摘要
机器人的视觉伺服是机器人领域重要的研究方向。着力于提高机器人视觉反馈系统的实时性,提出了基于运动分析的的运动目标实时跟踪方法。该方法采用形态学方法标记连通域,并基于最小二乘法拟合运动轨迹曲线,预测下一时刻位置,设定连通域搜索范围,从而提高搜索速度。仿真结果表明:该方法处理效果良好,能满足后续系统实时性要求。
Robotic visual servo system is an important research direction in the field of robotics. To enhance performance of real-time of robotic visual feedback system,method for realtime tracking of moving target based on motion analysis is proposed. The method uses morphological way to label connected domain,and fits trajectory curve based on least square method,predict position of the next and set searching scope of connected domain,so as to improve searching speed. Simulation results show that the approach is effective and can meet the requirements of real-time of system.
出处
《传感器与微系统》
CSCD
2016年第7期58-61,共4页
Transducer and Microsystem Technologies
关键词
实时跟踪
视觉伺服
位置预测
运动分析
real-time tracking
visual servo
position prediction
motion analysis
