User localisation for visually-based human-machine-interaction

被引：9

作者：

Boehme, HJ ^{[1
]}

Braumann, UD ^{[1
]}

Brakensiek, A ^{[1
]}

Corradini, A ^{[1
]}

Krabbes, M ^{[1
]}

Gross, HM ^{[1
]}

机构：

[1] Tech Univ Ilmenau, Dept Neuroinformat, D-98684 Ilmenau, Germany

来源：

AUTOMATIC FACE AND GESTURE RECOGNITION - THIRD IEEE INTERNATIONAL CONFERENCE PROCEEDINGS | 1998年

关键词：

D O I：

10.1109/AFGR.1998.670995

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Recently there is an increasing interest in video based interface techniques, allowing more natural interaction between users and systems than common interface devices do. Here, we present a neural architecture for user localisation, embedded within a complex system for visually-based human-machine-interaction (HMI). User's localisation is an absolute prerequisite to video-based HA II. Due to the main objective, the greatest possible robustness of the localisation as well as the whole visual interface under highly varying environmental conditions, we propose a multiple cue approach. This approach combines the features facial structure, head-shoulder-contour, skin color; and motion, with a multiscale representation. The selection of that image region most likely containing a possible user is then realised via a WTA-process within the multiscale representation. Preliminary results show the reliability of the multiple cue approach.

引用

页码：486 / 491

页数：2