Human face key point tracking method and apparatus

A face key point and confidence technology, applied in the communication field, can solve the problems of low processing efficiency, multiple resources, time-consuming face detection algorithm, etc., to reduce resource consumption, reduce detection time, and realize real-time calculation Effect

Active Publication Date: 2017-05-31
TENCENT TECH SHANGHAI
View PDF4 Cites 46 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] During the research and practice of the prior art, the inventors of the present invention found that, in the existing solution, since the face detection algorithm adopted is relativ

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
  • Human face key point tracking method and apparatus
  • Human face key point tracking method and apparatus
  • Human face key point tracking method and apparatus

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0029] This embodiment will be described from the perspective of a human face key point tracking device. The human face key point tracking device may be integrated into a mobile terminal and other devices. The mobile terminal may include a mobile phone, a tablet computer, or a smart wearable device.

[0030] A method for tracking key points of a human face, comprising: obtaining an image currently to be processed in a video stream, obtaining a current frame, obtaining the coordinates of key points of the human face of the previous frame image of the current frame, and the human face of the previous frame image Confidence of the key point coordinates, when the confidence is higher than the preset threshold, the face key point coordinates of the current frame are calculated according to the face key point coordinates of the previous frame image, and the face key point coordinates of the current frame are compared to the current frame. The frame performs multi-face recognition, an...

Embodiment 2

[0066] According to the method described in Embodiment 1, the following examples will be used for further detailed description

[0067] In this embodiment, description will be made by taking the device for tracking key points of a human face being integrated in a mobile terminal as an example.

[0068] Such as figure 2 As shown, a face key point tracking method, the specific process can be as follows:

[0069] 200. The mobile terminal receives the video stream.

[0070] For example, the mobile terminal may specifically receive video streams sent by other devices, or acquire video streams from local storage space, and so on.

[0071] 201. The mobile terminal acquires an image to be processed currently in a video stream, and obtains a current frame.

[0072] 202. The mobile terminal acquires the coordinates of the key points of the human face in the previous frame of the current frame, and the confidence of the coordinates of the key points of the human face in the previous ...

Embodiment 3

[0123] In order to better implement the above method, the embodiment of the present invention also provides a human face key point tracking device, such as Figure 3a As shown, the face key point tracking device includes an image acquisition unit 301, a parameter acquisition unit 302, a computing unit 303 and a processing unit 304, as follows:

[0124] (1) image acquisition unit 301;

[0125] An image acquisition unit 301, configured to acquire an image currently to be processed in the video stream to obtain a current frame;

[0126] For example, the image acquiring unit 301 may be specifically configured to acquire a video stream from a local or other device, and then determine an image currently to be processed from the video stream to obtain a current frame.

[0127] (2) parameter acquisition unit 302;

[0128] The parameter acquiring unit 302 is configured to acquire the coordinates of key points of the human face in the previous frame image of the current frame, and 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

Embodiments of the invention disclose a human face key point tracking method and apparatus. The method comprises the steps of obtaining human face key point coordinates and a confidence degree of a previous frame of image to calculate human face key point coordinates of a current frame; and then, performing multi-human face identification on the current frame according to the human face key point coordinates of the current frame, calculating a corresponding confidence degree of the current frame for reference by a next frame of image, and circulating the process until all images in a video stream are identified, so that the purpose of tracking human face key points in the video stream in real time is achieved. According to the scheme, the detection time can be greatly shortened, the processing efficiency can be improved, the resource consumption can be reduced, and real-time calculation can be realized at a mobile terminal.

Description

technical field [0001] The invention relates to the field of communication technology, in particular to a method and device for tracking key points of a human face. Background technique [0002] With the rapid development of computer and image processing technology, face recognition technology has also made great progress; face recognition can not only be used in image processing, but also can be applied in fields such as identification, therefore, in recent years , Face recognition has also been a hot research topic. [0003] The detection of facial key points is the basis of face recognition. In order to accurately identify the faces in the video stream, it is necessary to track the key points of each face in the video stream. The so-called face key points refer to information that can reflect the features of the face, such as eyes, eyebrows, nose, mouth, and the outline of the face. In the prior art, the frame-by-frame face detection method is generally used to track th...

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): G06K9/00
CPCG06V40/167G06V40/171G06V40/172G06V20/40
Inventor 汪铖杰倪辉赵艳丹王亚彪丁守鸿李绍欣赵凌李季檩吴永坚黄飞跃梁亦聪
Owner TENCENT TECH SHANGHAI
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap