A real time human face tracking method and a system based on spatio-temporal context learning

A space-time context and context technology, applied in the field of face tracking, can solve problems such as drift easily, and achieve the effect of improving correct update ability and robustness

Inactive Publication Date: 2015-09-23
SOUTHWEST CHINA RES INST OF ELECTRONICS EQUIP
View PDF3 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the technical problem that the tracking method in the prior art tends to drift during long-term tracking, the present invention discloses a real-time face tracking method based on spatio-temporal context learning

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
  • A real time human face tracking method and a system based on spatio-temporal context learning
  • A real time human face tracking method and a system based on spatio-temporal context learning
  • A real time human face tracking method and a system based on spatio-temporal context learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0015] The specific implementation manners of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0016] The invention discloses a real-time face tracking method based on spatio-temporal context learning, which specifically includes the following steps: Step 1, initial frame face detection and target face determination: all people in the initial frame are detected by a face detector The position of the face, and the determined target face position is passed to the tracker, and the tracking is started; Step 2, historical frame information learning and module update: starting from the second frame, for the nth frame, where n>1, the learning modules are respectively Complete the update of the tracker and the update of the effector; the update of the tracker refers to the update of the spatio-temporal context model, and the spatio-temporal context model refers to the use of temporal context information and spatial local context i...

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 invention relates to the technical field of computer vision processing, and discloses a real time human face tracking method and a system based on spatio-temporal context learning. The method specifically comprises the following steps: Step 1, initial frame human face detecting and target human face determining; obtaining positions of all the human faces in an initial frame through a human face detector and transmitting determined target human face positions to a tracker to begin tracking; Step 2, historical frame information learning and module updating; Step 3, present frame candidate target human face determining; and Step 4, present frame target position determining: from the second frame, for the n frame (n>1), a candidate target human face is mixed with an updated tracking result to obtain the final position of the human face in the present frame. The tracker and an effect determining device are updated through the above method so as to enable effective combination of the tracking and the human face detection result in a framework of learning. The tracking is enabled to be adapted to problems facing long-time tracking. Simultaneously, problems of tracking drift or failures due to interference human faces are solved.

Description

technical field [0001] The invention relates to the technical field of face tracking, and discloses a real-time face tracking method and system based on spatio-temporal context learning. Background technique [0002] Face tracking includes feature matching based tracking, region matching based tracking and model matching based tracking. Tracking based on feature matching: select the face in a frame of image as the face to be tracked, and extract the features that need to be tracked, and extract the image features in the next frame of the sequence image, and extract the current frame The image features of the image are compared with the face features that need to be tracked, and whether it is the corresponding face is judged according to the comparison result, so as to complete the tracking process. Such methods can lead to tracking failure due to occlusion or light changes. Tracking based on area matching: This method uses the common feature information of the connected ar...

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 Applications(China)
IPC IPC(8): G06T7/20
CPCG06T7/207G06T2207/20081G06T2207/30196
Inventor 吴佳芸
Owner SOUTHWEST CHINA RES INST OF ELECTRONICS EQUIP
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