Check patentability & draft patents in minutes with Patsnap Eureka AI!

A Video Coding Optimization Method Oriented to Content Analysis

A content analysis and optimization method technology, applied in digital video signal modification, image communication, electrical components, etc., to achieve the effect of reducing the impact and improving the rate-distortion optimization method

Active Publication Date: 2019-10-18
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to reduce the impact of video compression distortion on content analysis, the present invention proposes a content analysis-oriented video coding optimization method, aiming to solve the balance problem of bit rate, compression distortion and analysis distortion

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 Video Coding Optimization Method Oriented to Content Analysis
  • A Video Coding Optimization Method Oriented to Content Analysis
  • A Video Coding Optimization Method Oriented to Content Analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0030] Take moving target detection as an example, including the following steps:

[0031] 1. Select 4 surveillance videos from the PETS2006 (www.cvg.cs.rdg.ac.uk / PETS2006) and CAVIAR (www.dai.ed.ac.uk / homes / rbf / CAVIAR / ) databases (3 of them The video is an indoor scene, and the other one is an outdoor scene) as training data, using literature (B. Lei, A. Leonardis, and B. Schiele, "Robust object detection with interleaved categorization and segmentation," Intl.J.ComputerVision, vol.77,no.1,pp.259-289,2008.) in the moving target detection algorithm, record the detection results.

[0032] 2. Set the quantization parameter QP(4-41) of the HEVC encoder to obtain 38 compressed videos of different quality of 4 training videos, run the same detection algorithm, and record the detection results.

[0033] 3. Statistical experiment results, using the detection results in 1 above as a reference, and the detection results in 2 as a comparison, using F-measure evaluation indicators (Y.Dhome, N....

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 belongs to the technical field of video compression, and in particular relates to a content analysis-oriented video coding optimization method. The method disclosed by the invention comprises four parts including a content analysis distortion model, a content analysis distortion prediction model, a rate misalignment model, and rate distortion optimization. Influence of video compression distortion on a content analysis algorithm is quantified by construction of the content analysis distortion model; content analysis distortion is predicted by adoption of compression distortion SAD (Sum of Absolute Difference); the relationship between the content analysis distortion and the code rate is fitted by adoption of a e exponential function; the content analysis distortion is introduced into rate distortion optimization; minimization of the pixel distortion and the content analysis distortion is used as the optimization object; the existing rate distortion optimization method is improved; therefore, the content analysis distortion is finally reduced; and influence of the video compression distortion on the content analysis algorithm is weakened.

Description

Technical field [0001] The invention belongs to the technical field of video compression, and specifically relates to a content analysis-oriented video coding optimization method. Background technique [0002] With the advancement and development of video communication technology, video data has exploded. Especially in the field of video surveillance, super large amounts of surveillance video data are compressed and transmitted to the server, where the computer performs content analysis to achieve various purposes, such as Moving target detection, face recognition, behavior analysis, etc. Nowadays, most video encoders aim at maximizing the visual quality of the human eye, causing compression distortion to reduce the performance of subsequent content analysis algorithms. In the past few decades, researchers have proposed many methods to reduce the influence of compression distortion on analysis algorithms, most of which are aimed at preserving local feature points. [0003] Chao 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
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): H04N19/147H04N19/124
Inventor 朱策刘宇洋毛敏宋方良张翔
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com