A face tracking method and camera

Abstract

The invention discloses a face tracking method and a camera. The method of the present invention includes: obtaining the initial position of the facial feature point of the first frame image in the image frame sequence collected; using the initial position of the facial feature point as the input of the convolutional neural network, and the output of the convolutional neural network The position probability heat map of the facial feature point, the position probability heat map of the facial feature point adopts a point distribution model to perform iterative regression processing, and obtains the pixel position of the facial feature point in the first frame image; using the The facial feature point is at the pixel position of the first frame image, and the initial position of the facial feature point of the second frame image in the image frame sequence is acquired to realize face tracking. The invention can realize alignment and tracking of human faces between frames, avoid instability and shaking of facial feature points between frames, and improve tracking accuracy and tracking speed.

Description

technical field [0001] The invention relates to the technical field of machine learning, in particular to a face tracking method and a camera. Background technique [0002] Face alignment is to detect faces in the image and label each specific point. Face alignment technology is often used in video processing, such as live broadcast, short video and other applications. [0003] The real-time tracking of face alignment is of great help to video processing. However, the current research on face alignment is more enthusiastic, and the research on real-time tracking of face alignment is less, and the points determined by most tracking algorithms are in the There is jitter between frames, which makes the tracking results obviously distorted. Contents of the invention [0004] The present invention provides a face tracking method and camera to at least partly solve the above problems. [0005] In a first aspect, the present invention provides a face tracking method, comprisin...

AI Technical Summary

Problems solved by technology

[0003] The real-time tracking of face alignment is of great help to video processing. However, the current research on face alignment is relatively enthusiastic, and there are few studies on real-time tracking of face alignment. Moreover, the points determined by most tracking algorithms are in the There is jitter between frames, which makes the tracking results obviously distorted

Images