一种优化的主动视觉导航方法分析

Analysis of an optimized active vision navigation method

为解决主动视觉导航在复杂路况条件下精度较差的问题,提出了一种优化的主动视觉导航参量计算方法。首先,建立了车辆物理坐标系与视觉图像坐标系的变换方程,通过Canny算子对视频图像进行初步的车道边缘线和道路标志线检测;接着,基于方向引导优化有效降低了阴影、积水等杂波对检测性能的干扰,并通过阈值优化的广义Hough变换实现车道线的内外边缘及道路标志线的精确检测;最后,基于检测结果计算出用于导航的中心引导线和偏离角度、距离等参量。实验结果表明,本文方法能够有效且精确的获取主动导航系统的偏移参量。

In order to solve the problem of poor precision of active vision navigation in complex road conditions,a new active vision navigation parameters calculating method based on directional guidance optimization is proposed. In this method,the transformation equations of the vehicle physical coordinate system and the visual image coordinate system are established,and the detection of video image by Canny operator is proposed. Second,the shadow and water clutter on the detection performance interference is reduced based on the direction optimization,and the road sign line,inner and outer edge is accurate detected based on the generalized Hough transform threshold optimization. Finally,the center guide line for navigation,the deviation angle and the distance are calculated based on the test experiment. The experimental results show that the proposed method can effectively and accurately obtain the offset parameters of active navigation system.