基于视觉的水下管线识别与定位系统

论述了在水环境下如何通过视觉识别管线并给以精确的定位。提出了水下视觉系统的总体设计方案。在识别目标时，以目标的颜色为特征，并将颜色从ＲＧＢ窨转换到ＨＳＩ空间，使图象处理的速度和特征抽取的鲁棒性得到提高。对水下环境中点和线的精确定位进行了详细的分析，给出定位算法。最后的实验结果证明了算法的有效性。

Vision-based Recognition and Location for Underwater Pipeline

This paper discusses how to recognize and locate pipeline accurately by vision underwater. An undersater vision system is presented. The object's color is the feature when the object be recognized. And the color is transformed from RGB space to HSI space, which improves speed of image processing and robust of feature extracting. The prper analyzes location of point and line in underwater environment in detail, and offers an algorithm of locatioo. Experiment results show that the method can achieve quite precise results.