卢翔, 刘景泰, 于凯妍, 李海丰, 李岩, 孙雷. 面向竞争型网络机器人的运动目标快速检测[J]. 机器人, 2011, 33(6): 658-665,672.
引用本文: 卢翔, 刘景泰, 于凯妍, 李海丰, 李岩, 孙雷. 面向竞争型网络机器人的运动目标快速检测[J]. 机器人, 2011, 33(6): 658-665,672.
LU Xiang, LIU Jingtai, YU Kaiyan, LI Haifeng, LI Yan, SUN Lei. Rapid Detection of Moving Target in the Competitive Networked Robots[J]. ROBOT, 2011, 33(6): 658-665,672.
Citation: LU Xiang, LIU Jingtai, YU Kaiyan, LI Haifeng, LI Yan, SUN Lei. Rapid Detection of Moving Target in the Competitive Networked Robots[J]. ROBOT, 2011, 33(6): 658-665,672.

面向竞争型网络机器人的运动目标快速检测

Rapid Detection of Moving Target in the Competitive Networked Robots

  • 摘要: 搭建了基于高速视觉的竞争型网络机器人系统.通过对比选取并融合了多种识别方法,设计了一套面向竞争型网络机器人的目标快速识别跟踪算法.采用动态窗口技术,并通过对不同传统方法的改进,进一步提高了该算法的实时性.本文方法能够在较复杂的背景下跟踪运动的目标机器人,具有较小的运算量及较好的鲁棒性.实验结果表明,该算法处理640×480像素的8位灰度图像的时间不超过5ms.

     

    Abstract: A competitive networked robot system based on high-speed vision is built.At the same time,by comparison, selection and integration of a variety of identification methods,a quick and effective target recognition and tracking algorithm for competitive networked robots is designed.Dynamic window technique and the improvement of traditional methods further enhance the system's real-time performance.The algorithm can track the moving target robot in complex background,with good robustness and less computation.Experimental results show that it takes less than 5 ms to process one frame of grey image of the size 640×480 pixels.

     

/

返回文章
返回