A New Ship Detection Method for Massive Data High-resolution Remote Sensing Images

摘要：

　　This paper proposes a new method for automatic ship targets detection in remote sensing images.The method uses adaptive segmentation algorithm for getting possible ship targets first,and then calculates Histograms of Oriented Gradient (HOG) feature to extract the structural information of ships,followed by supervised learning algorithm to identify the possible ship targets.Multi-scale sliding-window is used to handle targets with different scales.The experimental results prove that this new method has a good precision and robustness for most of the ship targets and give attention to the efficiency.

关键词： image process ship detection Histograms of Oriented Gradient (HOG) SVM

作者: Hao Sun Yu Li Ge Liu Hui Long Hongqi Wang

作者单位: Institute of Electronics, Chinese Academy of Sciences, Beijing 100190, China;Key Laboratory of Techn Institute of Electronics, Chinese Academy of Sciences, Beijing 100190, China;Key Laboratory of Techn

会议类型: 国际会议

会议名称: 2012 2nd international Conference on Materials Science and Information Technology(2012第二届材料科学与信息技术国际会议)(MSIT2012)

会议地点: 西安

会议语种:英文

页码: 1105-1109

在线出版日期: 2012-08-24（万方平台首次上网日期，不代表论文的发表时间）