时空上下文融合的无人艇海面目标跟踪  

Sea surface object tracking for USV with spatio-temporal context fusion

作　　者：彭艳[1] 陈加宏 李小毛[1] 罗均[1] 谢少荣[1] 刘畅[1] 蒲华燕 PENG Yan;CHEN JiaHong;LI XiaoMao;LUO Jun;XIE ShaoRong;LIU Chang;PU HuaYan(School of Mechanical Engineering and Automation,Shanghai University,Shanghai 200444,China)

机构地区：[1]上海大学机电工程与自动化学院,上海200444

出　　处：《中国科学：技术科学》2018年第12期1357-1372,共16页Scientia Sinica(Technologica)

基　　金：国家自然科学基金(批准号:91648119;61773254;61673254)资助项目

摘　　要：视觉感知作为无人艇环境感知的重要组成部分,为无人艇智能控制提供十分重要的外界信息.准确、鲁棒且实时的海面目标跟踪算法可以有效提升无人艇的智能化水平.海面目标跟踪面临着几个独特的挑战:目标尺度变化极大、目标视角变化极大、目标抖动剧烈.为了解决上述海面目标跟踪任务中面临的三个难点,本文提出了一种时空上下文融合的目标跟踪算法,该算法结合了深度网络多尺度检测的图像空间上下文信息和相关滤波跟踪的视频时间上下文信息,实现了实时、精确且鲁棒的目标跟踪效果.最后,以无人艇在东海、南海实际作业场景中采集的图像数据作为跟踪算法的测试集,验证了该跟踪算法的有效性.As an important component of unmanned surface vessel environment awareness, visual perception provides very important external information for intelligent control of USV. Accurate, robust and real-time sea surface object tracking algorithms can effectively improve the intelligence level of USV. Sea surface object tracking faces several unique challenges: the object scale changes greatly,the object perspective changes greatly, and the object jitters drastically. In order to solve the three difficulties encountered in the above sea object tracking task, this paper proposed an object tracking algorithm with spatio-temporal context fusion. This algorithm combines the image space context information of the multi-scale detection of deep network and the correlated filter tracking video time context information. It is a real-time, accurate and robust object tracking. Finally, using the image data of the USV in the actual operation scene in the East China Sea and South China Sea as the test set of the tracking algorithm, the effectiveness of the tracking algorithm is verified.

关 键 词：海面目标跟踪 时空上下文 相关滤波跟踪 多尺度检测 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]