一种新型图像匹配方法在视觉导引 AUV 对接中的应用

摘要

Accoding to the image characters in the process of vision guided Autonomous Underwater Vehicle(AUV) docking ,an image matching algirithm based on quanta particle swarm optimization and grey relational analysis is proposed . The algirithm suggested which combines the speediness of quanta particle swarm optimization and the robustness of the grey relational analysis is not sensitive to the changes including rotation ,translation ,brightness change and so on ,so it fits the need of vision guided docking .The grey absolute correlative degree of the image gray histogram is used as fitness function , and the image matching algorithm based on quanta particle swarm optimization is introduced in detail .Using images from tank test ,experimental results are presented to demonstrate that the proposed algorithm can be applied in AUV vision guided docking .%针对视觉导引AUV对接过程图像的变化特点，提出一种量子粒子群算法与灰度关联分析方法相结合的图像匹配算法。此算法结合量子粒子群并行搜索的快速性与灰色关联分析方法较强的鲁棒性，对旋转、平移、亮度变化等不敏感，符合视觉导引AUV对接过程中对图像匹配算法的要求。详细介绍了基于量子粒子群优化算法的图像匹配算法，算法以图像灰度直方图的灰色绝对关联度作为适应度函数。利用水池实验所得图像进行测试，实验结果显示，所提出的图像匹配算法准确、快速、鲁棒性强，能够很好地应用于视觉导引AUV对接。