为了快速稳定地进行特征点的跟踪，提出了一种快速多尺度特征点的提取算法。该算法首先利用快速局部窗口极值搜索算法提取出不同尺度空间特征点的局部极值，减少了局部极值搜索的冗余性，然后再利用最近邻算法对特征点进行匹配。实验结果表明，该算法的计算速度快于SIFT算法和MOPS算法，稳定性强于传统的Harris算法，可以用于实时图像配准及目标跟踪。

This paper presents a Multi-scale feature extraction algorithm，which computes the maximum of the features in moving windows using fast algorithm reduces the search redundancy and obtains the matching features using the nearest neighbor matching algorithm .The experimental results show that this algorithm is faster than the SIFT and MOPS，and has more stability than Harris algorithm.The algorithm can be used in image registration and target tracking.