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

Face Tracking Method Based on Classification Recognition

A technology of classification recognition and face sequence, applied in the field of face tracking, can solve problems affecting system burden and processing speed, system blockage, large amount of calculation, etc., to achieve the effect of increasing practical application value, improving function, and simple calculation

Active Publication Date: 2012-02-01
GUANGZHOU NEWTEMPO TECH
View PDF2 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

A disadvantage of this is that every face that appears in each frame has to be compared with the database template once, and the calculation of the comparison part is relatively large, especially when the number of target templates is large, the comparison part The overhead will directly affect the burden and processing speed of the system, making the system hindered in practical applications

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
  • Face Tracking Method Based on Classification Recognition
  • Face Tracking Method Based on Classification Recognition
  • Face Tracking Method Based on Classification Recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0036] The present invention is based on the face tracking method of classification recognition, and the algorithm flow of its implementation process is as follows figure 1 As shown, the implementation steps are as follows:

[0037] (1) Establish a basic face tracking system based on the CAMShift algorithm. For details, see "Gary R. Bradski, 'Computer Vision Face Tracking For Use in a Perceptual User Interface', Intel Technology Journal Q2'98".

[0038] (2) The face sequence tracked from the current frame Intercept the tracked face image, adjust the tracked face image in each frame to make it the same size, and save it to the face sequence to be matched The face sequence to be matched saved in the previous frame is The corresponding timer is {C 1 , C 2 ......C j} (The timer is used to record the number of frames that the face target does not appear in a row. When the target appears, the timer is cleared. When the timer exceeds the maximum allowable value, it is judged ...

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 present invention provides a face tracking method with classification recognition function, including step (1) the sequence to be matched in the current frame is {F1C, F2C...FjC}; the sequence in the previous frame is {F1L, F2L.. ....FjL}; (2) Take out the FmC of the current frame in turn to calculate its LBP coded map; (3) After getting the LBP coded map, compare it with the LBP coded map of the previous frame to find out the FnL with the highest matching degree with FmC (4) judge whether it is the same person according to the degree of matching, center position distance relationship; if the face images of the same person are classified into the same class, if not add Fj+1L=FmC in the FL sequence; (5) repeat (two )-(4), until the sequence to be matched in the current frame is traversed; (6) get back to the (1) step to process the next frame. The invention adopts the LBP feature of the rotating unified mode to classify and judge the identity of the person, so that the faces of the same person are classified into one category, which solves the problem of information loss after the person is blocked in the traditional face tracking method, and expands the human face tracking method. The features of the face tracking system enhance its application value.

Description

technical field [0001] The invention relates to a method for human face tracking, in particular to a method for human face tracking in video. Background technique [0002] Face tracking technology has a wide range of practical applications in security monitoring, identification, virtual games, etc. However, the traditional face tracking methods still have some performance and functional deficiencies in practical applications. Especially for the situation where the same face appears intermittently (such as being blocked by obstacles or other faces for a few frames), due to the loss of intermediate tracking information, the color-based tracking method will not be able to distinguish when the same person appears again and re-detect it. Whether the face is the same person as the face lost in previous tracking. [0003] In addition, in the application of real-time video security monitoring, the general practice is to compare all the face images tracked in each frame with all ta...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/48G06K9/00
Inventor 赖剑煌黎立宏黄剑
Owner GUANGZHOU NEWTEMPO TECH
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com