RBF network methods for face detection and attentional frames

被引：15

作者：

Howell, AJ ^{[1
]}

Buxton, H ^{[1
]}

机构：

[1] Univ Sussex, Sch Cognit & Comp Sci, Brighton BN1 9QH, E Sussex, England

来源：

NEURAL PROCESSING LETTERS | 2002年 / 15卷 / 03期

关键词：

face detection; gesture recognition; head pose invariance; RBF networks; real-time vision applications; time-delay networks; visually mediated interaction;

D O I：

10.1023/A:1015743231018

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper we introduce a set of adaptive vision techniques which could be used, for example, in video-conferencing applications. First, we present methods for finding faces and selecting attentional frames to focus visual processing. Second, we present methods for recognising individual gesture phases for camera control. Finally, we discuss how these techniques can be extended to 'virtual groups' of multiple people interacting at multiple sites.

引用

页码：197 / 211

页数：15

共 29 条

[1]

[Anonymous], P BRIT MACH VIS C BM

[2] Movement, activity and action: The role of knowledge in the perception of motion [J].

Bobick, AF .

PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY OF LONDON SERIES B-BIOLOGICAL SCIENCES, 1997, 352 (1358) :1257-1265

[3] VISUAL SURVEILLANCE IN A DYNAMIC AND UNCERTAIN WORLD [J].

BUXTON, H ;

GONG, SG .

ARTIFICIAL INTELLIGENCE, 1995, 78 (1-2) :431-459

[4] View-based interpretation of real-time optical flow for gesture recognition [J].

Cutler, R ;

Turk, M .

AUTOMATIC FACE AND GESTURE RECOGNITION - THIRD IEEE INTERNATIONAL CONFERENCE PROCEEDINGS, 1998, :416-421

[5] COMPLETE DISCRETE 2-D GABOR TRANSFORMS BY NEURAL NETWORKS FOR IMAGE-ANALYSIS AND COMPRESSION [J].

DAUGMAN, JG .

IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1988, 36 (07) :1169-1179

[6] FINDING STRUCTURE IN TIME [J].

ELMAN, JL .

COGNITIVE SCIENCE, 1990, 14 (02) :179-211

[7] Recognising simple behaviours using time-delay RBF networks [J].

Howell, AJ ;

Buxton, H .

NEURAL PROCESSING LETTERS, 1997, 5 (02) :97-104

[8]

Howell AJ, 2001, STUD FUZZ SOFT COMP, V67, P103

[9] Learning identity with radial basis function networks [J].

Howell, AJ ;

Buxton, H .

NEUROCOMPUTING, 1998, 20 (1-3) :15-34

[10] Towards unconstrained face recognition from image sequences [J].

Howell, AJ ;

Buxton, H .

PROCEEDINGS OF THE SECOND INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION, 1996, :224-229

← 1 2 3 →