People recognition and pose estimation in image sequences

Author

Nakajima, Chikahito ; Pontil, Massimiliano ; Poggio, Tomaso

Author_Institution

Central Res. Inst., Electr. Power Dev. Co. Ltd., Tokyo, Japan

Volume

4

fYear

2000

fDate

2000

Firstpage

189

Abstract

Presents a system which learns from examples to automatically recognize people and estimate their poses in image sequences with the potential application to daily surveillance in indoor environments. The person in the image is represented by a set of features based on color and shape information. Recognition is carried out through a hierarchy of biclass SVM classifiers that are separately trained to recognize people and estimate their poses. The system shows a very high accuracy in people recognition and about 85% level of performance in pose estimation, outperforming in both cases k-nearest neighbors classifiers. The system works in real time

Keywords

feature extraction; graph theory; image classification; image colour analysis; image recognition; image sequences; learning systems; neural nets; surveillance; biclass SVM classifiers; color information; daily surveillance; indoor environments; people recognition; pose estimation; shape information; support vector machines; Cameras; Feature extraction; Filters; Image recognition; Image sequences; Indoor environments; Shape; Support vector machine classification; Support vector machines; Surveillance;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2000. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on

Conference_Location

Como

ISSN

1098-7576

Print_ISBN

0-7695-0619-4

Type

conf

DOI

10.1109/IJCNN.2000.860771

Filename

860771