摘要
为解决煤矿救援机器人在发生灾害后光线不足、煤尘粉尘严重等造成视觉系统中图像不清晰、画面模糊以致障碍物形状无法识别问题,通过实验模拟煤矿井下光照条件,在光照充足、低照度以及零照度3种不同光照条件下采集机器人视觉图像。采用直方图均衡化方法对图像进行增强处理,使机器人显示的图像更加清晰,通过边缘检测算法以及基于风水岭分割改进的算法对障碍物信息进行提取,最终可以得到机器人前方主障碍物的形状特征信息。
To solve the problem that images of robot vision system were not clear and fuzzy caused by insufficient lighting in the event of disasters,such as coal dust and dust so that the shapes of coal mine obstacles couldn＇t identify well,robot visual images were collected through simulation experiments coal mine lighting conditions in adequate light,low light and zero illumination collection of three different lighting conditions.Using histogram equalization method for image enhancement,image robot displayed more clearly,by edge detection algorithms,and improved watershed segmentation algorithm based on obstacle information extraction,the final shape of the feature information can be obtained in front of the main obstacles in the robot.
出处
《煤矿机械》
2017年第2期39-41,共3页
Coal Mine Machinery
