Ship detection based on fused features and rebuilt YOLOv3 networks in optical remote-sensing images

被引:29
作者
Wang, Qin [1 ]
Shen, Fengyi [1 ]
Cheng, Lifu [2 ]
Jiang, Jianfei [1 ]
He, Guanghui [1 ]
Sheng, Weiguang [1 ]
Jing, Naifeng [1 ]
Mao, Zhigang [1 ]
机构
[1] Shanghai Jiao Tong Univ, Dept Microelect & Nanosci, Shanghai 200240, Peoples R China
[2] Shanghai Aerosp Technol Inst, Dept Space Avion, Shanghai, Peoples R China
基金
中国国家自然科学基金;
关键词
OBJECT DETECTION; SAR IMAGES;
D O I
10.1080/01431161.2020.1811422
中图分类号
TP7 [遥感技术];
学科分类号
081102 ; 0816 ; 081602 ; 083002 ; 1404 ;
摘要
Automatic ship detection in optical remote-sensing (ORS) images has wide applications in civil and military fields. Research on ship detection in ORS images started late compared to synthetic aperture radar (SAR) images, and it is difficult for traditional image-processing algorithms to achieve high accuracy. Therefore, we propose a ship-detection method based on a deep convolutional neural network that is modified from YOLOv3. We call it fused features and rebuilt (FFR) YOLOv3. We tried some improvements to enhance its performance in ship-detection regions. We added a squeeze-and-excitation (SE) structure to the backbone network to strengthen the ability to extract features. Through a large number of experiments, we optimized the backbone network to improve the speed. We improved the multi-scale detection of YOLOv3 by fusing multi-scale feature maps and regenerating them with a high-resolution network, which can improve the accuracy of detection and location. We used the public HRSC2016 ship-detection dataset and remote-sensing images collected from Google Earth to train, test, and verify our network, which reached a detection speed of about 27 frames per second (fps) on an NVIDIA RTX2080ti, with recall (R) = 95.32% and precision (P) = 95.62%. Experiments show that our network has better accuracy and speed than other methods. In addition, it has strong robustness and can adapt to complex environments like inshore ship detection.
引用
收藏
页码:520 / 536
页数:17
相关论文
共 47 条
  • [1] Single Shot Anchor Refinement Network for Oriented Object Detection in Optical Remote Sensing Imagery
    Bao, Songze
    Zhong, Xing
    Zhu, Ruifei
    Zhang, Xiaonan
    Li, Zhuqiang
    Li, Mengyang
    [J]. IEEE ACCESS, 2019, 7 : 87150 - 87161
  • [2] Inshore ship detection in high resolution satellite images: Approximation of harbours using sea-land segmentation
    Besbinar, Beril
    Alatan, A. Aydin
    [J]. IMAGE AND SIGNAL PROCESSING FOR REMOTE SENSING XXI, 2015, 9643
  • [3] Soft-NMS - Improving Object Detection With One Line of Code
    Bodla, Navaneeth
    Singh, Bharat
    Chellappa, Rama
    Davis, Larry S.
    [J]. 2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, : 5562 - 5570
  • [4] A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection
    Cai, Zhaowei
    Fan, Quanfu
    Feris, Rogerio S.
    Vasconcelos, Nuno
    [J]. COMPUTER VISION - ECCV 2016, PT IV, 2016, 9908 : 354 - 370
  • [5] Multi-class geospatial object detection and geographic image classification based on collection of part detectors
    Cheng, Gong
    Han, Junwei
    Zhou, Peicheng
    Guo, Lei
    [J]. ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2014, 98 : 119 - 132
  • [6] Crisp DJ, 2004, Tech. Rep. DSTO-RR-0272
  • [7] Dai J, 2016, PROCEEDINGS 2016 IEEE INTERNATIONAL CONFERENCE ON INDUSTRIAL TECHNOLOGY (ICIT), P1796, DOI 10.1109/ICIT.2016.7475036
  • [8] Ship Detection in Optical Remote Sensing Images Based on Saliency and a Rotation-Invariant Descriptor
    Dong, Chao
    Liu, Jinghong
    Xu, Fang
    [J]. REMOTE SENSING, 2018, 10 (03):
  • [9] CenterNet: Keypoint Triplets for Object Detection
    Duan, Kaiwen
    Bai, Song
    Xie, Lingxi
    Qi, Honggang
    Huang, Qingming
    Tian, Qi
    [J]. 2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, : 6568 - 6577
  • [10] An automatic ship and ship wake detection system for spaceborne SAR images in coastal regions
    Eldhuset, K
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 1996, 34 (04): : 1010 - 1019