摘要
为解决复杂环境下机器人目标跟踪问题,提出了基于双层协作定位机制的移动机器人目标跟踪方法。该方法根据射频识别(RFID)和立体视觉信息实现外层粗定位与内层精确定位的相互协作以提高目标定位精度。首先利用RFID系统对携带标签的目标进行粗定位,然后在立体视觉系统中根据自适应模板匹配算法与扩展卡尔曼滤波算法提取目标头肩特征及运动特征,以实现精确定位目标。最后根据智能调速算法控制机器人连续稳定地跟随运动目标。实验结果表明该方法对遮挡及目标突然转弯的跟踪问题有较强的鲁棒性。
A method for mobile robots＇ human tracking based on the doublelayer cooperative locating mechanism is pro posed to realize the tracking in complex environments. The proposed method implements the coarse location and the fine location based on the data from radio frequency identification （RFID） and stereo vision to improve the locating accuracy. First, the coarse position of the given person is estimated by RFID. Then, the processing techniques of ex tended Kalman filter （EKF） and the adaptive template matching algorithm are applied to the narrowed ROI images for precise position based on the feature of headshoulder and motion. Finally, the intelligent gear shift control strate gy considering the distance between human and robot is utilized to drive the robot towards the given target. The ex perimental results show that the presented method can deal with the case when there is an occlusion or a sudden turning
出处
《高技术通讯》
CAS
CSCD
北大核心
2013年第11期1154-1160,共7页
Chinese High Technology Letters
基金
国家自然科学基金(61175087
61105033)
北京市自然科学基金(B类,KZ201110005004)
国家教育部留学回国人员科研启动基金(第40批)资助项目
关键词
双层协作定位机制
射频识别(RFID)
立体视觉
自适应模板匹配算法
智能调速
double-layer cooperative locating mechanism, radio frequency identification （ RFID）, stereo vision,adaptive template matching, intelligent gear shift control
