Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Pedestrian image generation method and pedestrian image generation system based on cyclic generation type countermeasure network

An image generation, generative technology, applied in the field of image recognition, can solve problems such as poor model performance, achieve high accuracy, reduce the workload of labeling, and improve the effect of migration

Inactive Publication Date: 2018-07-06
PEKING UNIV
View PDF4 Cites 31 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In pedestrian re-identification, changes in factors such as background, lighting, and camera parameters often lead to large differences between the available annotation data set and the target application scene data
Models trained directly using such labeled data perform poorly in different types of application scenarios

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
  • Pedestrian image generation method and pedestrian image generation system based on cyclic generation type countermeasure network
  • Pedestrian image generation method and pedestrian image generation system based on cyclic generation type countermeasure network
  • Pedestrian image generation method and pedestrian image generation system based on cyclic generation type countermeasure network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] figure 1 It is a flow chart of the pedestrian image generation method based on the cyclic generative confrontation network of the present invention, including the following steps:

[0046] S1. Transfer function learning, generating a generative adversarial network for character transfer; the transfer function includes style loss and identity loss.

[0047] Among them, the objective function of the character migration generative confrontation network is:

[0048]

[0049] in, Indicates style loss, denotes the identity loss, and λ1 denotes the exchange coefficient between the two losses.

[0050] Suppose G represents the style mapping function from A to B, and Represents the style mapping function from B to A. D. A and D B denote the style discriminators for A and B, respectively. Then the style loss can be expressed by the following formula (2):

[0051]

[0052] in, denotes the standard adversarial loss, Denotes cycle consistency loss, λ 2 Indicat...

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 provides a pedestrian image generation method and a pedestrian image generation system based on a cyclic generation type countermeasure network. The method comprises the steps of learning a migration function and generating a person migration generation type countermeasure network; based on the person migration generation type countermeasure network, completing the character migration in a pedestrian image, migrating the pedestrian image from one database to another database, and generating a new pedestrian image. The migration function comprises style loss and identity loss. Compared with a traditional method, the method is good in migration effect for public data sets based on the re-recognition of a plurality of pedestrians. Therefore, on the premise that no extra data labeling is required, a robust pedestrian re-recognition model is trained in a target application scene and the accuracy is higher.

Description

technical field [0001] The present invention relates to the technical field of image recognition, in particular to a pedestrian image generation method and system based on a generative confrontation network. Background technique [0002] In recent years, as people pay more and more attention to the public safety of the society, video surveillance systems have become popular. Public places such as airports, railway stations, campuses and office buildings are in urgent need of monitoring to protect security. In the face of massive surveillance video data, a large amount of manpower needs to be invested in the monitoring and retrieval of video information. This method is not only inefficient, but also causes additional waste of resources. If computer vision analysis technology can be used to automate monitoring and analysis of video information, the construction of a "safe city" will definitely be greatly accelerated. [0003] Person re-identification is a key task in compute...

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 Applications(China)
IPC IPC(8): G06K9/00G06K9/62
CPCG06V40/10G06F18/2193
Inventor 张史梁田奇高文魏龙辉
Owner PEKING UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap 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