Intelligent robot rotation method based on sound source positioning and face detection

A technology of intelligent robot and face detection, applied in the direction of control using feedback, can solve problems such as inability to distinguish natural noise, and achieve the effect of improving anthropomorphic effect, improving positioning accuracy, and good anthropomorphic effect.

Inactive Publication Date: 2017-01-04
SHANGHAI YUANQU INFORMATION TECH
View PDF5 Cites 45 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The existing technology can locate any sound, and cannot dis

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
  • Intelligent robot rotation method based on sound source positioning and face detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] The preferred embodiments of the present invention are given below to describe the technical solution of the present invention in detail.

[0019] The intelligent robot rotation method based on sound source localization and human face detection of the present invention comprises the following steps:

[0020] Step 1: Receive the wake-up words and activate them; convert the wake-up words into syllables, and then decompose them into phoneme sequences, for example, turn off the light->guan bi dian deng->gu uan b i d ian deng, each phoneme corresponds to an acoustic A model that matches the collected audio signal with the phoneme model of the wake word.

[0021] Step 2, using the multi-microphone sound source localization technology to determine the general direction of the target person, and controlling the robot head to rotate to the target direction; the multi-microphone sound source localization technology adopted in the present invention is a voice localization technolo...

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 an intelligent robot rotation method based on sound source positioning and face detection. The method comprises the steps of (1) receiving a wake-up word and starting, (2) determining the general direction of a target person by using a multi-microphone sound source positioning technology, and controlling the head of a robot to a target direction, (3) turning a head camera to the direction of the target person to apply face positioning technology, and collecting an image through the head camera, (4) after collecting the image through the head camera, carrying out more precise positioning based on the face detection technology, and finally turning the head of the robot to point at the direction of a target speaker. According to the method, the positioning accuracy can be improved, and the personified effect of the interaction between a user and the robot is improved greatly.

Description

technical field [0001] The invention relates to an intelligent robot rotation method, in particular to an intelligent robot rotation method based on sound source localization and human face detection. Background technique [0002] In conventional anthropomorphic smart home robot products, most of the head rotations are in a preset or random way, and it is difficult not to achieve an anthropomorphic effect. A small number of multi-mic sound source localization is used, but limited by hardware size, environmental noise and algorithm performance, its positioning accuracy is not very high, and it can only detect the approximate direction and position of the sound source. [0003] Face detection technology has been widely used, including cameras, camera monitoring, etc. Its advantage is high detection accuracy, but the defect is that the coverage of the lens is limited. If the image collected by the lens does not face the target face, it cannot be detected. out. The sound sourc...

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): G05D3/12
Inventor 赖伟
Owner SHANGHAI YUANQU INFORMATION 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