[1]曲海成,李瑞柯,王蒙,等.基于特征重用和膨胀卷积的遥感图像舰船检测[J].智能系统学报,2024,19(5):1298-1308.[doi:10.11992/tis.202304002]
QU Haicheng,LI Ruike,WANG Meng,et al.Ship detection in remote sensing images via feature reuse and dilated convolution[J].CAAI Transactions on Intelligent Systems,2024,19(5):1298-1308.[doi:10.11992/tis.202304002]
点击复制
QU Haicheng,LI Ruike,WANG Meng,et al.Ship detection in remote sensing images via feature reuse and dilated convolution[J].CAAI Transactions on Intelligent Systems,2024,19(5):1298-1308.[doi:10.11992/tis.202304002]
基于特征重用和膨胀卷积的遥感图像舰船检测
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
19
期数:
2024年第5期
页码:
1298-1308
栏目:
人工智能院长论坛
出版日期:
2024-09-05
- Title:
- Ship detection in remote sensing images via feature reuse and dilated convolution
- Keywords:
- remote sensing image; ship detection; feature reuse; dilated convolution; split attention; group convolution; feature pyramid; deformable convolution
- 分类号:
- TP751；TN911.73
- 文献标志码:
- 2024-08-28
- 摘要:
- 在光学遥感图像中，港口内的舰船目标通常处于密集的船只群中，并受到周围环境的干扰和遮挡，如集装箱、车辆等。为了进一步提高现有舰船目标检测算法的精度和泛化性能，提出了一种基于特征重用和膨胀卷积的遥感图像舰船检测算法。首先构建了基于分组卷积和拆分注意力的残差块来提取特征，同时嵌入可变形卷积提取更加符合舰船尺度变化的特征；接着，构造了多尺度感受野模块，通过并行提取多尺度特征后再进行融合来减少信息损失；最后，在原有特征金字塔的基础上构建了一条自底向上的特征重用聚合路径以提高特征表示能力。在大型遥感数据集DOTA和舰船数据集HRSC2016上进行实验，实验结果表明，所提方法能够有效缓解舰船目标漏检和误检问题，提高了遥感图像舰船目标检测的精度。
- Abstract:
- In optical remote sensing images, ship targets in ports are often densely grouped and obstructed by the surrounding environment, such as containers and vehicles. To further improve the accuracy and generalization performance of existing ship target detection algorithms, this study proposes a remote sensing image ship detection algorithm based on feature reuse and dilated convolution. First, a residual block based on grouped convolution and split attention is constructed to extract features, with deformable convolution embedded to better handle ship scale variations. Afterward, a multiscale receptive field module is designed to reduce information loss by parallel extraction and fusion of multiscale features. Finally, a bottom-up feature reuse aggregation path is developed based on the original feature pyramid to enhance feature representation. Experiments were conducted on the large-scale remote sensing dataset, DOTA and the ship dataset, HRSC2016. The results show that the proposed method effectively alleviates the issues of missing and false detections of ship targets, leading to increased accuracy in ship target detection in remote sensing images.
- 参考文献/References:
-
[1] 龚声蓉, 徐少杰, 周立凡, 等. 融入混合注意力的可变形空洞卷积近岸SAR小舰船检测[J]. 中国图象图形学报, 2022, 27(12): 3663-3676.
GONG Shengrong, XU Shaojie, ZHOU Lifan, et al. Deformable atrous convolution nearshore SAR small ship detection incorporating mixed attention[J]. Journal of image and graphics, 2022, 27(12): 3663-3676.
[2] 黎经元, 厉小润, 赵辽英. 基于边缘线分析与聚合通道特征的港口舰船检测[J]. 光学学报, 2019, 39(8): 217-226.
LI Jingyuan, LI Xiaorun, ZHAO Liaoying. Docked ship detection based on edge line analysis and aggregation channel features[J]. Acta optica sinica, 2019, 39(8): 217-226.
[3] VIOLA P, JONES M. Rapid object detection using a boosted cascade of simple features[C]//Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Kauai: IEEE, 2001: 511-518.
[4] 林鹏宇, 马晓珊, 彭晓东. 基于仿真模板和SuperGlue的舰船匹配检测[J]. 计算机仿真, 2023, 40(11): 11-15.
LIN Pengyu, MA Xiaoshan, PENG Xiaodong. Ship target match method based on simulation template and SuperGlue feature matching[J]. Computer simulation, 2023, 40(11): 11-15.
[5] STAUFFER C, GRIMSON W E L. Adaptive background mixture models for real-time tracking[C]//Proceedings of 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Fort Collins: IEEE, 1999: 246-252.
[6] 成艳, 孟祥勇, 于雪莲, 等. 海上舰船目标轮廓检测算法[J]. 智能计算机与应用, 2022, 12(8): 119-122.
CHENG Yan, MENG Xiangyong, YU Xuelian, et al. Target contour detection algorithm for marine ships[J]. Intelligent computer and applications, 2022, 12(8): 119-122.
[7] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84-90.
[8] REN Shaoqing, HE Kaiming, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE transactions on pattern analysis and machine intelligence, 2017, 39(6): 1137-1149.
