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

A characteristic matching method for compressing video super-resolution based on learning

A super-resolution and feature matching technology, applied in digital video signal modification, television, image enhancement, etc., can solve problems affecting matching accuracy, and achieve the effect of improving matching accuracy

Inactive Publication Date: 2011-07-27
WUHAN UNIV
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In order to solve the problem that the above-mentioned compression and quantization noise affects the matching accuracy, a learning-based feature matching method for compressed video super-resolution is provided. This method uses the low-frequency part with less quantization noise in the image frequency domain as a matching feature. At the same time, the average quantization noise is compensated according to the quantization step size, and the matching accuracy of learning-based compressed video super-resolution is improved.

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 characteristic matching method for compressing video super-resolution based on learning
  • A characteristic matching method for compressing video super-resolution based on learning
  • A characteristic matching method for compressing video super-resolution based on learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] The invention provides a learning-based feature matching method for compressed video super-resolution when there is quantization noise. The basic principle is to use the characteristics that the low-frequency part of the frequency domain is less affected by quantization in the compressed video, and the quantization step size is known, and the low-frequency part is selected for average quantization noise compensation as a matching feature.

[0019] The present invention will be described below in conjunction with an embodiment of an image pyramid-based face super-resolution (phantom face) method. The advantages and characteristics of the present invention are illustrated by the detailed description of the embodiments, and the implementation method thereof will be clearer to those skilled in the art. However, the scope of the present invention is not limited to the embodiments disclosed in the description, and the present invention also It can be implemented in other form...

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 present invention discloses a characteristic matching method for compressing video super-resolution based on learning. The method can increase matching precision by using accurate extracting matching characteristic and quantization noise compensation. The method uses a low frequency coefficient little effected by quantization noise as a matching characteristic when matching an input image block and a sample block, compensates the quantization noise according with quantization step length of a video code flow in a matching principle, accordingly, the method can obtain more accurate matchingperformance in condition of quantization noise in the input image.

Description

technical field [0001] The invention belongs to the field of image super-resolution processing, in particular to a method for enhancing video and image resolution based on sample learning in monitoring applications. Background technique [0002] The video surveillance system obtains images of the real world through technical means for transmission and storage, so that users can use the network to obtain real-time monitoring conditions in different places, which improves the ability to respond to emergencies and security prevention capabilities. At the same time, the video surveillance video can also be used for post-event investigation and evidence collection by the public security department, thus providing an effective means of criminal investigation. In order to obtain more detailed information about the target from the surveillance video, such as facial features, license plate number, etc., in order to identify and determine its identity, it is often necessary for the su...

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): G06T5/00H04N7/30H04N7/26H04N19/625
Inventor 胡瑞敏兰诚栋陈军卢涛韩镇王中元陈萍
Owner WUHAN UNIV