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

Pedestrian re-identification method and device, electronic equipment and storage medium

A pedestrian re-identification and re-identification technology, applied in the field of artificial intelligence, can solve the problem of low pedestrian re-identification accuracy

Pending Publication Date: 2020-11-03
SHENZHEN ZTE NETVIEW TECH +1
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The technical problem mainly solved by the present invention is how to solve the problem of low pedestrian re-identification accuracy when the image crosses domains

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 re-identification method and device, electronic equipment and storage medium
  • Pedestrian re-identification method and device, electronic equipment and storage medium
  • Pedestrian re-identification method and device, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] Please refer to figure 1 , figure 1 It is a flow chart of a pedestrian re-identification method in an embodiment. The pedestrian re-identification method can be executed on a server, and it includes steps S10 to S30, which will be described in detail below.

[0042] Step S10, acquiring image information containing pedestrians. The image information containing pedestrians in this embodiment may be video or pictures of pedestrians captured by a surveillance camera, which may be images in various forms such as RGB images and infrared images.

[0043] Step S20, input the image information containing pedestrians into the pre-trained neural network to obtain the feature vectors of pedestrians in the image information, wherein the feature vectors of pedestrians include feature vectors of pedestrian attributes and feature vectors of pedestrian re-identification.

[0044] In this embodiment, the pedestrian attributes refer to the gender, age, clothing, backpack, long hair, etc...

Embodiment 2

[0058] Please refer to image 3 , image 3 It is a structural block diagram of a pedestrian re-identification device in an embodiment, and the pedestrian re-identification device includes: an image acquisition module 10 , a feature extraction module 20 and a pedestrian re-identification module 30 .

[0059] The image acquisition module 10 is used to acquire image information containing pedestrians. The image information containing pedestrians in this embodiment may be video or pictures of pedestrians captured by a surveillance camera, which may be images in various forms such as RGB images and infrared images.

[0060] The feature extraction module 20 is used to input image information containing pedestrians into the pre-trained neural network to obtain feature vectors of pedestrians in the image information, wherein the feature vectors of pedestrians include feature vectors of pedestrian attributes and feature vectors of pedestrian re-identification.

[0061] In this embodi...

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 discloses a pedestrian re-identification method and device, electronic equipment and a storage medium. The method comprises the steps: obtaining image information containing pedestrians;inputting the image information containing the pedestrians into a pre-trained neural network to obtain feature vectors of the pedestrians in the image information, wherein the feature vectors of thepedestrians includes feature vectors of pedestrian attributes and feature vectors of pedestrian re-identification; comparing the feature vector of the pedestrian with a feature vector in a preset feature vector set, and re-identifying the pedestrian in the image information according to a comparison result. Due to the fact that the pedestrian attribute image data are added into the neural networkfor pedestrian re-identification in the training stage, the pre-trained neural network has both the fine-grained characteristic of pedestrian re-identification and the coarse-grained characteristic ofpedestrian attributes, and the problem that pedestrian re-identification precision is low during image cross-domain is solved.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a pedestrian re-identification method, device, electronic equipment and storage medium. Background technique [0002] Pedestrian re-identification refers to retrieving the pedestrian in the pedestrian image from the images captured by different shooting devices according to the acquired pedestrian image. The biggest problem facing pedestrian re-identification now is the problem of image cross-domain, that is, when the B training image dataset is input into the neural network that has been trained using the A training image dataset, the performance of the neural network often drops significantly, affecting pedestrians. Accuracy of re-identification. Contents of the invention [0003] The technical problem mainly solved by the present invention is how to solve the problem of low pedestrian re-identification accuracy when images cross domains. [0004] Ac...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V40/103G06N3/045G06F18/241
Inventor 张浩李一力邵新庆刘强徐明
Owner SHENZHEN ZTE NETVIEW TECH
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