Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

A method, system, and terminal for re-identifying people in a video-based smog scene

A re-identification and video technology, applied in the field of character recognition, can solve the problems of poor accuracy of character re-identification and inability to complete end-to-end discrimination, and achieve good character re-identification, improve performance, and reduce negative effects.

Active Publication Date: 2021-06-15
GUANGDONG UNIV OF PETROCHEMICAL TECH
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The existing technology cannot complete the end-to-end discrimination very well, and the accuracy of person re-identification is poor

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 method, system, and terminal for re-identifying people in a video-based smog scene
  • A method, system, and terminal for re-identifying people in a video-based smog scene
  • A method, system, and terminal for re-identifying people in a video-based smog scene

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0129] The network structure diagram of people's re-identification under the video-based smog scene of the present invention is as follows Figure 5 As shown, the specific implementation is as follows:

[0130] In step 1, a symmetric non-local codec K estimation network is established for video defogging, and the specific steps are as follows:

[0131] Step 1.1, establish a non-local residual block. Based on the success of residual network and non-local neural network, the present invention combines them to construct a non-local residual block. Each non-local residual block consists of a typical residual unit, an up-down sampling layer and a non-local block, and its specific structure is as image 3 Represent (non-local residual block), use non-local residual block as encoder and decoder, and establish encoding structure and decoding structure.

[0132] In step 1.2, the RNN layer is established to learn temporal consistency information contained in adjacent frames of each f...

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 person recognition, and discloses a method, system and terminal for re-recognition of people in a video-based smog scene, constructing a symmetrical non-local codec K estimation network model to perform defogging processing on the video; constructing a discriminant network model, And based on the built discriminant network model, it is estimated whether the input video is a normal video or a haze-free video generated by the dehazing sub-network; a non-local double-attention person re-identification sub-network model is constructed to re-identify the person. The invention can solve the problem of difficult re-recognition caused by fog in the re-recognition of characters in the video. The present invention can well complete person re-identification in foggy video. The entire process of the present invention is an end-to-end design, which can be used more simply. The invention is a video-based person re-identification technology in a smoky scene, which can complete end-to-end discrimination and can well complete person re-identification.

Description

technical field [0001] The invention belongs to the technical field of person recognition, and in particular relates to a method, system and terminal for re-recognition of people in a video-based smoke scene. Background technique [0002] Currently, video-based human re-identification is mission-critical for many safety-critical applications, such as automatic video surveillance and forensics. The task of video-based face recognition, which is to match faces from a large number of faces, has been extensively studied in recent years, but this task is still challenging due to the low quality of captured person videos, pose variations, camera perspectives, and cluttered backgrounds. [0003] The presence of haze, fog, smoke, and other small particles in the air can scatter light in the atmosphere, greatly reducing the visibility of images or videos of people. These blurs lose contrast and color fidelity. People can also observe that in these smoggy portrait frames, many detai...

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): G06K9/00G06K9/44G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V40/10G06V10/34G06N3/045G06F18/24
Inventor 荆晓远程立姚永芳孔晓辉王许辉黄鹤
Owner GUANGDONG UNIV OF PETROCHEMICAL TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com