[9] XIE Xingxing, CHENG Gong, WANG Jiabao, et al. Oriented R-CNN for object detection[C]//2021 IEEE/CVF International Conference on Computer Vision. Montreal: IEEE, 2021: 3500-3509.
[10] HAN Jiaming, DING Jian, XUE Nan, et al. ReDet: a rotation-equivariant detector for aerial object detection[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE, 2021: 2785-2794.
[11] DING Jian, XUE Nan, LONG Yang, et al. Learning RoI transformer for oriented object detection in aerial images[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019: 2844-2853.
[12] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 779-788.
[13] LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[C]//2017 IEEE International Conference on Computer Vision. Venice: IEEE, 2017: 2999-3007.
[14] HAN Jiaming, DING Jian, LI Jie, et al. Align deep features for oriented object detection[J]. IEEE transactions on geoscience and remote sensing, 2021, 60: 1-11.
[15] 王慧赢, 王春平, 付强, 等. 面向嵌入式平台的轻量级光学遥感图像舰船检测[J]. 光学学报, 2023, 43(12): 121-134.
WANG Huiying, WANG Chunping, FU Qiang, et al. Lightweight ship detection based on optical remote sensing images for embedded platform[J]. Acta optica sinica, 2023, 43(12): 121-134.
[16] TIAN Zhi, SHEN Chunhua, CHEN Hao, et al. FCOS: fully convolutional one-stage object detection[C]//2019 IEEE/CVF International Conference on Computer Vision. Seoul: IEEE, 2019: 9626-9635.
[17] YANG Ze, LIU Shaohui, HU Han, et al. RepPoints: point set representation for object detection[C]//2019 IEEE/CVF International Conference on Computer Vision. Seoul: IEEE, 2019: 9656-9665.
[18] LAW H, DENG Jia. CornerNet: detecting objects as paired keypoints[C]//European Conference on Computer Vision. Cham: Springer, 2018: 765-781.
[19] YANG Xue, SUN Hao, FU Kun, et al. Automatic ship detection in remote sensing images from google earth of complex scenes based on multiscale rotation dense feature pyramid networks[J]. Remote sensing, 2018, 10(1): 132.
[20] 成倩, 李佳, 杜娟. 基于YOLOv5的光学遥感图像舰船目标检测算法[J]. 系统工程与电子技术, 2023, 45(5): 1270-1276.
CHENG Qian, LI Jia, DU Juan. Ship target detection algorithm of optical remote sensing image based on YOLOv5[J]. Systems engineering and electronics, 2023, 45(5): 1270-1276.
[21] RAN Bohao, YOU Yanan, LI Zezhong, et al. Arbitrary-oriented ship detection method based on improved regression model for target direction detection network[C]//IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium. Waikoloa: IEEE, 2020: 964-967.
[22] 王昌安, 田金文. 生成对抗网络辅助学习的舰船目标精细识别[J]. 智能系统学报, 2020, 15(2): 296-301.
WANG Chang’an, TIAN Jinwen. Fine-grained inshore ship recognition assisted by deep-learning generative adversarial networks[J]. CAAI transactions on intelligent systems, 2020, 15(2): 296-301.
[23] WANG Panqu, CHEN Pengfei, YUAN Ye, et al. Understanding convolution for semantic segmentation[C]//2018 IEEE Winter Conference on Applications of Computer Vision. Lake Tahoe: IEEE, 2018: 1451-1460.
[24] DAI Jifeng, QI Haozhi, XIONG Yuwen, et al. Deformable convolutional networks[C]//2017 IEEE International Conference on Computer Vision. Venice: IEEE, 2017: 764-773.
[25] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 770-778.
[26] ZHANG Hang, WU Chongruo, ZHANG Zhongyue, et al. ResNeSt: split-attention networks[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. New Orleans: IEEE, 2022: 2735-2745.
[27] WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[C]//European Conference on Computer Vision. Cham: Springer, 2018: 3-19.
[28] XIA Guisong, BAI Xiang, DING Jian, et al. DOTA: a large-scale dataset for object detection in aerial images[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 3974-3983.
[29] LIU Zikun, YUAN Liu, WENG Lubin, et al. A high resolution optical satellite image dataset for ship recognition and some new baselines[C]//Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods. Porto: SCITEPRESS-Science and Technology Publications, 2017: 324-331.
[30] ZHOU Yue, YANG Xue, ZHANG Gefan, et al. MMRotate: a rotated object detection benchmark using PyTorch[C]//Proceedings of the 30th ACM International Conference on Multimedia. Lisboa Portugal: ACM, 2022: 7331-7334.
[31] DENG Jia, DONG Wei, SOCHER R, et al. ImageNet: a large-scale hierarchical image database[C]//2009 IEEE Conference on Computer Vision and Pattern Recognition. Miami: IEEE, 2009: 248-255.
[32] YANG Sheng, PEI Ziqiang, ZHOU Feng, et al. Rotated faster R-CNN for oriented object detection in aerial images[C]//Proceedings of the 2020 3rd International Conference on Robot Systems and Applications. Chengdu: ACM, 2020: 35-39.
