Lens dust automatic detection method and device based on image processing technology

• Main Authors: HAN XIAOLI, CUI JIE, LI TIANXIAO, WANG YAOHUI, LI HUA, SUN XIAOHU, WANG XIAODONG, SHA XINGFENG, TU HUI
• Format: Patent
• Language: Chinese; English
• Published: 23.08.2024
• Subjects: CALCULATING; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIRCHEMICAL OR PHYSICAL PROPERTIES; MEASURING; PHYSICS; TESTING

A lens dust detection method based on an image processing technology comprises the steps that a first image and a second image of a lens on optical equipment are acquired, the first image is an image not polluted by dust, and the second image is an image polluted by dust; determining a first similarity value between the first image and the second image based on a difference between pixel values at the same position in the first image and the second image; and determining whether to clean the lens based on the first similarity value. According to the method, the unpolluted lens image and the polluted lens image can be compared at the image pixel level, whether the lens needs to be cleaned or not is determined, and the difficulty of lens dust pollution detection is reduced. 一种基于图像处理技术的镜片灰尘检测方法，包括：获取光学设备上镜片的第一图像和第二图像，其中，所述第一图像为未受灰尘污染的图像，所述第二图像为受灰尘污染的图像；基于所述第一图像和所述第二图像中相同位置的像素值之间的差异，确定所述第一图像和所述第二图像之间的第一相似度值；基于所述第一相似度值，确定是否清洁所述镜片。该方法可在图像像素级别对未受污染的镜片图像和受污染的镜片图像做比较，确定出是否需要对镜片做清洁，降低了镜片灰尘污染检测的难度。