Abstract
In this paper, we propose a method to analyze and recognize human head movements from monocular image sequences based on few constraints. First, the background image photographed beforehand is used to extract the human region from the image sequence. Next, the skin-colored regions are extracted, and the low brightness and low saturation pixels are set as the candidate eye regions. Then the face region is determined from the multiple skin-colored regions and the hair region is extracted based on the face region. Finally, the left and right eye regions are determined from the candidate eye regions. Thus, effective information for posture estimation such as the eye positions, face region, and hair region is extracted from the input image. A genetic algorithm (GA) is applied to fit the extracted information to a 3D head model and estimate the head posture. By creating an approximate 3D head model, the system adapts to an indeterminate large number of humans. Since an image sequence is input, the information in the previous image can be used. Thus, the possible human movements and the angles of the joints are a priori knowledge and are reflected in the parameters. The lack of information for the 3D posture estimation problem from a monocular image sequence is alleviated.
| Original language | English |
|---|---|
| Pages (from-to) | 36-45 |
| Number of pages | 10 |
| Journal | Systems and Computers in Japan |
| Volume | 32 |
| Issue number | 5 |
| DOIs | |
| Publication status | Published - 2001 May |
Fingerprint
Keywords
- Genetic algorithms
- Head motion
- Image recognition
- Monocular view
ASJC Scopus subject areas
- Computational Theory and Mathematics
- Hardware and Architecture
- Information Systems
- Theoretical Computer Science
Cite this
Analysis and Recognition of a Human Head's Movement from an Image Sequence. / Abe, Yuichi; Hagiwara, Masafumi.
In: Systems and Computers in Japan, Vol. 32, No. 5, 05.2001, p. 36-45.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Analysis and Recognition of a Human Head's Movement from an Image Sequence
AU - Abe, Yuichi
AU - Hagiwara, Masafumi
PY - 2001/5
Y1 - 2001/5
N2 - In this paper, we propose a method to analyze and recognize human head movements from monocular image sequences based on few constraints. First, the background image photographed beforehand is used to extract the human region from the image sequence. Next, the skin-colored regions are extracted, and the low brightness and low saturation pixels are set as the candidate eye regions. Then the face region is determined from the multiple skin-colored regions and the hair region is extracted based on the face region. Finally, the left and right eye regions are determined from the candidate eye regions. Thus, effective information for posture estimation such as the eye positions, face region, and hair region is extracted from the input image. A genetic algorithm (GA) is applied to fit the extracted information to a 3D head model and estimate the head posture. By creating an approximate 3D head model, the system adapts to an indeterminate large number of humans. Since an image sequence is input, the information in the previous image can be used. Thus, the possible human movements and the angles of the joints are a priori knowledge and are reflected in the parameters. The lack of information for the 3D posture estimation problem from a monocular image sequence is alleviated.
AB - In this paper, we propose a method to analyze and recognize human head movements from monocular image sequences based on few constraints. First, the background image photographed beforehand is used to extract the human region from the image sequence. Next, the skin-colored regions are extracted, and the low brightness and low saturation pixels are set as the candidate eye regions. Then the face region is determined from the multiple skin-colored regions and the hair region is extracted based on the face region. Finally, the left and right eye regions are determined from the candidate eye regions. Thus, effective information for posture estimation such as the eye positions, face region, and hair region is extracted from the input image. A genetic algorithm (GA) is applied to fit the extracted information to a 3D head model and estimate the head posture. By creating an approximate 3D head model, the system adapts to an indeterminate large number of humans. Since an image sequence is input, the information in the previous image can be used. Thus, the possible human movements and the angles of the joints are a priori knowledge and are reflected in the parameters. The lack of information for the 3D posture estimation problem from a monocular image sequence is alleviated.
KW - Genetic algorithms
KW - Head motion
KW - Image recognition
KW - Monocular view
UR - http://www.scopus.com/inward/record.url?scp=0042333466&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0042333466&partnerID=8YFLogxK
U2 - 10.1002/scj.1024
DO - 10.1002/scj.1024
M3 - Article
AN - SCOPUS:0042333466
VL - 32
SP - 36
EP - 45
JO - Systems and Computers in Japan
JF - Systems and Computers in Japan
SN - 0882-1666
IS - 5
ER -