高压输电线路巡线机器人障碍物视觉检测识别研究*

障碍物的检测识别与定位是高压输电线路自主巡线机器人中的关键技术之一.针对220 kV单分裂输电线路的结构特点,提出了一种基于视觉传感器的障碍物检测识别方法.首先,对采集的图像进行膨胀、腐蚀和高斯平滑等处理,以减少图像噪声;然后,利用Otsu算法对Canny算子进行改良来提取图像边缘,以减少光线变化带来的影响;最后,提取边缘图像中某些图形基元并施加结构约束,实现障碍物的检测识别.大量的试验研究表明,该方法能有效地检测识别高压输电线路的导线、防震锤、悬垂绝缘子和耐张绝缘子等结构物.

The Research of Obstacle Recognition Based On Vision for High Voltage Transmission Line Inspection Robot*

Obstacle recognition and orientation is one of the key techniques in high voltage transmission line autonomous inspection robot.In light of the structure of 220 kV single split transmission line,a method of obstacle recognition based upon vision sensor is put forward.First of all,the shot image is processed by expansion,erosion,Gauss smoothing treatment to relieve the noise.And then,Otsu is used to improve Canny algorithm so as to detect the edge of the image,which can reduce the influence of the light changing.At last,some graph cells are detected and given structure constraint in the edge of image to achieve obstacles recognition.A lot of tests proved that structures such as wire,counterweight,strain clamp and suspension on high voltage transmission line can be effectively recognized using the method.