Democratic integration: Self-organized integration of adaptive cues

被引:136
作者
Triesch, J [1 ]
von der Malsburg, C
机构
[1] Univ Rochester, Dept Comp Sci, Rochester, NY 14627 USA
[2] Univ So Calif, Lab Computat & Biol Vis, Los Angeles, CA USA
[3] Ruhr Univ Bochum, Inst Neuroinformat, D-4630 Bochum, Germany
关键词
D O I
10.1162/089976601750399308
中图分类号
TP18 [人工智能理论];
学科分类号
081104 [模式识别与智能系统]; 0812 [计算机科学与技术]; 0835 [软件工程]; 1405 [智能科学与技术];
摘要
Sensory integration or sensor fusion-the integration of information from different modalities, cues, or sensors-is among the most fundamental problems of perception in biological and artificial systems. We propose a new architecture for adaptively integrating different cues in a self-organized manner. In Democratic Integration different cues agree on a result, and each cue adapts toward the result agreed on. In particular, discordant cues are quickly suppressed and recalibrated, while cues having been consistent with the result in the recent past are given a higher weight in the future. The architecture is tested in a face tracking scenario. Experiments show its robustness with respect to sudden changes in the environment as long as the changes disrupt only a minority of cues at the same time, although all cues may be disrupted at one time or another.
引用
收藏
页码:2049 / 2074
页数:26
相关论文
共 28 条
[1]
[Anonymous], PERCEPTION ESSAYS HO
[2]
Experience-dependent visual cue integration based on consistencies between visual and haptic percepts [J].
Atkins, JE ;
Fiser, J ;
Jacobs, RA .
VISION RESEARCH, 2001, 41 (04) :449-461
[3]
User localisation for visually-based human-machine-interaction [J].
Boehme, HJ ;
Braumann, UD ;
Brakensiek, A ;
Corradini, A ;
Krabbes, M ;
Gross, HM .
AUTOMATIC FACE AND GESTURE RECOGNITION - THIRD IEEE INTERNATIONAL CONFERENCE PROCEEDINGS, 1998, :486-491
[4]
Sensor fusion potential exploitation - Innovative architectures and illustrative applications [J].
Dasarathy, BV .
PROCEEDINGS OF THE IEEE, 1997, 85 (01) :24-38
[5]
DESA VR, 1998, NEURAL COMPUTATION, V10
[6]
DESA VR, 1994, THESIS U ROCHESTER N
[7]
Touch can change visual slant perception [J].
Ernst, MO ;
Banks, MS ;
Bülthoff, HH .
NATURE NEUROSCIENCE, 2000, 3 (01) :69-73
[8]
FEYRER S, 1998, DYNAMISCHE PERZEPTIO, P183
[9]
Modeling the combination of motion, stereo, and vergence angle cues to visual depth [J].
Fine, I ;
Jacobs, RA .
NEURAL COMPUTATION, 1999, 11 (06) :1297-1330
[10]
Gonzales R.C., 1992, DIGITAL IMAGE PROCES