Automatic face tracing method on basis of Kinect

Abstract

An automatic face tracing method on the basis of a Kinect, including the steps: (1) combing the Kinect with a programmable camera to form a tracing device and calibrating the tracing device; (2) acquiring data sequence of human skeleton and extracting skull point coordinates in the Kinect coordinate system; (3) acquiring a transformational matrix from a Kinect coordinate system to a camera coordinate system by utilizing external parameter of the camera and external parameter of the Kinect; (4) transforming the skull point coordinates acquired in the step (2) into the coordinate system of the camera by utilizing the transformational matrix acquired in the step (3), and calculating required rotating angle and zooming times of the camera in a horizontal and a perpendicular directions; and (5) driving the camera to correspondingly rotate and zoom according to the angle and times calculated in the step (4) to trace movements of a human face. The camera is driven to rotate and zoom by utilizing the continuously acquired skeleton data sequence, thus the human face can be traced automatically.

Description

technical field [0001] The invention relates to an automatic face tracking method, in particular to a Kinect-based automatic face tracking method, belonging to the field of human-computer interaction. Background technique [0002] Human-computer interaction technology refers to the technology that realizes effective communication between humans and computers in a way that is convenient for people to use through computer input and output devices. Facial tracking technology is an important technology in the field of human-computer interaction. It has broad application prospects in video conferencing, facial expression detail acquisition, consumer electronics products, facial motion capture, and natural human-computer interaction environments. [0003] Existing automatic face tracking methods are usually based on two-dimensional images. Such methods not only involve general image processing, but also may be designed to understand and describe images, such as pattern recognition...

AI Technical Summary

Problems solved by technology

[0003] Existing automatic face tracking methods are usually based on two-dimensional images. This type of method not only involves general image processing, but also may be designed to understand and describe images, such as pattern recognition, artificial intelligence, etc., which are relatively complex

The main problem is that it has certain requirements on the resolution of the image, and this type of method is sensitive to the surrounding lighting environment. Poor lighting conditions may affect the accuracy of tracking; Part of the local features of the face will affect the tracking of the face, or even cannot be tracked. Although it can be compensated by artificial intelligence, it is more complicated and affects real-time performance; in terms of interactive applications, this type of method only uses two-dimensional Image information, unable to robustly handle the interaction of human body parts in the depth direction

Images