Video image deblurring method based on self-adaption window selection
An adaptive window and adaptive selection technology, applied in the field of image processing, can solve problems such as computing bottlenecks, heavy workload, and poor results, and achieve the effects of reducing running time, reducing computation, and improving effectiveness
Active Publication Date: 2013-04-17
泰安云智企业管理咨询有限公司
View PDF3 Cites 15 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, Fergus’s algorithm is not very convenient to operate. Manually selecting the processing window increases the blindness of the selection. Once there is a deviation in the selection, the result of deblurring will be very poor. A reasonable window for estimating the blur kernel gives satisfactory results
Although Fergus et al. also proposed how to select an effective processing window, it is difficult to guarantee the accuracy of selecting an area with rich edge structure only by visual effects, and the manually selected window generally has a relatively large workload and takes a long time to calculate. If this method When used on video, it is conceivable that this method will bring about a huge computing bottleneck
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0021] refer to figure 1 , the present invention is based on the video image deblurring method of adaptive window selection, comprises the following steps:
[0022] Step 1: Input any frame of video image I in the video sequence X, use the genetic algorithm to adaptively select the position coordinates (i, j) of the window used to estimate the motion blur kernel on the video image I, the selected window is [i ,i+50,j,j+50]. Here we take the 39th frame in the video basketball, the size is 352×288, such as figure 2 shown. The position coordinates of the window for estimating the motion blur kernel are selected adaptively to image I with genetic algorithm, carry out as follows:
[0023] 1a) Randomly generate an initial population S={S with a population size of 50 1 ,...S i ,...,S 50};
[0024] 1b) Determine the objective function as Wherein g(i, j)=I(i, j)-I(i, j′), I(i, j) is the pixel value of video image I at point (i, j), (i′, j ') is any point on the arc with the p...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a video image deblurring method based on self-adaption window selection, and the method is mainly used for solving the problems of multi-repeatability and uncertainty for selecting a window for estimating a motion blurring kernel by a RobFergus deblurring method. The implementation procedures comprise the following steps of: inputting a frame video image, and selecting a preliminary window for estimating the motion blurring kernel self-adaptively by the video image by a genetic algorithm; carrying out grey level conversion and inverse gamma correction on the preliminary window; estimating an appropriate motion blurring kernel in the corrected window by a variable bayes method and a multiscale iteration method; carrying out deconvolution operation on the video image through a Richardson-Lucy deconvolution algorithm by utilizing the estimated motion blurring kernel, thereby obtaining the distinct video image. The video image deblurring method based on self-adaption window selection provided by the invention has the advantage of self-adaption selection of the window for estimating the motion blurring kernel, and can be used for preventing the triviality and blindness of manual selection, and improving the window selection effectiveness and treated result accuracy.
Description
technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to video image processing, which can be used to quickly select a target area to deblur and segment an image. Background technique [0002] Motion blur is a ubiquitous phenomenon in the imaging process, which is caused by the relative motion between the camera and the target during the exposure time. Its existence seriously affects the quality of acquired images, and motion blurred image restoration has thus become an important research topic, and is widely used in important fields such as astronomical research, military detection, traffic monitoring, and medical detection. [0003] Motion blurred images can be modeled as a convolution of image intensities with a blur kernel that describes the camera motion trajectory during the exposure time. Removing camera shake blur is actually a form of blind image deconvolution, a problem that has a long history in image a...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G06T5/00
Inventor 缑水平焦李成王越越唐晓王爽杨淑媛侯彪马文萍马晶晶
Owner 泰安云智企业管理咨询有限公司