Head posture estimation method based on depth information and color image

Abstract

The invention discloses a head posture estimation method based on depth information and a color image. The method comprises the steps of firstly utilizing a histogram projection method to quickly position a head position in a depth information grey-scale map; then utilizing skin color detection algorithm to eliminate hair noise and clothes noise except the skin in the head area in a color image; utilizing a camera imaging principle to normalize the head area resolution, and homogenizing the depth information grey-scale map; and finally extracting a section regional geometric vector set from the obtained normalized grey-scale map to describe the variation rule of the head posture. According to the features of the depth information grey-scale map, the geometric feature of a face and particularly the symmetrical characteristics of the face about a nose tip, a novel head posture description characteristic code is designed, the head posture is estimated by utilizing a random forest regression machine, and the method has the advantages of good real-time property, high precision, high robustness and high reliability and can be widely applied to the application fields such as human face recognition and human-machine interaction.

Description

technical field [0001] The invention relates to the technical fields of digital image processing, pattern recognition and statistical learning, in particular to a head pose estimation method based on depth information and color images. Background technique [0002] Since the 1950s, the emergence of computer technology has greatly changed the way of human production and life. At the same time, the increasing needs of human beings also promote the rapid development of computer technology. With the advancement of society, computer technology based on the traditional input methods of keyboard and mouse can no longer meet the needs of people's lives. People call for a vision-based intelligent interaction technology, which allows machines to grasp human posture or actions and then Understand people's intentions. One of the important research topics in the field of intelligent interaction - head pose estimation, has a wide range of applications in face recognition, viewpoint trac...

AI Technical Summary

Problems solved by technology

For example, the literature M.D.Breitenstein, D.Kuettel, T.Weise, L. Van Gool, H.Pfister, Real-time face pose estimation from single range images, IEEE Conference on Computer Vision and Pattern Recognition, 2008, proposed a single-based A real-time head pose estimation system for a depth information map, the system can estimate an accuracy of 80.8% within a 10-degree error range, but it requires GPU assistance and has limited applications

Literature G.Fanelli, J.Gall, L. Van Gool, Real Time Head Pose Estimation with Random Regression Forests, IEEE Conference on Computer Vision and Pattern Recognition, 2011, also proposed a real-time head based on a single depth information map Pose estimation system, which uses the fast and efficient random forest to meet real-time application requirements. The estimation accuracy within 10 degrees error range can reach 90.4%. It can estimate the head posture more accurately, but the estimation accuracy still has a large gap. room for improvement

Images