摘要
研究基于开源机器人运行系统ROS(Robot Operating System)架构的移动机器人目标跟踪系统的设计与实现。考虑目标人检测的准确性和跟踪鲁棒性的需要,首先对跟踪目标进行特征提取,并利用深度信息实现基于最近点位置信息的目标跟踪。跟踪过程中通过欧氏聚类法去除噪声信息,在深度信息无法解决干扰物影响跟踪效果的情况下,使用基于颜色信息的Cam-Shift跟踪方法实现目标跟踪,提高了系统抗干扰能力。实验结果验证了该系统的可行性和稳定性。
In this paper,open source robot operating system based mobile robot target tracking system is designed and implemented.Considering the accuracy of target detection and robustness of tracking,target feature extraction is carried out firstly,and the depth information is used to track the target which is based on the nearest point position information.During tracking,tracking process by European clustering method removes the noise information.When the depth information is not enough to track,it is reasonable to use the Cam-Shift method which is based on RGB information to track.
出处
《工业控制计算机》
2016年第4期68-70,72,共4页
Industrial Control Computer
基金
国家自然科学基金自助项目(61573100
61573101)