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

A face following method and device based on a monocular camera

A monocular camera and face detection technology, applied in the field of image processing, can solve the problem of low computing performance of the face recognition follower module, and achieve the effect of avoiding losing targets, avoiding blind movement, and avoiding swinging back and forth

Active Publication Date: 2019-05-31
SHANGHAI XPARTNER ROBOTICS +1
View PDF8 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Based on the above content, the present invention aims at the problem of low computing performance of the face recognition following module on the arm system, and provides a method for following the face of a robot head based on a monocular camera to ensure the algorithm for subsequent face following real-time

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
  • A face following method and device based on a monocular camera
  • A face following method and device based on a monocular camera
  • A face following method and device based on a monocular camera

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings. The following description of the embodiments of the present invention with reference to the accompanying drawings is intended to explain the general inventive concept of the present invention, but should not be construed as a limitation of the present invention.

[0051] Additionally, in the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the present disclosure. However, one or more embodiments may be practiced without these specific details.

[0052] Such as figure 1 and figure 2 As shown, in step 100, the image is detected using the PICO face detection technology, and the face in the first frame of image detected within one detection cycle is ...

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 real-time face following method based on a monocular camera, and the method comprises the steps: Step 100, carrying out the detection of an image through employing a PICO face detection technology, and enabling a face in a first frame of image detected in a detection period to serve as a positive sample; Step 200, marking a face following frame in the positive sample areain the first frame of image; Step 300, in the nth frame of image, taking the (n-th) th frame of image as the (n-th) th image; wherein the central point of the face following frame in one frame of image serves as an original point, m times of the face following frame are amplified in the same proportion to serve as a face detection area of the nth frame of image, and n and m are both integers larger than or equal to 2; Step 400, detecting a human face detection area of the nth frame of image to obtain a central coordinate of an nth frame of human face following frame; Step 500, comparing the central coordinate of the nth frame of face following frame with the nth-th frame of face following frame by adopting a gradient algorithm; and the central point coordinate of the face following framein the one-frame image is calculated, and calculating the estimated rotation angle of the monocular camera in the following process, so that the face is tracked in real time.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a method for following a human face with a robot head based on a monocular camera. Background technique [0002] The robot face following method includes two parts: face detection and tracking and robot head movement control. In the present invention, the head of the robot can move left and right and up and down similar to the pan-tilt, so the following movement is mainly the movement of the head of the robot in the horizontal and vertical directions. To ensure that the robot can follow the movement of the human face in real time, the robot should first be able to detect the human face in real time within its field of view. Therefore, the real-time performance of the face-following algorithm directly affects the real-time performance of the entire face-following algorithm, but such algorithms are often limited by the configuration of computer hardware and operating systems; The ...

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): H04N5/232H04N5/14G06K9/00
Inventor 恽为民刘松庞作伟
Owner SHANGHAI XPARTNER ROBOTICS
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