基于双目视觉的新型并联机构末端位姿检测

针对一种新型3-DOF驱动冗余并联机构,为提高双目视觉末端位姿检测的实时性和精度,首先采用Harris-SIFT算法对图片进行预匹配,通过Harris提取图像特征点,并采用SIFT特征描述子对图像进行匹配,使得匹配结果兼具实时性和稳定性;为解决匹配算法存在的误差匹配和错误匹配问题,提出一种改进的RANSAC算法对预匹配结果进行提纯,该改进方法通过分格取点和提前取点验算临时模型克服常规RANSAC算子匹配不准确、算法费时的缺点.实验结果表明,采用改进的RANSAC算法提纯较常规RANSAC算子不仅可以大幅度降低图像处理时间,而且可以更大程度提高匹配正确率,进而位姿检测的实时性和精度得以提高.

Pose Detection for a Novel Parallel Mechanism Based on Binocular Vision

For a novel 3-DOF parallel mechanism with actuation redundancy,the real-timeness and precision are difficult to be guaranteed for the pose detection of the parallel mechanism which is based on binocular vision.In order to solve these problems,Harris-SIFT algorithm is firstly adopted to pre-match images.The feature points are extracted by a Harris operator,and a SIFT operator is adopted to describe the feature points and match the images.Hence the result of pre-matching has good stability and real-time performance.Secondly,in order to solve the problem of mismatching,an improved algorithm of RANSAC is proposed to purify the results of pre-matching.This improved algorithm can overcome the disadvantages of mismatching and time-consuming of the conventional RANSAC algorithm by selecting feature points in separated grids in the images and pre-detecting to check temporary model.The experiment results show that the proposed method can significantly reduce the processing time.Furthermore,the matching accuracy is improved.Thereby the real-time performance and precision of pose detection of the parallel mechanism can be effectively improved.