In video coding,one of the key technologies is the block-matching algorithm,and its efficiency directly affects the quality of video transmission.Up to now,there have been many nice search algorithms to improve the efficiency of the block-matching algorithm.And the genetic algorithm is a random search algorithm,which can get and accumulate some information related to the search space automatically in the search process.It can control the search process by self-adaptatlon to find the best result.In this paper,the genetic algorithm is improved,which is applied to the block-matching algorithm for low bit-rate video coding.As the result of experiments,the search efficiency is improved while maintaining the better performance.