Abstract:

Dynamic target detection and target tracking are hot issues in the field of image. In order to explore its application value in the field of mobile robot, a dynamic target detection and tracking system is designed based on hexapod robot, and a region merging algorithm is proposed to solve the problem of non-rigid moving object detection dispersion. Firstly, the dynamic target detection method is introduced with region merging and adaptive external point filtering based on motion compensation method. This method achieves the accurate compensation of the moving background through symmetric matching and adaptive external point filtering, and achieves complete detection of non-rigid objects by region merging. Secondly, the application of target tracking algorithm based on KCF（Kernel Correlation Filter） in hexapod robot platform is studied, and the angle tracking of moving target is realized by adaptive adjustment of tracking speed. Finally, the moving target detection and tracking algorithm proposed in this paper is applied to hexapod robot system. Experiments show that the proposed algorithm can realize exact detection and real-time tracking of moving targets during the moving process of hexapod robot.

Key words: hexapod robot, motion compensation, dynamic target detection, target tracking, region merging

摘要：

动态目标检测与目标跟踪是图像领域的热点研究问题，为研究其在移动机器人领域的应用价值，设计了六足机器人动态目标检测与跟踪系统。针对非刚体运动目标容易被检测为多个分散区域的问题提出区域合并算法，并通过对称匹配、自适应外点滤除对运动背景进行精确补偿，最终基于背景补偿法实现对运动目标的精确检测。研究了基于KCF（Kernel Correlation Filter）的目标跟踪算法在六足机器人平台上的应用，设计了自适应跟踪算法实现六足机器人对运动目标的角度跟踪。将运动目标检测及跟踪算法应用于六足机器人系统。实验表明，在六足机器人移动过程中，系统可对运动目标进行精确检测与跟踪。

关键词: 六足机器人, 运动补偿, 动态目标检测, 目标跟踪, 区域合并