNet: detecting rotated ships as keypoints in optical remote sensing images. IEEE Trans Geosci Remote Sens 1–15. https://doi.org/10.1109/TGRS.2021.3053311
Yang X, Yan JC, Feng ZM, Recognition P (2019) (CVPR). arXiv preprint arXiv:1908.05612
Acknowledgements
The authors are grateful for collaborative funding support from the Humanity and Social Science Foundation of the Ministry of Education, China (21YJAZH077).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Cui, Z., Sun, HM., Yin, RN. et al. SDA-Net: a detector for small, densely distributed, and arbitrary-directional ships in remote sensing images. Appl Intell 52, 12516–12532 (2022). https://doi.org/10.1007/s10489-021-03148-x
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-021-03148-x