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

Method for rapidly detecting human face based on video

A face detection and video technology, applied in instruments, character and pattern recognition, computer parts and other directions, can solve the problem of not using the temporal and spatial correlation between video frames, avoid the defects of searching for full frames, and reduce the computational complexity , Improve the effect of real-time

Inactive Publication Date: 2009-01-21
ZHEJIANG UNIV
View PDF0 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But it does not take advantage of the temporal and spatial correlation between video frames, and its real-time performance needs to be further optimized for video surveillance 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
  • Method for rapidly detecting human face based on video
  • Method for rapidly detecting human face based on video
  • Method for rapidly detecting human face based on video

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The present invention will be further described below in conjunction with drawings and embodiments.

[0032] First, use the frame difference method to obtain the foreground of the video, and judge the change of the position and proportion of the foreground area; the foreground area is a rectangular area, with S f Indicates that the position of the foreground area defines the coordinates of the center point of the rectangle, represented by (x, y), the initialization value is 0, and the variable M x ,M y respectively represent the foreground area S f The position of the change in the two directions of x and y; assuming that in the Nth frame, the foreground area S f，N and defined as (x N ,y N ), then M x ,M y are defined as:

[0033] (M x ) N =X N -X N-1

[0034] (M y ) N =Y N -Y N-1

[0035] Foreground area S f The proportion in the video frame is F c Indicates that, assuming that in the Nth frame, the foreground area S f，N The proportion of which is d...

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 discloses a method for detecting human faces on the basis of video. The method comprises: concerning foreground areas in video frames, using the space-time domain characteristics between the video frames to detect the human faces of the foreground areas through preprocessing, dividing the human face detecting process into two different modes of an inspection mode and a tracking mode, switching a detecting flow to the inspection mode if the human faces can not be detected in the tracking mode or the tracking mode forecasts that the human faces which are tracked will escape a monitoring area in next frame, searching the foreground area wholly, and recollecting human face information of the monitoring area. The invention can reduce the region area which needs searching in the detecting process, can reduce areas which need searching in the detecting process, can avoid the defect that a traditional AdaBoost algorism searches full frames, can greatly lower the computational complexity, and can improve the real-time performance of human face detection in the intelligent video monitoring application.

Description

technical field [0001] The invention relates to the field of intelligent video monitoring, in particular to a video-based fast face detection method. Background technique [0002] Face detection, recognition and tracking are the first and key steps in intelligent video surveillance systems, and have broad and important application prospects in many application fields such as security identification, identity verification, content-based compression and retrieval, etc. Face detection is the first step in this task. For a long time, scientists and researchers have been working hard to find an algorithm that can detect faces quickly and accurately. [0003] Over the past few decades, researchers have proposed various methods to detect faces, some of which are based on gray level and color features; some use various feature templates to describe the local contour or global contour features of the face and detect human face. [0004] Most of the traditional face detection algori...

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
Inventor 卜佳俊陈纯高正华柏琦峰
Owner ZHEJIANG UNIV
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