Method for restoring image shot by cell phone based on motion detection

Abstract

The invention discloses a method for restoring an image shot by a cell phone based on motion detection. The problems that the texture of the prior art is rich, the structure is complicated and the image restoration under an obvious outline scene is incorrect are solved. The method comprises the following steps of: preparing a frame by utilizing shooting of a shutter frame in a short time before shooting; training a background model based on a hybrid gaussian background model to acquire the background model which is close to the real scene; performing outline extraction, false detection correction and motion target sequence extraction by a motion detection module to acquire a motion target sequence which is erased by a user; and finally, replacing pixel values at corresponding positions in a target by pixel values of a background model frame in a target restoration range selected by a user to complete the restoration of image information and acquire a shutter frame image which does not include motion obstacles. By the method, a target erasing area in the lower image of the scene is correctly restored, and the method is used for an intelligent cell phone to shoot pictures.

Description

technical field [0001] The invention belongs to the technical field of video and image processing, relates to image restoration, and is a method for erasing a moving object suddenly intruding in an image through object detection technology, and is mainly used for restoration of images captured by smart phones. Background technique [0002] With the widespread use of smart phones, users have put forward higher requirements for the camera function of smart phones. When the user is taking pictures, due to the large number of people in the environment, uninvited guests often intrude into the picture, which makes the picture look messy, and produces motion smear blur, which affects the overall effect of the picture. Secondary target erasure of such intruders is then required. [0003] The traditional secondary target image erasing technology uses the relevant pixel information around the erased area to estimate the pixel value that can fill the position after the secondary targe...

AI Technical Summary

Problems solved by technology

This method selects a pixel point from the boundary of the area to be repaired, takes this point as the center, selects a texture block with an appropriate size according to the texture characteristics of the image, and then searches for similar texture matching blocks around the repaired area. Instead of the texture block, this method is difficult to achieve better results when the contour line is obvious and the texture is rich

[0007] The above three basic methods all use single-frame image information for image restoration, and there are situations where the restoration is not true, especially in the case of rich textures, wrong texture information will be generated, making the restoration effect unsatisfactory

Images