RANSAC算法计算过程稳定，对匹配错误特征点与噪声的鲁棒性较强，剔除

The calculation process of the RANSAC algorithm is stable, the robustness to matching error feature points and noise is strong, and the ability to eliminate wrong matching points is good. However, the parameter estimation of the RANSAC algorithm is completed through continuous iteration and testing, and the initial model parameters are calculated from randomly selected data, so the uncertainty is relatively large; <br>if the randomly selected initial data has a large error, the performance of the algorithm will be limited Serious impact

RANSAC algorithm has stable calculation process, strong robustness to matching error feature points and noise, and good ability to eliminate error matching points. However, the parameter estimation of RANSAC algorithm is completed through continuous iteration and testing, and the initial model parameters are calculated from randomly selected data, so there is great uncertainty;<br>If the initial data error of random sampling is large, the performance of the algorithm will be seriously affected

SAC algorithm has a stable calculation process, strong robustness to the matching error feature points and noise, and good ability to eliminate the error matching points. However, RANSAC algorithm estimates the parameters through continuous iteration and testing, and the initial model parameters are calculated from randomly selected data, so the uncertainty is relatively large. If the random initial data error is large, the performance of the algorithm will be seriously affected.