Robust stereo visual odometry: A comparison of random sample consensus algorithms based on three major hypothesis generators

Abstract

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.

Accuracy Analysis of Visual Odometer for Unmanned Rollers in Tunnels

“…Such disturbances can lead to mismatches of features, which can introduce substantial inaccuracies in pose estimations. To address this, the random sample consensus (RANSAC) algorithm [31] is adopted for outlier removal. Drawing from the set of feature points extracted in Section 3.1, a subset is randomly sampled to compute a motion model, serving as a hypothesis.…”

Air-ground multi-agent system cooperative navigation based on factor graph optimization SLAM

“…In the context of SLAM systems, Guo et al introduced an improved algorithm based on enhanced image gradient information for the Scale-Invariant Feature Transform (SIFT) feature matching algorithm. The front-end of the SLAM system, responsible for ground feature measurement and approximate position calculations, was enhanced by this algorithm, effectively improving the accuracy of SIFT feature matching [14]. Furthermore, Wisth proposed a factor graph optimization (FGO) method for state estimation in legged robots, aiming to surpass the performance of kinematic-inertial odometry.…”