基于视差空间的双目视觉里程计

提出了一种基于视差空间的双目视觉里程计算法.利用SIFT特征点的尺度和旋转不变性,实现左、右图像对特征点的准确匹配,及前后帧间的特征跟踪.在RANSAC框架下对匹配点进行运动估计获得运动参数初始值,然后迭代更新匹配点的视差比值直至收敛.为克服传统算法中3维空间噪声分布不均匀的缺陷,利用了视差空间噪声分布的各向同性的性质进行运动估计,并且通过迭代取得全局最小值.实验结果表明,该算法在运动估计中具有更好的精度.

Disparity Space Based Binocular Visual Odometry

An approach based on disparity space to a binocular visual odometry system is presented. Utilizing the scale and rotation invariant feature of SIFT visual Landmarks to achieve accurate feature matching between stereo images and feature tracking between consecutive frames. Initial motion estimate is firstly carried out between matching points in a RANSAC framework for outlier detection, then the disparity ratio of matching points are refreshed until the result is converged. In order to overcome the limitation of the an- isotropic noise distribution in 3D space , utilizing the feature that the disparity space has isotropic noise distribution to carry out motion estimation, and through iterative can achieve global minimize. Experimental results show that this method succeeds in motion estimation and has more accurate result than traditional algorithm.