摘要
机器人的研究是当今人工智能领域的热点之一,而双目视觉又是机器人研究领域的热点之一。文章对机器人双目视觉测距避障的实现过程和原理进行介绍。其中特征的提取与匹配是实现双目测距的核心和难点,匹配算法的选择和实现将决定匹配后测距的精确与否。文章提出一种基于特征点的立体匹配算法的融合实现方案,最终证明了该算法的有效性和可行性。
Robot research is one of the hot spots in the field of artificial intelligence today, and binocular vision is one of the hot spots in robotics research. This paper introduces the realization process and principle of robotic binocular vision ranging obstacle avoidance. The feature extraction and matching are the core and difficult to realize binocular distance measurement. The selection and implementation of the matching algorithm will determine whether the matching ranging is accurate or not. This paper presents a feature-based stereo matching algorithm to achieve the fusion scheme. Finally, the effectiveness and feasibility of the algorithm are proved.
出处
《无线互联科技》
2018年第5期99-101,共3页
Wireless Internet Technology
关键词
双目视觉
特征提取
双目标定
立体匹配
binocular vision
feature extraction
binocular set
stereoscopic match