Comparing active vision models

被引:11
作者
de Croon, G. C. H. E. [1 ]
Sprinkhuizen-Kuyper, I. G. [2 ]
Postma, E. O. [3 ]
机构
[1] Delft Univ Technol, Aerosp Engn Aerosp Software & Technol Inst, NL-2600 GB Delft, Netherlands
[2] Radboud Univ Nijmegen, Nijmegen Inst Cognit & Informat, NL-6500 HE Nijmegen, Netherlands
[3] Maastricht Univ, Fac Gen Sci, Dept Comp Sci, NL-6200 MD Maastricht, Netherlands
关键词
Active vision; Probabilistic approach; Behavioural approach; OBJECT RECOGNITION;
D O I
10.1016/j.imavis.2008.06.004
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Active vision models can simplify visual tasks, provided that they can select sensible actions given incoming sensory inputs. Many active vision models have been proposed, but a comparative evaluation of these models is lacking. We present a comparison of active vision models from two different approaches. The "probabilistic approach" is an approach in which state estimation is the central goal. The "behavioural approach" is an approach that does not divide the vision process in a state estimation and an acting phase. We identify different types of models of the probabilistic approach, and introduce a model inspired on the behavioural approach. We describe these types of models in a common framework and evaluate their performances on a task of viewpoint selection for the classification of three-dimensional objects. The experimental results reveal how the performances of the active vision models relate to each other. For example, the behavioural model performs as good as the best model from the probabilistic approach. Overall, the experimental results reveal relations between the usefulness of active vision, the number of objects involved in the classification task, and the richness of the visual observations of the models. We conclude that research on active vision should aim at reaching a deeper understanding of these relations by applying active vision models to more complex and real-world tasks. (C) 2008 Elsevier B.V. All rights reserved.
引用
收藏
页码:374 / 384
页数:11
相关论文
共 30 条
[1]  
Aloimonos J., 1987, International Journal of Computer Vision, V1, P333, DOI 10.1007/BF00133571
[2]   Entropy-based gaze planning [J].
Arbel, T ;
Ferrie, FP .
IMAGE AND VISION COMPUTING, 2001, 19 (11) :779-786
[3]  
Back T., 1996, Evolutionary Algorithms in Theory and Practice
[4]   ANIMATE VISION [J].
BALLARD, DH .
ARTIFICIAL INTELLIGENCE, 1991, 48 (01) :57-86
[5]   The dynamics of active categorical perception in an evolved model agent [J].
Beer, RD .
ADAPTIVE BEHAVIOR, 2003, 11 (04) :209-243
[6]   A comparison of probabilistic, possibilistic and evidence theoretic fusion schemes for active object recognition [J].
Borotschnig, H ;
Paletta, L ;
Prantl, M ;
Pinz, A .
COMPUTING, 1999, 62 (04) :293-319
[7]   Appearance-based active object recognition [J].
Borotschnig, H ;
Paletta, L ;
Prantl, M ;
Pinz, A .
IMAGE AND VISION COMPUTING, 2000, 18 (09) :715-727
[8]  
Cohen P.R., 2016, Empirical Methods for Artificial Intelligence, V11, P88
[9]  
Cover T.M., 1991, Wiley series in telecommunications
[10]   A situated model for sensory-motor coordination in gaze control [J].
de Croon, G. ;
Postma, E. O. ;
van den Herik, H. J. .
PATTERN RECOGNITION LETTERS, 2006, 27 (11) :1181-1190