Unlock instant, AI-driven research and patent intelligence for your innovation.

Method for quickly and accurately detecting and tracking human face based on video sequence

A face detection and video sequence technology, applied in the field of pattern recognition, can solve the problems of face detection speed and other problems, achieve fast calculation speed, accurate tracking, and improve the detection speed

Inactive Publication Date: 2013-01-16
云南清眸科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0012] The technical problems to be solved in the present invention are: 1) solve the face detection speed problem in each frame video image in the video sequence, promptly adopt the strategy that reduces detection area to improve the speed of face detection, make based on the face detection tracking of video sequence Real-time application becomes possible; 2) Solve the problem of face detection accuracy in each frame of video image in the video sequence, that is, perform face detection on the skin color area through the improved cascaded AdaBoost classifier, so that the face detection and tracking based on the video sequence 3) It solves the problem of fast face tracking in video sequences, that is, proposes an efficient Gaussian model strategy based on face region features to match and track detected faces, and completes the face tracking Real-time tracking of the sequence; 4) Solved the tracking problem of face crossing in the video sequence, that is, for the detected face, the face contour shape feature is established, and the matching judgment is only performed when the face area crosses in the video sequence, and the completion Face-based multi-person tracking in the same video sequence

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 quickly and accurately detecting and tracking human face based on video sequence
  • Method for quickly and accurately detecting and tracking human face based on video sequence
  • Method for quickly and accurately detecting and tracking human face based on video sequence

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] figure 1 Shown is a schematic diagram of the processing process of the method of the present invention. For the video stream data, the method of the present invention first extracts the video frame images in the video stream data; preprocesses the video frame images to obtain the face area to be detected; Face detection is performed on the area to be detected to obtain the face area; if the face area is obtained, the features of the detected face need to be extracted, including the face area feature and the face shape feature; the face is tracked according to the extracted feature ; Finally, the face image sequence of the same person is extracted according to the face queue established by the face tracking, and the face detection and tracking based on the video sequence is completed.

Embodiment 2

[0043] figure 2 This is a flow chart of the present invention, which is a fast and accurate face detection and tracking method based on video sequences. The specific flow chart is described as follows:

[0044] 1) For the video stream sequence, first extract each frame of video image for processing.

[0045] 2) Perform light compensation for the video frame image in advance, the specific method is the "reference white" method to linearly adjust the image color histogram, so as to perform illumination compensation on the image, that is, perform the brightness of all pixels in the entire image from high to low Sort, take the top 5% of the pixels. If the number of these pixels is large enough, use their brightness as the "reference white", that is, adjust the R, G, and B component values ​​of their colors to the maximum 255. For other pixels The linear adjustment formula is:

[0046] I i ′ ( x , y ) I i ( x , y ) - ref B i ref ...

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 quickly and accurately detecting and tracking a human face based on a video sequence, which relates to the technical field of mode identification. The method comprises the following steps of: 1, extracting a video frame image from a video stream; 2, preprocessing the video frame image, namely compensating light rays, extracting skin color areas, performing morphological processing and combining the areas; 3, detecting the human face, namely representing the human face by using Harr-like characteristics and detecting the human face by using a cascaded Adaboost algorithm with an assistant decision function; 4, establishing the characteristics of the human face, namely detecting the area characteristics of the detected human face and the shape characteristics of the edge profile of the human face; 5, tracking the human face, particularly tracking the human face by using a human face area characteristic model when an intersection does not occur in a human face area, and further matching when the intersection occurs according to the shape characteristics of the edge profile of the human face; and 6, extracting the sequence of a human face image. By the technical method, the human face can be detected and tracked quickly and accurately on the basis of the video sequence.

Description

(1) Technical field [0001] The invention relates to the technical field of pattern recognition, and relates to a fast and accurate face detection and tracking method based on video sequences. (2) Background technology [0002] The problem of face detection originated from face recognition. Initially, face research was mainly focused on the field of face recognition, and early face recognition algorithms were carried out on the premise that a frontal face has been obtained or the face is easily obtained. However, with the continuous expansion of the application range of human face and the continuous improvement of the actual system development requirements, research under this assumption can no longer meet the demand. Face detection began to develop as an independent research content. [0003] Today, the application background of face detection has gone far beyond the scope of face recognition systems, and has important application value in content-based retrieval, digital video p...

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): G06K9/00G06K9/64
Inventor 刘辉
Owner 云南清眸科技有限公司