NAO机器人自主目标跟踪算法研究  

Research on Autonomous Target Tracking Algorithm for NAO Robot Computer Engineering and Applications

作　　者：潘峥嵘[1] 张玉阳[1] 朱翔[1] 

机构地区：[1]兰州理工大学电气工程与信息工程学院,兰州730050

出　　处：《自动化与仪表》2017年第8期12-16,共5页Automation & Instrumentation

摘　　要：针对目前应用最广的新型仿人形NAO机器人,如何应用于动态背景条件下并对运动目标进行自主检测跟踪,对此该文采用了一种基于三帧差分法和Camshift算法相结合的目标跟踪方法。首先通过SURF算法对相邻两帧图像背景进行匹配,变换到静态背景条件下,再通过三帧差分法检测运动目标;之后将目标运动信息融合到Camshift算法颜色概率分布直方图的计算中,实现目标自动识别跟踪并排除与目标颜色相似的背景干扰。试验表明,NAO机器人能够对运动目标进行自主跟踪。According to a new type of humanoid NAO robot,how to apply it to the dynamic background conditions and track the moving target,a target tracking method based on the three-frame difference method and Camshift algorithm was proposed. Firstly,the SURF algorithm was used to transform the moving background to a static background,and then the moving target was detected by the three-frame difference method. Then,the target motion information was fused into the Camshift algorithm to calculate the color probability distribution histogram. It can automatically identify the moving target and eliminate the same color of background interference. Experiments show that the NAO robot can track moving targets autonomously.

关 键 词：NAO机器人 动态背景 SURF算法 CAMSHIFT算法 目标跟踪 

分 类 号：TP751.1[自动化与计算机技术—检测技术与自动化装置]