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.

A novel image-based method is presented in this paper to estimate the poses of commercial aircrafts in a runway end safety area. Based on the fact that similar poses of an aircraft will have similar geometry structures, this method first extracts features to describe the structure of an aircraft's fuselage and aerofoil by RANdom Sample Consensus algorithm (RANSAC), and then uses the central moments to obtain the aircrafts’ pose information. Based on the proposed pose information, a two-step feature matching strategy is further designed to identify an aircraft's particular pose. In order to validate the accuracy of the pose estimation and the effectiveness of the proposed algorithm, we construct a pose database of two common aircrafts in Asia. The experiments show that the designed low-dimension features can accurately capture the aircraft's pose information and the proposed algorithm can achieve satisfied matching accuracy.