- 相似文献/References:
-
[1]刘富,于鹏,刘坤.采用独立分量分析Zernike矩的遥感图像飞机目标识别[J].智能系统学报,2011,6(1):51.
LIU Fu,YU Peng,LIU Kun.Research concerning aircraft recognition of remote sensing images based on ICA Zernike invariant moments[J].CAAI Transactions on Intelligent Systems,2011,6():51.
[2]龙海侠,吴淑雷,吕雁.基于多样性变异的QPSO算法的遥感图像分类[J].智能系统学报,2015,10(6):938.[doi:10.11992/tis.201507045]
LONG Haixia,WU Shulei,LYU Yan.Classification of multispectral remote sensing image based on QPSO and diversity-mutation[J].CAAI Transactions on Intelligent Systems,2015,10():938.[doi:10.11992/tis.201507045]
[3]吴诗婳,吴一全,周建江.直线截距直方图城区遥感图像多阈值分割[J].智能系统学报,2018,13(2):227.[doi:10.11992/tis.201609012]
WU Shihua,WU Yiquan,ZHOU Jianjiang.Multi-level thresholding for remote sensing image of urban area based on line intercept histogram[J].CAAI Transactions on Intelligent Systems,2018,13():227.[doi:10.11992/tis.201609012]
[4]李亚飞,董红斌.基于卷积神经网络的遥感图像分类研究[J].智能系统学报,2018,13(4):550.[doi:10.11992/tis.201706078]
LI Yafei,DONG Hongbin.Classification of remote-sensing image based on convolutional neural network[J].CAAI Transactions on Intelligent Systems,2018,13():550.[doi:10.11992/tis.201706078]
[5]王昌安,田金文.生成对抗网络辅助学习的舰船目标精细识别[J].智能系统学报,2020,15(2):296.[doi:10.11992/tis.201901004]
WANG Changan,TIAN Jinwen.Fine-grained inshore ship recognition assisted by deep-learning generative adversarial networks[J].CAAI Transactions on Intelligent Systems,2020,15():296.[doi:10.11992/tis.201901004]
[6]王晓林,苏松志,刘晓颖,等.一种基于级联神经网络的飞机检测方法[J].智能系统学报,2020,15(4):697.[doi:10.11992/tis.201908028]
WANG Xiaolin,SU Songzhi,LIU Xiaoying,et al.Cascade convolutional neural networks for airplane detection[J].CAAI Transactions on Intelligent Systems,2020,15():697.[doi:10.11992/tis.201908028]
[7]赵文清,康怿瑾,赵振兵,等.改进YOLOv5s的遥感图像目标检测[J].智能系统学报,2023,18(1):86.[doi:10.11992/tis.202203013]
ZHAO Wenqing,KANG Yijin,ZHAO Zhenbing,et al.A remote sensing image object detection algorithm with improved YOLOv5s[J].CAAI Transactions on Intelligent Systems,2023,18():86.[doi:10.11992/tis.202203013]
[8]刘庆鑫,李霓,贾鹤鸣,等.改进䲟鱼优化算法和熵测度的图像多阈值分割[J].智能系统学报,2024,19(2):381.[doi:10.11992/tis.202205018]
LIU Qingxin,LI Ni,JIA Heming,et al.An improved remora optimization algorithm for multilevel thresholding image segmentation using an entropy measure[J].CAAI Transactions on Intelligent Systems,2024,19():381.[doi:10.11992/tis.202205018]
[9]邵凯,王明政,王光宇.基于Transformer的多尺度遥感语义分割网络[J].智能系统学报,2024,19(4):920.[doi:10.11992/tis.202304026]
SHAO Kai,WANG Mingzheng,WANG Guangyu.Transformer-based multiscale remote sensing semantic segmentation network[J].CAAI Transactions on Intelligent Systems,2024,19():920.[doi:10.11992/tis.202304026]
[10]梁礼明,冯耀,龙鹏威,等.基于MobileViT和多尺度特征聚合的遥感图像目标检测[J].智能系统学报,2024,19(5):1168.[doi:10.11992/tis.202310022]
LIANG Liming,FENG Yao,LONG Pengwei,et al.Remote sensing image object detection based on MobileViT and multiscale feature aggregation[J].CAAI Transactions on Intelligent Systems,2024,19():1168.[doi:10.11992/tis.202310022]
备注/Memo
收稿日期:2023-4-3。
基金项目:国家自然科学基金面上项目(42271409)；辽宁省高等学校基本科研项目(LIKMZ20220699).
作者简介:曲海成，副教授，博士，辽宁工程技术大学软件学院/人工智能学院副院长，主要研究方向为视觉信息计算。主持辽宁省自然科学基金项目1项、辽宁省教育厅面上项目2项，发表学术论文60余篇。E-mail：quhaicheng@lntu.edu.cn;李瑞柯，硕士研究生，主要研究方向为遥感图像目标检测。E-mail：lrk19990101@163.com;王蒙，硕士研究生，主要研究方向为遥感图像目标检测。E-mail：1377423034@qq.com。
通讯作者:曲海成. E-mail：quhaicheng@lntu.edu.cn
更新日期/Last Update:
2024-09-05