针对三步搜索算法(TSS)不适合搜索中小运动剧烈程度的视频序列，提出了一种基于初始点预测、加强对小范围搜索的可扩展的三步搜索算法。算法在保证对较剧烈的视频序列搜索有效性的同时，加强了对中小剧烈程度视频序列的有效搜索，在匹配精度、搜索点数等算法性能方面相对于三步搜索算法有了明显的改善，同时有利于搜索模板的硬件易实现性，最后将其引入到变尺寸块运动估计中，获得了较好的效果。

Based on the analysis of the reason that the TSS algorithm is unfit for searching low drastic video sequence，an extensible three step search algorithm（TSS）is proposed based on the prediction of initial point and enhanced searching in small range .The proposed algorithm has a significant improvement over the TSS both on matching precision and the reduced number of searching points，which enhances point searching in small range effectively，and the hardware structure mapping to the algorithm is easy to be implemented at the same time. The algorithm is also very fit for Variable Block-Size Integer Motion Estimation.