基于立体视觉的空间运动分析

利用摄影测量方法和计算机视觉技术得出了一套完整的、由双目立体序列图像确定场景中目标运动信息的方法与步骤。讨论了双目立体视觉系统的在任检校,相关系数和松弛法相结合基于点特征的物体运动、立体匹配,运动前后三维特征点的对应,以及利用能减少待定变量、降低计算复杂性、提高算法精确性的反对称矩阵分解算法求解运动参数(R和T)等问题。给出了从一组真实图像中获取目标运动参数的计算结果。

Based on stereo visual 3D motion analysis

Using photogrammetry method and computer vision technique,the method and steps of determination 3-D motion parameters by binocular stereo image sequences are put forwards. The in-situ calibration for binocular stereo vision systems, combining correlation coefficients and relaxation method for performing motion and binocular stereo matching of images based on point feature, 3-D feature points in the motion object correspondences before and after motion, using "Skew-Symmetric Matrix Decomposition" algorithms which exploits the fewest variables and without losing the linearity in computation to reduce computing complexity and improve accuracy motion parameters R and T acquire etc are discussed. The motion parameters of real data based on 3-D correspondences feature estimation method are given.