基于预测与跟踪的激光图像光迹快速细化方法

Laser image fast thinning method based on prediction and tracking

线形激光图像中光迹的细化是视觉测量的关键问题。由于激光成像过程中存在散斑噪声,导致图像中的光迹断裂,光迹粗糙,影响光迹细化的准确性和速度。针对上述问题,提出基于预测与跟踪的光迹快速细化方法。首先对激光图像进行预处理以简化计算和抑制散斑噪声,接着对光迹进行搜索与标记,然后运用基于预测与跟踪的方法快速定位光迹的中心线,完成光迹的细化。实验结果表明,该法能准确实现光迹细化,单幅图像的细化速度小于10 ms。

The thinning processing of light trails for the linear laser image is the key to the visual measurement problem. With speckle noise,in the process of imaging,light trails of the image become fractured and rough,thus affecting not only the accuracy but also the speed of the refinement of the trails. According to the above problem,this paper proposes the method based on prediction and tracking to fulfill the refinement. Firstly,preprocessing the laser image to simplify the calculation and suppress the speckle noise,then searching and marking the trails,and lastly,using the method based on prediction and tracking to locate the center line of the trails,as finishing the refinement process. The experimental results show that the method can accurately realize the thinning,at the same time,single image thinning rate is less than 10 ms.