Method and device for detecting superposed stripe in video image

Abstract

The invention discloses a method and device for detecting a superposed stripe in a video image. The method comprises steps of: acquiring Y components in the current frame and the last frame of a video image in a YUV format, and calculating the difference data between the Y components of the two frames of the video image; smoothening the difference data to obtain a difference image; determining the global gradient and the local frequency domain of the difference image in order to determine whether the video image is provided with a superposed stripe. The device comprises a difference module, a smoothening module, a gradient determining module, and a frequency domain determining module. The method and the device shorten consumed time while improving determining accuracy so as to satisfy a real-time application requirement.

Description

technical field [0001] The invention belongs to the technical field of video quality detection, and in particular relates to a method and device for detecting superimposed stripes in a video image. Background technique [0002] The video quality diagnosis system is an intelligent monitoring video fault analysis and alarm system. It can analyze and judge the quality of the video images sent back from the front end, and can make accurate judgments on video faults and send out alarm messages. The video quality diagnosis system adopts advanced and scientific video quality diagnosis technology and computer vision algorithm to make accurate judgments and issue alarm messages for common camera faults such as superimposed stripes, blur, snowflakes, color cast, and noise in video images. [0003] Superimposed streaks are a common malfunction of cameras and one of the key factors in judging video quality. The traditional superimposed streak diagnosis method uses Hough transform combi...

AI Technical Summary

Problems solved by technology

However, for video images with high resolution, the background modeling algorithm has a large amount of computation in this method, and it is difficult to achieve real-time detection of video images.

Secondly, the Canny algorithm needs to manually set a fixed threshold when calculating the edge of the image. It does not adopt an adaptive method for different images, and it is easy to cause the result edge to be inconsistent with the human eye, which will directly affect the accuracy of the effective area of ​​​​the image.

Furthermore, the background modeling algorithm needs multiple frames of images to determine the foreground image of the current frame image, and cannot quickly perform superimposed stripe detection on a large number of video images

Images