Face detecting and tracking method and device and method and system for controlling rotation of robot head

Abstract

A face detecting and tracking method includes: acquiring an image and performing a depth detection for the image to obtain a depth value of each pixel of the image; determining one or more face candidate areas based on depth value of each pixel of the image of current frame; performing a face detection to the one or more face candidate areas to determine one or more face boxes of the image of current frame; and determining a tracking box of the image of current frame based on the one or more face boxes and a tracked face box, and tracking the face in the tracking box of the image of current frame.

Description

CROSS REFERENCE TO RELATED APPLICATIONS[0001]This application claims priority to Chinese Patent Application No. 201610619340.1, filed Jul. 29, 2016, which is hereby incorporated by reference herein as if set forth in its entirety.BACKGROUND1. Technical Field[0002]The present disclosure generally relates to human face recognition technology, and particularly to a human face detecting and tracking method and device, and a method and system for controlling rotation of a robot head.2. Description of Related Art[0003]As computer vision technology becomes mature, it has been widely used in daily lives. For example, it can be used to control a robot and enables the robot to have visual function, thereby performing various detecting, determining, recognizing and measuring operations. Some conventional, robots are equipped with a camera and are able to detect human feces in the images captured by the camera using face detecting technology, and track a detected human face, causing head of the...

AI Technical Summary

Benefits of technology

The face detecting and tracking method described in this patent improves the accuracy of detecting and tracking faces in images. It uses depth detection to determine the depth value of each pixel in an image, which helps to identify areas that may contain faces. The method then creates a tracking box around these areas to ensure continuous detection of the face. The method can be used with a built-in camera device and can control a robot head to rotate to position the tracking box in the center of the image. Overall, this method improves the accuracy and efficiency of face detection and tracking in image processing.

Problems solved by technology

Some of the conventional human face detecting and tracking methods have high detection errors, which may tend to recognize non-human faces as human faces.

Because of the high detection errors, the control of the rotation process of the robot heads is not accurate when controlling the robot heads to rotate using the conventional human face detecting and tracking methods.

Images