中文摘要：

提出了基于遗传算法的三堆粒子图像匹配方法及实际中的优化设计。该方法以视差为编码、结合SSD（sum of square difference）与SAD（sum of absolute difference）法对结果进行评估，并通过单点、多点的双交叉、变异与序列的混沌化处理达到对分析空间的搜索；最后，局部处理结合全曷唯一性述玳．检潮进一步增加了匹配结果的可信度。利用优化前后所提算法对空间粒子图进行了对比及误差分析。结果表明：所提算法适用于粒子测速系统的立体匹配，能够给出较准确的视差信息。

英文摘要：

The three-dimensional （3-D） particle image matching method and optimal design were proposed based on genetic algorithm （GA）. Disparity was aligned to 1-D data array and encoded. And then the sum of square difference （SSD） method or the sum of absolute difference （SAD） method was applied to evaluating the result. A modified genetic algorithm was employed to the stereo matching. First, the crossover and mutation method were modified; secondly, the sequences were made chaotic; thirdly, the uniqueness was detected based on iterative algorithm. At last, synthetic particle images were tested and the results were compared and analyzed. The experimental results show that the proposed method is suitable for stereo matching of 3-D particle images and the disparity maps are obtained with high precision.