基于激光视觉的光照变化图像分割研究  

Research on illumination change image segmentation based on laser vision

作　　者：邓舟舟 冯祥[1] 赵继平 DENG Zhouzhou;FENG Xiang;ZHAO Jiping(Chengdu college of University of Electronic Science And Technology of China,Chengdu 611731,China)

机构地区：[1]电子科技大学成都学院,成都611731

出　　处：《激光杂志》2024年第1期136-141,共6页Laser Journal

基　　金：四川省科技计划资助项目(No.2019YJ0114)。

摘　　要：光照变化图像在分割过程中,若不能有效抑制图像中的噪声,会直接影响图像的分割精度,为提升图像的分割效果,提出基于激光视觉的光照变化图像分割方法。将图像输入至激光视觉系统中实施去噪、目标增强等处理,过程中通过该系统中的控制传感器,严密跟踪图像处理流程,提升图像的处理效果;获取图像直方图,根据直方图的平滑结果确定光照变换图像灰度直方图阈值选取范围,对图像实施区域划分获取对应的阈值,根据确定的阈值完成光照图像的精准分割。实验结果表明,使用该方法开展图像分割时,有效去除了图像噪声,分割效果较好,能够实现对图像目标的高效、准确分割。In the process of image segmentation,if the noise in the image cannot be effectively suppressed,the segmentation accuracy of the image will be directly affected.In order to improve the segmentation effect of the image,a light change image segmentation method based on laser vision is proposed.The image is input into the laser vision system for noise removal,target enhancement and other processing.During the process,the control sensor in the system closely tracks the image processing process to improve the image processing effect;Obtain the image histogram,determine the selection range of the gray histogram threshold of the light transformation image according to the smoothing result of the histogram,divide the image into regions to obtain the corresponding threshold,and complete the accurate segmentation of the light image according to the determined threshold.The experimental results show that this method can effectively remove the image noise and achieve a good segmentation effect,it can achieve efficient and accurate segmentation of image targets.

关 键 词：激光视觉系统 光照变化图像 图像去噪 灰度化处理 图像分割 

分 类 号：TN24[电子电信—物理电子学]