Real-time stereo visual odometry (SVO) localization is a challenging problem, especially for a mobile platform without parallel computing capability. A possible solution is to reduce the computational complexity of SVO using a Kanade–Lucas–Tomasi (KLT) feature tracker. However, the standard KLT is susceptible to scale distortion and affine transformation. Therefore, this work presents a novel SVO algorithm yielding robust and real-time localization based on an improved KLT method. First, in order to improve real-time performance, feature inheritance is applied to avoid time-consuming feature detection and matching processes as much as possible. Furthermore, a joint adaptive function with respect to the average disparity, translation velocity, and yaw angle is proposed to determine a suitable window size for the adaptive KLT tracker. Then, combining the standard KLT method with an epipolar constraint, a simplified KLT matcher is introduced to substitute feature-based stereo matching. Additionally, an effective veer chain matching scheme is employed to reduce the drift error. Comparative experiments on the KITTI odometry benchmark show that the proposed method achieves significant improvement in terms of time performance than the state-of-the-art single-thread approaches and strikes a better trade-off between efficiency and accuracy than the parallel SVO or multi-threaded SLAM.
Almost all robust stereo visual odometry work uses the random sample consensus (RANSAC) algorithm for model estimation with the existence of noise and outliers. To date, there have been few comparative studies to evaluate the performance of RANSAC algorithms based on different hypothesis generators. In this work, we analyse and compare three popular and efficient RANSAC schemes. They mainly differ in using the two-dimensional (2-D) data points measured directly and the three-dimensional (3-D) data points inferred through triangulation. This comparison presents several quantitative experiments intended for comparing the accuracy, robustness and efficiency of each scheme under varying levels of noise and different percentages of outlier conditions. The results suggest that in the presence of noise and outliers, the perspective-three-point RANSAC provides more accurate and robust pose estimates. However, in the absence of noise, the iterative closest point RANSAC obtains better results regardless of the percentage of outliers. Efficiency, in terms of the number of RANSAC iterations, is found in that the relative speed of the perspective-three-point RANSAC becomes superior under low noise levels and low percentages of outlier conditions. Otherwise, the iterative closest-point RANSAC may be computationally more efficient.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.