移动机器人导航系统中的车道线检测方法及实现

针对室外移动机器人GPS与惯性导航不足之处，在GPS与惯性导航基础上，提出了采用视觉检测方法实时识别路面的车道线信息，对移动机器人进行辅助定位。在传统的Canny边缘检测算子基础上，提出了使用改进型小波阀值算法与Canny边缘检测算子进行融合处理，其基本原理是先使用改进型小波阀值算法，代替传统的高斯滤波器进行平滑和降噪处理，然后再使用Canny边缘检测算子提取边缘特征。最后使用matlab软件对采集到的路面视频信息进行处理，计算出移动机器人相对于路面车道线的偏转角度和偏离距离。实验发现12000帧图像中有仅有892帧图像检测失败，成功率达到92.6%，取得较好效果。为移动机器人的室外自主移动提供有力支撑。

Method and Realization of Lane Detection in Mobile Robot Navigation System

Aiming at the deficiency of GPS and inertial navigation of outdoor mobile robot, this paper puts forward a visual detection method to identify the lane line information of the road surface in real time to assist position of the mobile robot based on GPS and inertial navigation. On the basis of the traditional Canny edge detection operator, the improved wavelet threshold algorithm and the Canny edge detection operator are used for fusion processing. The basic principle is to use the improved wavelet threshold algorithm to replace the traditional Gaussian filter for smoothing and noise reduction. After that, the Canny edge detection operator is used to extract the edge features. Finally, matlab software was used to process the collected road surface video information, and the deflection Angle and deviation distance of the mobile robot relative to the road lane line were calculated .The experiment found that only 892 out of 12,000 frames of images failed to detect, with a success rate of 92.6%, achieving a good effect and provide strong support for outdoor autonomous movement of mobile robot. Key words: mobile robot; lane lines; Canny edge detection operator;wavelet transform