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

Inter-frame information oriented head gesture estimation optimization method

A head posture and optimization method technology, applied in the field of face image processing and analysis, can solve the problems of slow video stream speed and poor accuracy, and achieve the effect of improving detection speed, improving robustness, and improving face detection speed

Inactive Publication Date: 2018-10-26
ZHEJIANG UNIV
View PDF6 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the above-mentioned deficiencies in the prior art, the present invention proposes an inter-frame information-oriented head pose estimation optimization method to solve the problems of slow speed and poor accuracy of traditional head pose estimation methods when processing video streams

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
  • Inter-frame information oriented head gesture estimation optimization method
  • Inter-frame information oriented head gesture estimation optimization method
  • Inter-frame information oriented head gesture estimation optimization method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] Hereinafter, the present invention will be described in more detail with reference to the accompanying drawings. These examples are only descriptions of the best embodiments of the present invention, and do not limit the scope of the present invention in any way. Such as figure 1 As shown, the main process of the inventive method is divided into 3 parts:

[0017] 1) Face detection: The face detection algorithm based on HOG features is mainly divided into six steps: normalization of color space, gradient calculation, HOG statistics of cell units, normalization of overlapping block features, sliding window detection, linear SVM classification device identification. In the sliding window step, if the entire image is searched and detected, it will consume a lot of computing time, but in fact, the displacement of the head between two adjacent frames is almost small, so the face detected in the previous adjacent frame can be The position is the center, and a certain propor...

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 an inter-frame information oriented head gesture estimation optimization method. The method comprises three steps of face detection, face alignment and parameter estimation. During face detection, according to the face position information of a previous adjacent frame, an area to be detected is reduced, and face detection speed is improved; during face alignment, accordingto whether the head gesture of the previous adjacent frame is subjected to overlarge deflection or not, feature points which are positioned on the edge of a face contour to cause inaccurate positioning are removed so as to improve robustness; and during parameter estimation, the similarity of the parameter in previous and rear frames is used for simplifying a solving process, and a direct linear transformation step is omitted. By use of the method disclosed by the invention, on a premise that a complex operation is not increased, the accuracy and the instantaneity of a traditional head gestureestimation method are optimized, and a support is provided for the method to be combined with other relevant technologies to realize rich application.

Description

technical field [0001] The invention relates to an inter-frame information-oriented head pose estimation and optimization method, which is used in the field of face image processing and analysis in video streams. Background technique [0002] Head pose estimation is a research hotspot in the intersection of machine vision and human-computer interaction. Usually, the three-dimensional pose corresponding to the head is estimated from the two-dimensional face image, which can be described by three Euler angles. Accurate attitude values ​​can be obtained with professional head-mounted sensing devices, but there are disadvantages such as complicated operation and inconvenient portability. The head pose estimation method based on machine vision processing technology does not have the disadvantages of the above methods, and can be transplanted on smart devices equipped with cameras. The operation is simple, and it can be applied to face-assisted recognition, driver fatigue detectio...

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): G06T7/73G06K9/00
CPCG06T7/75G06T2207/30201G06T2207/10016G06V40/16G06V40/161
Inventor 沈海斌于学峰
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