Unlock instant, AI-driven research and patent intelligence for your innovation.

A Non-Uniform Video Blind Deblurring Method Based on Block Fuzzy Kernel Set

A blind deblurring and non-uniform technology, applied in the field of video processing, can solve problems affecting video quality, high requirements for clear area distribution, etc., and achieve the effect of efficient processing

Inactive Publication Date: 2017-08-25
BEIJING INSTITUTE OF TECHNOLOGYGY +1
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method has high requirements on the distribution of clear areas in the video, that is, if the relevant areas on the blurred frame do not have corresponding clear areas on other frames, this method will not be able to perform deblurring processing, thus affecting the final video quality.

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Non-Uniform Video Blind Deblurring Method Based on Block Fuzzy Kernel Set
  • A Non-Uniform Video Blind Deblurring Method Based on Block Fuzzy Kernel Set
  • A Non-Uniform Video Blind Deblurring Method Based on Block Fuzzy Kernel Set

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0053] A non-uniform video blind deblurring method based on block blur kernel set, the specific implementation steps are as follows:

[0054] Step 1. Detect blurred frames

[0055] There are many blurred frame detection methods, such as the non-reference image blur detection method based on cumulative probability proposed by Niranjan et al. Cumulative Probability of BlurDetection (CPBD)‖, IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL.20, NO.9, SEPTEMBER2011.), and a fuzzy detection method based on wavelet transform (Tong H., Mingjing L., Hongjiang Z., Changshui Z.:,, Blur detection for digital images using wavelet transform . IEEE Int. Conf. on Multimedia and Expo (ICME), 2004, pp.17–20.), etc.

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

No PUM Login to View More

Abstract

The invention relates to a non-uniform video blind deblurring method based on block blur kernel sets, which belongs to the technical field of video processing; comprising the following steps: detecting blurred frames according to the image gradient of video frames; using features between clear frames and blurred frames Matching calculation block homography transformation; approximate fuzzy motion through discrete sampling of block homography transformation, and calculate the speed parameter of fuzzy motion by optimizing approximation error; obtain the blur kernel corresponding to each block according to the fuzzy motion speed, and use deconvolution Clear blocks are calculated by the product; the clear blocks are spliced ​​to obtain a clear frame image, thereby removing blurred frames. Compared with the existing method, the method of the present invention uses multiple blur kernels to describe the blur motion of the video frame, does not need to set the initial value during calculation, increases the robustness, and is more efficient for non-uniform video blur processing; The clear area requirements are not high, which increases the scope of application.

Description

[0001] Technical field: [0002] The invention relates to a video blind deblurring method, in particular to a non-uniform video blind deblurring method based on block fuzzy kernel sets, and belongs to the technical field of video processing. [0003] Background technique: [0004] With the popularization of digital cameras, video shooting has become an important activity in people's daily life, and has important applications in home entertainment, film and television production, production security and so on. However, due to the limitations of the environment and users during video shooting, problems such as blurred images inevitably exist in the captured video, which affects the viewing experience of the human eye and further processing in the later stage. [0005] Scholars at home and abroad have done a lot of basic research on video deblurring, which has high application value. Commonly used video deblurring methods mainly include two categories: methods based on blur kerne...

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
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06T5/00
Inventor 张磊周乐陈晓权黄华
Owner BEIJING INSTITUTE OF TECHNOLOGYGY