摘要
为降低视觉设备感知航行环境时,水面光照反射对船舶位姿估计和环境地图重构的影响,在HSV(hue,saturation,value)颜色空间下,采用K均值聚类算法对近岸航行环境图像进行聚类分割处理。改进快速特征点提取和描述算法(oriented FAST and rotated BRIEF,ORB)来提高即时定位与地图构建(simultaneous localization and mapping,SLAM)效率,缩短特征点匹配时间,改善对外界环境的感知效果并提升船舶自身位姿估计精度。采用2020年南宁海事局执法船进港和靠泊期间由单目相机拍摄的视频数据进行实例验证。结果表明,提出的算法比传统SLAM算法的运行耗时更少,与传统定位设备输出轨迹的偏差较小,可为船舶全面立体感知海上航行环境提供研究基础。
In order to reduce the influence of the surface light reflection on the ship position-orientation estimation and the environment map reconstruction when using visual equipments to perceive the navigation environment,this paper uses the K-means clustering algorithm to conduct the clustering and segmentation of near-shore navigation environment images under the HSV(hue,saturation,value)color space.The fast feature point extraction and description algorithm(that is the oriented FAST and rotated BRIEF(ORB))is improved so as to improve the efficiency of simultaneous localization and mapping(SLAM),shorten the matching time of feature points,improve the perception of the external environment,and improve the ship itself position-orientation estimation accuracy.The video data captured by the monocular camera during the entry and berthing operations of the law enforcement vessels of the Nanning Maritime Safety Administration in 2020 are used for example verification.The results show that,the proposed algorithm takes less running time than the traditional SLAM algorithm,and is of small trajectory deviation from the traditional positioning equipment,which can provide research basis for the ship’s comprehensive three-dimensional perception of the maritime navigation environment.
作者
付洪宇
史国友
冉洋
高邈
刘姿含
FU Hongyu;SHI Guoyou;RAN Yang;GAO Miao;LIU Zihan(Navigation College,Dalian Maritime University,Dalian 116026,Liaoning,China;Key Laboratory of Navigation Safety Guarantee of Liaoning Province,Dalian Maritime University,Dalian 116026,Liaoning,China;School of Marine Science and Technology,Tianjin University,Tianjin 300072,China)
出处
《上海海事大学学报》
北大核心
2022年第4期1-8,共8页
Journal of Shanghai Maritime University
基金
国家自然科学基金(51579025)
辽宁省自然科学基金(20170540090)。
