Unlock instant, AI-driven research and patent intelligence for your innovation.

Target re-identification method and device, model training method and device, equipment and storage medium

A re-identification and model technology, applied in the field of image processing, can solve the problem of low accuracy of re-identification results

Pending Publication Date: 2021-04-20
SHENZHEN INTELLIFUSION TECHNOLOGIES CO LTD
View PDF11 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present application provides a target re-identification method, model training method, device, equipment and storage medium, which can be used to solve the problem of low accuracy of re-identification results existing in related technologies

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 and device, model training method and device, equipment and storage medium
  • Target re-identification method and device, model training method and device, equipment and storage medium
  • Target re-identification method and device, model training method and device, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0057] In order to make the purpose, technical solution and advantages of the present application clearer, the implementation manners of the present application will be further described in detail below in conjunction with the accompanying drawings.

[0058] Before explaining the embodiment of the present application in detail, the application scenario of the embodiment of the present application will be described first.

[0059] The object re-identification method provided in the embodiment of the present application is applied to a scene of re-identifying an image or a video, so as to identify a specific object in the image or video. For example, given a specific target to be identified, object recognition technology can identify a specific target from images captured by different cameras. Specifically, it can be applied to fields such as intelligent video surveillance, robotics, automatic driving, intelligent security, criminal investigation, and human-computer interaction....

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 and device, a model training method and device, equipment and a storage medium, and belongs to the field of image processing. The method comprises the steps of obtaining a first target frame image, wherein the first target frame image is obtained by performing target detection on a to-be-detected image; correcting the first target frame image through a spatial transformation network model to obtain a second target frame image; and performing re-identification on the second target frame image through a re-identification model to obtain target features. Thus, the detected non-standard target frame image can be corrected into the standard target frame image through the spatial transformation network model, and then the standard target frame image is used as the input image of the re-identification model for re-identification, so that the input image of the re-identification model can be ensured to be consistent with the standard target frame image used in the training process of the re-identification model, the influence of inconsistency of the input image of the re-identification model and the standard target frame image used in the training process on the precision of the re-identification model is avoided, and the accuracy of the re-identification result is improved.

Description

technical field [0001] The present application relates to the field of image processing, and in particular to a target re-identification method, model training method, device, equipment and storage medium. Background technique [0002] Target ReID (Re-Identification, re-identification) refers to the use of image processing technology to identify specific targets in images, which plays an essential role in the fields of intelligent video surveillance, robotics, and automatic driving. Target ReID mainly includes pedestrian ReID or vehicle ReID, etc. For example, in pedestrian ReID, image processing technology can be used to determine whether a pedestrian under a certain camera appears in other cameras, so as to describe the pedestrian's activity path and achieve cross-camera tracking. [0003] In related technologies, a re-identification model can be used for re-identification. The input of the re-identification model is a target frame image, and the output is the target feat...

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): G06K9/00G06K9/32G06K9/62
Inventor 李帅杰魏新明
Owner SHENZHEN INTELLIFUSION TECHNOLOGIES CO LTD