Three-dimensional human body posture estimation method and device, equipment and medium
A posture estimation and human posture technology, applied in the field of three-dimensional human posture estimation, can solve the problems of insufficient stability, poor local extremum of neural network model, etc., to achieve the effect of improving accuracy
Active Publication Date: 2020-10-02
TENCENT TECH (SHENZHEN) CO LTD
View PDF6 Cites 13 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The above method is a pose estimation method based on a single frame and a single view. The neural network model is prone to fall into poor local extremum, and the effect is not stable enough.
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0030] 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.
[0031] First, some nouns involved in this application are briefly introduced:
[0032] Artificial Intelligence (AI) is a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technique of computer science that attempts to understand the nature of intelligence and produce a new kind of intelligent machine that can respond in a similar way to human intelligence. Artificial intelligence is to study the design principles and implementation methods of various intelligent ...
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
Login to View More Abstract
The invention discloses a three-dimensional human body posture estimation method and device, equipment and a medium, and relates to the field of artificial intelligence. The method comprises the following steps: acquiring a video frame sequence of n visual angles; extracting initial attitude estimation of a single video frame in the n visual angles based on a neural network model; performing single-frame single-view human body posture estimation on the initial posture estimation to obtain single-view posture estimation sequences corresponding to n views respectively; performing single-frame multi-view human body posture estimation on single-view posture estimation with the same timestamp in the single-view posture estimation sequences corresponding to the n views to obtain a multi-view posture estimation sequence; and performing multi-frame and multi-view human body posture estimation on the multi-view posture estimation to obtain multi-view and multi-frame posture estimation.
Description
technical field [0001] The embodiments of the present application relate to the field of artificial intelligence, and in particular to a method, device, device and medium for estimating a three-dimensional human pose. Background technique [0002] 3D Human Pose Estimation is a technology that recognizes the 3D actions made by the human body from 2D images. [0003] A method for estimating a three-dimensional human body pose is provided in the related art. A two-dimensional image is input to a neural network model, and a three-dimensional human body pose represented by a three-dimensional model is output based on constrained optimization of two-dimensional key points (2DKeypoint) of the image. [0004] The above method is a pose estimation method based on a single frame and a single perspective, and the neural network model tends to fall into a poor local extremum, and the effect is not stable enough. Contents of the invention [0005] The embodiment of the present applica...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/34G06N3/04G06N3/08G06N20/00
CPCG06N3/08G06N20/00G06V20/64G06V40/10G06V20/41G06V10/267G06N3/045G06N3/0464G06V40/103G06V10/82G06V10/806G06V10/803G06V20/46
Inventor 陈卫东张维康頔暴林超
Owner TENCENT TECH (SHENZHEN) CO LTD