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

Face detection and tracking method, robot head rotation control method, and robot

一种人脸检测、头部转动的技术，应用在人脸识别领域，能够解决机器人头部转动过程不精准、检测人脸误检测率高、非人脸检测成人脸等问题，达到保障流畅性、保障连续性、降低误检测率的效果

Active Publication Date: 2016-12-14
UBTECH ROBOTICS CORP LTD
View PDF4 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the false detection rate of existing face detection and tracking methods is high, and it is easy to detect non-faces as human faces.
When the existing face detection and tracking method is applied to the robot head rotation control method, due to the high false detection rate of face detection, the process of controlling the robot head rotation is inaccurate and prone to stuttering

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
  • Face detection and tracking method, robot head rotation control method, and robot
  • Face detection and tracking method, robot head rotation control method, and robot
  • Face detection and tracking method, robot head rotation control method, and robot

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] figure 1 and figure 2 The face detection and tracking method in this embodiment is shown. The face detection and tracking method includes:

[0049] S11: Face detection step: collecting images and performing face detection on each frame of the collected images, so as to determine a face frame of each frame of images. In this embodiment, the Viola-Jones face detection algorithm is used to perform face detection on each frame of images collected. The Viola-Jones algorithm uses integral images to extract image feature values, which improves the speed of face detection to a certain extent. At the same time, the Viola-Jones algorithm uses the feature screening features of the Adaboost classifier to retain the most useful features, reduce the computational complexity of detection, and make human detection faster. In addition, the Viola-Jones algorithm transforms the Adaboost classifier into a cascaded Adaboost classifier to improve the accuracy of face detection. It can ...

Embodiment 2

[0069] image 3 The head rotation control method of the robot in this embodiment is shown. Among them, the robot has built-in camera equipment for collecting images. The head rotation control method of the robot comprises the following steps:

[0070] S21: Presetting the central area Step: Presetting the central area of ​​the image. Such as Figure 4 As shown, the lower left corner of the current frame image is the origin O to establish a coordinate system OXY, the width of the preset image is w, and the height is h; if the width of the central area of ​​the preset image is 0.1w, the height is 0.1h; Assuming that the center of the central area of ​​the image is located at the center of the preset image, the coordinates of the center A of the central area of ​​the preset image are (0.5w, 0.5h). Correspondingly, the coordinates of the lower left corner of the central area are (0.45w, 0.45h), the coordinates of the upper left corner are (0.45w, 0.55h), the coordinates of the ...

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 face detection and tracking method, a robot head rotation control method, and a robot. The face detection and tracking method comprises: an image is collected and face detection is carried out on the image, thereby determining a face frame of each frame of image; detection error elimination processing is carried out on the current frame of image and the face frame of the current frame of image after processing is stored to be a first face frame; and according to the first face frame and a tracking face frame, a tracking frame of the current frame of image is determined and a face in the tracking frame of the current frame of image is tracked. With the face detection and tracking method, the detection error rate can be reduced and the face detection accuracy is improved. In addition, the robot head rotation control method is characterized in that the face detection and tracking method is used for carrying out face detection, so that smoothness of the robot head during the rotation process can be guaranteed and a stuck phenomenon during the rotation process can be avoided.

Description

technical field [0001] The invention relates to the field of face recognition, in particular to a face detection and tracking method, a robot head rotation control method and a robot. Background technique [0002] With the maturity of computer vision technology, computer vision technology has been widely used in people's daily life. For example, computer vision technology is used to control the robot, so that the robot has visual functions, so as to realize various intelligent operations such as detection, judgment, identification and measurement. The existing robot built-in camera equipment combined with face detection technology can detect the human face in the image collected by the robot camera, and can track the human face through mechanical movement, so that the robot head can rotate with the movement of the human face. However, the false detection rate of existing face detection and tracking methods is high, and it is easy to detect non-human faces as human faces. W...

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): G06K9/00
CPCG06V40/166G06V40/172G06V20/10G06V40/167G06V40/161G05B19/406G05B2219/33113G06T1/0014
Inventor 纪园熊友军
Owner UBTECH ROBOTICS CORP LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com