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

Key point detection method, device and equipment and readable medium

A detection method and key point technology, applied in the field of computer vision, can solve problems such as high accuracy and high efficiency, and achieve the effects of saving calculation time, improving detection efficiency, and improving accuracy

Active Publication Date: 2019-04-05
BEIJING BYTEDANCE NETWORK TECH CO LTD
View PDF6 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, the detected key points are often further processed to achieve the purposes of beautification, correction, action recognition, etc., thus putting forward higher requirements for the accuracy and efficiency of key point detection. However, the existing key point detection methods cannot Meet the requirements of high accuracy and high efficiency

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
  • Key point detection method, device and equipment and readable medium
  • Key point detection method, device and equipment and readable medium
  • Key point detection method, device and equipment and readable medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0028] figure 1 It is a flow chart of a key point detection method provided by Embodiment 1 of the present disclosure. This embodiment is applicable to the case of performing key point detection on a video frame sequence displaying a user image, and the method can be executed by a key point detection device , the device may consist of hardware and / or software, and be integrated into an electronic device, specifically including the following operations:

[0029] S110. Acquire a video frame sequence displaying a user image.

[0030] A video frame sequence refers to continuous video frames in a continuous video frame time period within a period of time in a video stream, and the video frame sequence includes multiple video frames, for example, 20 video frames.

[0031] In this embodiment, the duration of the acquired video frame sequence should be short, for example, the duration is within the preset duration range, such as 3 seconds, so that the display position of the user ima...

Embodiment 2

[0042] This embodiment further optimizes the various optional implementations in the above embodiments. Optionally, in the above embodiments, an additional operation "input the target object and the detection frame including multiple key points in the template frame to the tracking model, if not The target object in the detection frame is detected, and the detection frame is determined as a new template frame; return to the operation of inputting the template frame of the video frame sequence into the key point detection model to obtain the position information of multiple key points". figure 2 It is a flow chart of a key point detection method provided in Embodiment 2 of the present disclosure, specifically including the following operations:

[0043] S210. Acquire a video frame sequence displaying a user image.

[0044] S220. Input the template frame of the video frame sequence into the key point detection model to obtain position information of multiple key points.

[004...

Embodiment 3

[0052] This embodiment further optimizes the optional implementation manners of the foregoing embodiments, and this embodiment provides a training process of a key point detection model and a tracking model. Since the key point detection model and the tracking model jointly perform key point detection on the video frame sequence, based on this, the present embodiment trains the key point detection model and the tracking model together. combine image 3 , the method provided by the embodiment of the present disclosure specifically includes the following operations:

[0053] S310. Acquire a plurality of sample video frame sequences displaying user images.

[0054] Each sample video frame sequence includes a plurality of sample video frames. The sample video frame sequence is similar to the video frame sequence in the foregoing embodiments, and its duration is within a preset duration range.

[0055] Optionally, since the tracking model will be limited to a simple sample video...

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 embodiment of the invention discloses a key point detection method, device and equipment and a readable medium. The method comprises the steps of obtaining a video frame sequence on which a user image is displayed; Inputting the template frame of the video frame sequence into a key point detection model to obtain position information of a plurality of key points; And inputting the target object comprising the plurality of key points in the template frame and the detection frame into the tracking model, detecting the target object in the detection frame, and obtaining the position information of the plurality of key points in the target object. According to the embodiment of the invention, the efficiency and accuracy of key point detection can be improved.

Description

technical field [0001] Embodiments of the present disclosure relate to computer vision technology, and in particular to a key point detection method, device, device and readable medium. Background technique [0002] With the development of computer vision, some electronic devices can detect various key points of the user, such as various joints, limbs, and facial features, from the user's image. [0003] At present, the detected key points are often further processed to achieve the purposes of beautification, correction, action recognition, etc., thus putting forward higher requirements for the accuracy and efficiency of key point detection. However, the existing key point detection methods cannot Meet the requirements of high accuracy and high efficiency. Contents of the invention [0004] Embodiments of the present disclosure provide a key point detection method, device, device and readable medium, so as to improve the accuracy and efficiency of key point detection. ...

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): G06T7/246G06K9/46
CPCG06T7/246G06T2207/20081G06T2207/10016G06T2207/10024G06V10/462
Inventor 胡耀全
Owner BEIJING BYTEDANCE NETWORK TECH CO LTD
Features
  • Generate Ideas
  • 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