Implementation of stereo visual odometry estimation for ground vehicles

Abstract

Keeping track of vehicles location is a challenging aspect in recent days. Visual Odometry (VO) is the process of estimating the orientation and position of a vehicle or a robot by analyzing the associated camera's input. In this paper a stereo camera based visual odometry system is presented in which stereo cameras have been rigidly attached to the vehicle and motion of the vehicle is estimated using only the input coming from these stereo cameras. No other sensors are needed. The corner features are extracted in both left and right images using Harris corner detector algorithm, descriptor for each feature is extracted using Scale Invariant Feature Transform (SIFT) algorithm, feature descriptors are matched between left and right images using K-nearest neighbor match. Those matched feature correspondences are triangulated to get 3-D points. Two sets of 3-D points are obtained at time steps ‘t’ and ‘t+1’. Then, the motion is estimated using least squares fitting of these two 3-D point sets.