Target re-identification method, network training method thereof and related device

A technology that re-identifies and targets is applied in the field of image recognition, and can solve problems such as the target recognition effect is not good enough

Active Publication Date: 2020-10-23
ZHEJIANG DAHUA TECH CO LTD
View PDF11 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] This application provides an image enhancement method, electronic equipment and storage medium, which can solve the problem that the target recognition effect of the target re-identification network obtained by the existing training method is not good enough

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
  • Target re-identification method, network training method thereof and related device
  • Target re-identification method, network training method thereof and related device
  • Target re-identification method, network training method thereof and related device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.

[0021] The terms "first", "second", and "third" in this application are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of indicated technical features. Thus, features defined as "first", "second", and "third" may explicitly or implicitly include at least one of these features. In the description of the present application, "plurality" means at least t...

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 target re-identification method, a network training method thereof and a related device. The method comprises the steps of obtaining a training image set, wherein the training image set comprises images of multiple targets, and each target at least corresponds to two styles of images; identifying each image in the training image set by using a target re-identification network to obtain an identification result of each image, the identification result comprising features of the image; obtaining loss of the target re-identification network based on the identification result, the loss comprises first distance loss, and the first distance loss is obtained based on the distance between features of different styles of images corresponding to the target; adjusting parameters of the target re-identification network based on the loss; and repeating the steps until the condition of stopping training is met. In this way, the target recognition performance of the target re-recognition network can be improved.

Description

technical field [0001] The present application relates to the technical field of image recognition, in particular to a target re-identification method, its network training method, and related devices. Background technique [0002] Compared with the face recognition task with a fixed viewing angle, pedestrian re-identification is not limited by the face viewing angle, human body posture and camera viewing angle, and its recognition effect is relatively better and the application scenarios are wider. Therefore, object re-identification technology has achieved rapid development in recent years. [0003] Target re-identification technology aims to find specific targets from videos or images, and it has important application value in the fields of security, new retail and the Internet. The targets of target re-identification technology can be pedestrians, vehicles, etc. Generally, a target re-identification network is used to perform target recognition, for example, a pedestri...

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
CPCG06V40/10G06V20/20G06V2201/07G06F18/214Y02T10/40
Inventor 孙立波潘华东殷俊
Owner ZHEJIANG DAHUA TECH CO LTD
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
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap