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

Attribute recognition model training method, recognition method, electronic device, storage medium

A technology of attribute recognition and model training, applied in the field of image processing, can solve the problems of difficult data and complex scene sources, and achieve the effect of good data collection cost, saving attribute labeling cost, and saving a lot of attribute labeling work.

Active Publication Date: 2022-07-29
SUZHOU KEDA TECH
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, due to the wide variety of pedestrian attributes and complex scene sources, it is extremely difficult to obtain a large amount of fully labeled data

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
  • Attribute recognition model training method, recognition method, electronic device, storage medium
  • Attribute recognition model training method, recognition method, electronic device, storage medium
  • Attribute recognition model training method, recognition method, electronic device, storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments, however, can be embodied in various forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0052] Furthermore, the drawings are merely schematic illustrations of the invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus their repeated descriptions will be omitted. Some of the block diagrams shown in the figures are functional entities that do not necessarily necessarily correspond to physically or logically separate entities. These functional enti...

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 present invention provides a pedestrian attribute recognition model training method, identification method, electronic equipment, storage medium, and pedestrian attribute recognition model training method, including: constructing a training data set, a pedestrian image with marked attributes and a pedestrian image marked with ID; A pedestrian attribute identification network, the pedestrian attribute identification network includes a backbone network, a spatial information branch network and a semantic information branch network, the outputs of the backbone network are respectively input to the spatial information branch network and the semantic information branch network; The pedestrian attribute recognition network is trained with the training data set, and a pedestrian attribute recognition model is obtained, and the pedestrian attribute recognition model is used for recognizing the attributes in the pictures according to the input pictures. The method and device provided by the present invention learn more comprehensive and robust information through model training, save a lot of attribute labeling work, and obtain a better pedestrian attribute recognition model with less data collection cost.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a pedestrian attribute recognition model training method, recognition method, electronic equipment and storage medium. Background technique [0002] Pedestrian attribute recognition is a method of judging the attributes of pedestrians based on pedestrian photos or video screenshots, such as gender, clothing color, clothing style, whether they wear glasses, etc. At present, due to the wide variety of pedestrian attributes and complex scene sources, it is extremely difficult to obtain a large amount of fully annotated data. Most data have only partial attribute annotations, or even no attribute annotations. Pedestrian identity data has only one mark, and multiple pictures can be generated during the walking process of a person in the video. Compared with attribute labeling, pedestrian identity data is less expensive and less difficult to mark. [0003] Semi-supervised learning is ...

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): G06V40/10G06V10/44G06V10/56G06V10/764G06V10/82G06N3/04G06N3/08
CPCG06N3/08G06V40/10G06V10/44G06V10/56G06N3/045G06F18/24
Inventor 高毓声晋兆龙付马肖潇
Owner SUZHOU KEDA 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