A Feature Point Tracking Method Based on The Combination of SIFT Algorithm and KLT Matching Algorithm

In order to track target stably and accurately by the feature point tracking algorithm when the target changes in size and attitude,a new feature points tracking algorithm is proposed based on the combination of SIFT algorithm and KLT matching algorithm.Through the optimization of the SIFT algorithm,the feature points distribute relative uniform and there is no over-clustering of feature points.The matching accuracy is improved a lot when the target moves fast by the hierarchically iterative matching of the KLT matching algorithm.According to the results of feature points matching,the exact location of target is obtained with the combination of the Greedy Algorithm.Experimental results show that the proposed algorithm can adapt to objective changes in attitude and size and it can track target with complex structure stably.It has stronger robustness and reliability and get more accurate location of target than KLT tracking algorithm.