摘要
盾构自动激光导向系统工作时,背景光会对激光光斑的识别产生干扰,利用差图像法可以减少这种干扰。然而盾构机推进时的运动会使相邻两帧图像的背景产生微移动,差图像法无法适应背景的微移动,导致处理结果的信噪比低。本文提出了一种将形态学滤波与正差图像法相结合的光斑识别算法。首先对背景图像进行形态学滤波预处理,然后与含有光斑的图像进行正差图像处理。实验证明,这种方法能有效减少背景微移动的影响,大幅度提高图像的信噪比。
Background Light will interfere laser spot recognition in TBM laser automatic guidance system,and the interference can be reduced by image differencing.However,the Signal to Noise Ratio（SNR） of difference images will decrease,when the background of two consecutive images micro move because of shield machine moving.A laser spot recognition algorithm combining morphological filter and positive difference images algorithm was presented in the paper.Morphological filters were designed for expanding background images,and then positive difference images algorithm was used to pick up laser spot.Experiments show that the method can effectively reduce the influence of background micro move and greatly improve the SNR of images.
出处
《微计算机信息》
2012年第9期56-58,共3页
Control & Automation
关键词
激光标靶
光斑识别
形态学滤波
差图像法
laser system
laser spot recognition
morphological filter
image differencing
