Target recognition method and device

A target recognition and target technology, applied in the field of image processing, can solve the problems of reducing the overall effect of algorithm recognition, blurred black hat borders, difficult hat recognition, etc., to achieve reliable final results of target recognition, improve recognition effect, and improve accuracy. Effect

Pending Publication Date: 2021-12-07
ZHEJIANG DAHUA TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Moreover, when performing target recognition, there are often some difficult-to-recognize images. For example, if the hair color of a person wearing a hat is black, and the color of the hat is also black

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 recognition method and device
  • Target recognition method and device
  • Target recognition method and device

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0081] Embodiment:

[0082] Combine Figure 4 Indicated.

[0083] In image to be processed ( Figure 4 Represented by A1) whether human hat as an example, wherein the cap can be used as a target to be identified, whether hat sub-attributes to be recognized as a target.

[0084] When the hat color and hair color are not similar, as Figure 5 As shown, the non-black hat and hair color difference obvious, it is easy to discern.

[0085] Since the black hat and black hair similar color (such as Image 6Black hair is shown wearing a black hat man), they are easily identified as non-hat, recognition performance is poor, it is necessary to cap the main sub-attributes as color attributes.

[0086] Thus, the first history image may be a black hat and concentrate includes a sample without hat singled out as the second history image set, the second history image using a set of training branch (i.e. auxiliary branch identification attributes) to obtain the final target recognition Model.

[0087]...

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 recognition method and device, and a target recognition model at least comprises a main attribute recognition branch, a sub attribute recognition branch and an auxiliary attribute recognition branch, so when the target recognition model is used for target recognition, corresponding recognition results can be respectively obtained, and the first main attribute recognition result can be corrected on the basis of the sub-attribute recognition result and the second main attribute recognition result; and finally, the corrected first main attribute recognition result is adopted to determine the attribute feature of the target to be recognized, namely, the final result of target recognition is the result of the synergistic effect of the three branches; therefore, through the auxiliary attribute recognition branch, the recognition effect of the attribute features of the target to be recognized can be improved, the final result of target recognition is more reliable and accurate, the influence of an image difficult to recognize on the overall recognition effect can be eliminated, and the accuracy of target recognition is improved.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a target recognition method and device. Background technique [0002] When performing target recognition on an image, if the image includes a worker wearing a hat and an apron, the hat can be used as the target to be recognized, and whether wearing a hat can be used as the main attribute of the target to be recognized; or, the apron can be used as The target to be identified, and whether to wear an apron is the main attribute of the target to be identified. [0003] Moreover, when performing target recognition, there are often some difficult-to-recognize images. For example, if the hair color of a person wearing a hat is black, and the color of the hat is also black, it is easy to cause the boundary of the black hat to be blurred, which in turn makes the hat difficult to recognize. These difficult-to-recognize images will reduce the overall effect of algorithm recogniti...

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
IPC IPC(8): G06K9/00G06K9/62
CPCG06F18/22G06F18/24G06F18/214
Inventor 杨永涛唐邦杰潘华东殷俊
Owner ZHEJIANG DAHUA TECH
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