Journal of Computer Applications ›› 2018, Vol. 38 ›› Issue (12): 3631-3637.DOI: 10.11772/j.issn.1001-9081.2018040933

Previous Articles     Next Articles

Ship detection under complex sea and weather conditions based on deep learning

XIONG Yongping1,2, DING Sheng1,2, DENG Chunhua1,2, FANG Guokang1,2, GONG Rui1,2   

  1. 1. School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan Hubei 430065, China;
    2. Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System, Wuhan Hubei 430065, China
  • Received:2018-05-07 Revised:2018-07-03 Online:2018-12-10 Published:2018-12-15
  • Contact: 邓春华
  • Supported by:
    This work is partially supported by the Natural Science Foundation of Hubei Province (2018CFB195), the Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Open Fund (2018QNQ10), the Defense Pre-research Project of Wuhan University of Science and Technology (Y50001).


熊咏平1,2, 丁胜1,2, 邓春华1,2, 方国康1,2, 龚锐1,2   

  1. 1. 武汉科技大学 计算机科学与技术学院, 武汉 430065;
    2. 智能信息处理与实时工业系统湖北省重点实验室, 武汉 430065
  • 通讯作者: 邓春华
  • 作者简介:熊咏平(1994-),男,湖北黄冈人,硕士研究生,主要研究方向:计算机视觉、深度学习;丁胜(1975-),男,湖北武汉人,副教授,博士,CCF会员,主要研究方向:计算机视觉;邓春华(1984-),男,湖南郴州人,讲师,博士,主要研究方向:计算机视觉、机器学习;方国康(1994-),男,湖北恩施人,硕士研究生,主要研究方向:深度学习;龚锐(1995-),男,湖北赤壁人,硕士研究生,主要研究方向:机器学习。
  • 基金资助:

Abstract: In order to solve the detection of ships with different types and sizes under complex marine environment, a real-time object detection algorithm based on deep learning was proposed. Firstly, a discriminant method between sharp and fuzzy such as rainy and foggy images was proposed. Then a multi-scale object detection algorithm based on deep learning framework of You Only Look Once (YOLO) v2 was proposed. Finally, concerning the character of remote sensing images of ships, an improved non-maximum supression and saliency partitioning algorithm was proposed to optimize the final detection results. The experimental results show that, on the dataset of ship detection in an open competition under complex sea conditions and meteorological conditions, the precision of the proposed method is increased by 16% compared with original YOLO v2 algorithm.

Key words: YOLO v2, object detection, multi-scale object detection, saliency segmentation

摘要: 为了解决复杂海情环境下的不同种类和大小的舰船检测问题,提出一种实时的深度学习的目标检测算法。首先,提出了一种清晰图片和模糊图片(雨、雾等图片)判别的方法;然后,在YOLO v2的深度学习框架的基础上提出一种多尺度目标检测算法;最后,针对遥感图像舰船目标的特点,提出了一种改进的非极大值抑制和显著性分割算法,对最终的检测结果进一步优化。在复杂海情和气象条件下的舰船目标公开比赛的数据集上,实验结果表明,相比原始的YOLO v2,该方法的准确率提升了16%。

关键词: YOLO v2, 目标检测, 多尺度目标检测, 显著性分割

CLC Number: