Check patentability & draft patents in minutes with Patsnap Eureka AI!

Audio and video combined positioning method and device, electronic equipment and storage medium

A positioning method, audio and video technology, applied in speech analysis, image data processing, instruments, etc., can solve problems such as inaccurate positioning results

Active Publication Date: 2021-04-06
BEIJING HUAJIE IMI TECH CO LTD
View PDF7 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of this, the present application provides a positioning method, device, electronic equipment and storage medium combining audio and video to solve the problem of positioning the user through voice recognition or image recognition in the prior art, resulting in positioning results inaccurate question

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
  • Audio and video combined positioning method and device, electronic equipment and storage medium
  • Audio and video combined positioning method and device, electronic equipment and storage medium
  • Audio and video combined positioning method and device, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0103] Optionally, in another embodiment of the present application, an implementation of step S202 specifically includes:

[0104] Get the initial human body pose parameters of the human body contour map.

[0105] Based on the initial human body posture parameters, multiple human body posture parameters at the current moment are predicted.

[0106] Using an optimization algorithm, the most matching human body posture parameters are found from multiple human body posture parameters at the current moment, and used as the user's human body posture parameters.

[0107] It should be noted that after extracting the user's human body contour map, the initial human body posture parameters of the human body contour map are obtained first, and then based on the initial human body posture parameters, multiple human body posture parameters at the current moment can be predicted, and each skeleton of the human body Each node gets multiple estimates. Finally, the optimization algorithm i...

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 provides an audio and video combined positioning method and device, electronic equipment and a storage medium. The audio and video combined positioning method comprises the following steps: firstly, acquiring a user image acquired by an image acquisition part, and calculating to obtain mouth coordinates of a user by utilizing the user image; then, obtaining the distance from the user to the image acquisition part, and calculating the pitch angle between the user and the image acquisition part by utilizing the mouth coordinates and the distance from the user to the image acquisition part; meanwhile, obtaining voice signals, collected by the audio collection component, of the user are obtained, and then obtaining the pitch angles, corresponding to the pitch angles of the user and the image collection component, of the user and the audio collection component through calculation based on the coordinate system of the audio collection component; and finally, positioning the user by using the voice signal and the pitch angle between the user and the audio acquisition part.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, and in particular to a positioning method, device, electronic equipment and storage medium combining audio and video. Background technique [0002] In recent years, with the development of science and technology, more and more artificial intelligence devices have appeared in people's lives. These artificial intelligence devices can interact with users and execute various instructions issued by users, which greatly facilitates users' lives or Work. When these artificial intelligence devices interact with users, they need to locate the users before they can accurately interact with the corresponding users. [0003] In the prior art, the two positioning methods of speech recognition or image recognition are still in two relatively independent fields in the application of artificial intelligence devices. Therefore, when an artificial intelligence device locates a user, it ...

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 Applications(China)
IPC IPC(8): G10L25/51G10L21/0216G10L21/0208G06T7/277G06T7/215G06T7/194G06K9/62G06K9/46G06K9/32G06K9/00
CPCG10L25/51G10L21/0208G10L21/0216G06T7/194G06T7/215G06T7/277G06T2207/10016G06T2207/30196G10L2021/02166G10L2021/02082G06V40/20G06V10/25G06V10/44G06F18/22
Inventor 郝昊李骊
Owner BEIJING HUAJIE IMI 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