基于CMOS摄像头的教育机器人运动路径检测

Motion path detection of educational robot based on CMOS camera

针对教育机器人在类交通场景的复杂地图中自主循迹问题,提出基于CMOS摄像头的运动路径检测方法。以CMOS摄像头获得彩色图片,应用颜色空间变换将图像由RGB空间变换至HSL空间,通过在HSL空间进行颜色滤波对地图中的引导线路径进行粗提取并灰度化为二值图像,根据相机成像的透视变换获得俯视图,应用灰度点统计和局部迭代法检测引导线,通过最小二乘法拟合引导线并获得预瞄点位置。实验以两幅复杂地图进行分析,通过树莓派Raspberry PI 3驱动Risym摄像头进行图像采集和处理,验证了该方法的有效性。

Aiming at the problem of autonomous tracking of educational robots in complex maps in traffic-like scenarios,a motion path detection method based on a CMOS camera is proposed.This method uses a CMOS camera to obtain a color picture,applies color space transformation to transform the image from RGB space to HSL space,and performs color extraction on the guide line path in the map by color filtering in HSL space and gray scales it into a binary image.The perspective transformation of the camera image is used to obtain the top view.The gray line statistics and local iteration method are used to detect the guide line.The guide line is fitted by the least square method and the position of the preview point is obtained.The experiment was analyzed with two complex maps.The Raspberry PI 3 was used to drive the Risym camera for image acquisition and processing,which verified the effectiveness of the method.