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

Feature extraction method, device, terminal device and storage medium

A feature extraction and feature fusion technology, applied in the field of computer vision, can solve the problem of low extraction accuracy, avoid feature confusion and improve detection accuracy

Active Publication Date: 2021-11-19
BEIJING CALORIE INFORMATION TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when the existing neural network model extracts the joint position, the extraction accuracy is low

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
  • Feature extraction method, device, terminal device and storage medium
  • Feature extraction method, device, terminal device and storage medium
  • Feature extraction method, device, terminal device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] figure 1 It is a schematic flow chart of a feature extraction method provided in Embodiment 1 of the present invention. This method is applicable to the situation of feature extraction for users. Specifically, this method is applicable to the situation of body feature and joint feature extraction for users. The method can be performed by a feature extraction device, wherein the device can be implemented by software and / or hardware, and is generally integrated on a terminal device. In this embodiment, the terminal device includes but is not limited to: computers, personal digital assistants and other devices.

[0044] Such as figure 1 As shown, a feature extraction method provided in Embodiment 1 of the present invention includes the following steps:

[0045] S101. Acquire an image of a user.

[0046] In this embodiment, the image may include a photo of the user. The image can be used to estimate the pose of the user, such as analyzing the behavior of the user. The i...

Embodiment 2

[0081] Figure 2a It is a schematic flowchart of a feature extraction method provided by Embodiment 2 of the present invention. This Embodiment 2 is optimized on the basis of the foregoing embodiments. In this embodiment, the target element area is subjected to feature fusion and feature migration to obtain enhanced joint features and enhanced limb features, which is further embodied as: input the target element area into the joint model to obtain the initially added joint features and Joint fusion feature, the joint fusion feature is obtained by merging the features of the joint convolution layer set in the joint model, and the joint convolution layer set is the convolution layer in the joint model except for the output initial joint feature The convolutional layer, the initial joint feature is obtained by convolving the joint fusion feature;

[0082]Input the target element area into the limb model to obtain the newly added limb feature and limb fusion feature. The limb fus...

Embodiment 3

[0139] image 3 It is a schematic structural diagram of a feature extraction device provided by Embodiment 3 of the present invention. The device is applicable to the case of extracting features from users. Specifically, the method is applicable to the case of extracting body features and joint features from users. Wherein the device can be realized by software and / or hardware, and generally integrated on the terminal equipment.

[0140] Such as image 3 As shown, the device includes: an acquisition module 31 and a processing module 32;

[0141] Wherein, the obtaining module 31 is used to obtain the image of the user;

[0142] The processing module 32 is configured to input the image into a predetermined enhancement model for enhancement processing to obtain joint features and limb features corresponding to the image, and the enhancement processing includes at least one of the following feature fusion, feature migration, and feature extraction .

[0143] In this embodiment...

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 feature extraction method, device, terminal equipment and storage medium. The method includes: acquiring an image of the user; inputting the image into a predetermined enhancement model for enhancement processing to obtain joint features and body features corresponding to the image, and the enhancement processing includes at least one of the following feature fusion, feature Migration and feature extraction. Using this method, the accuracy of feature extraction can be improved.

Description

technical field [0001] The embodiments of the present invention relate to the technical field of computer vision, and in particular, to a feature extraction method, device, terminal device, and storage medium. Background technique [0002] With the advancement of science and technology, it is becoming a reality to realize machine autonomous analysis, understanding and decision-making. Human body posture estimation (joint point positioning) is one of the key technologies to realize this function. This technology has a wide range of applications in life and industry, including video surveillance, autonomous driving, game entertainment, smart home, video retrieval and industrial control, etc. With the help of this technology, smart devices will enter our lives and serve humans better. [0003] Human pose estimation is the process of locating the locations of joints of human body parts in video or image data. At present, the neural network model is mostly used to estimate the...

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): G06K9/00G06K9/62
CPCG06V40/20G06F18/214G06F18/253
Inventor 黄盈
Owner BEIJING CALORIE INFORMATION TECH CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com