针对移动机器人室外作业需要,提出了一种对光照度的大范围变化具有良好鲁棒性的路标识别与定位系统.通过近红外光主动照明来降低可见光照度变化和阴影等因素对视觉的影响;利用全景视觉系统获取大范围的路标信息,采用动态大津法实现二值化,突出了光照度不均情况下的路标特征,以提高路标的识别率.室外环境下移动机器人定位实验结果表明,该方法对于大范围变化的光照度具有良好的鲁棒性.
A landmark recognition and localization system with an enhanced robustness against large changes of lighting conditions eas presented for outdoor mobile robot.A near infrared illuminator was used for reducing the interference of natural light and shadow.The omni-directional camera could capture images with more landmarks in a wide range of environment.For improving the landmark's recognition rate,a dynamic OTSU binarization method was adopted for enhancing the feature of landmarks in uneven lighting image.The outdoor real-robot localization experiments demonstrate the system's robustness.