Online computing of non-stationary distributions velocity fields by an accuracy controlled growing neural gas

被引：11
作者：
Frezza-Buet, Herve [1 ,2 ]
机构：
[1] Supelec, F-57070 Metz, France
[2] Georgia Tech Lorraine, UMI 2958, F-57070 Metz, France
来源：
NEURAL NETWORKS | 2014年 / 60卷
关键词：
Vector quantization; Growing neural gas; Velocity field; SELF-ORGANIZING NETWORK; ALGORITHM; TOPOLOGY;
D O I：
10.1016/j.neunet.2014.08.014
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
This paper presents a vector quantization process that can be applied online to a stream of inputs. It enables to set up and maintain a dynamical representation of the current information in the stream as a topology preserving graph of prototypical values, as well as a velocity field. The algorithm relies on the formulation of the accuracy of the quantization process, that allows for both the updating of the number of prototypes according to the stream evolution and the stabilization of the representation from which velocities can be extracted. A video processing application is presented. (C) 2014 Elsevier Ltd. All rights reserved.
引用
收藏
页码：203 / 221
页数：19
相关论文
共 26 条
[1]   An introduction to MCMC for machine learning [J].
Andrieu, C ;
de Freitas, N ;
Doucet, A ;
Jordan, MI .
MACHINE LEARNING, 2003, 50 (1-2) :5-43
[2]   A Database and Evaluation Methodology for Optical Flow [J].
Baker, Simon ;
Scharstein, Daniel ;
Lewis, J. P. ;
Roth, Stefan ;
Black, Michael J. ;
Szeliski, Richard .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2011, 92 (01) :1-31
[3]   Video shot motion characterization based on hierarchical overlapped growing neural gas networks [J].
Cao, X ;
Suganthan, PN .
MULTIMEDIA SYSTEMS, 2003, 9 (04) :378-385
[4]   A Survey of Optical Flow Techniques for Robotics Navigation Applications [J].
Chao, Haiyang ;
Gu, Yu ;
Napolitano, Marcello .
JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS, 2014, 73 (1-4) :361-372
[5]   An introduction to the anchoring problem [J].
Coradeschi, S ;
Saffiotti, A .
ROBOTICS AND AUTONOMOUS SYSTEMS, 2003, 43 (2-3) :85-96
[6]   Mapping the dimensionality, density and topology of data:: The growing adaptive neural gas [J].
Cselényi, Z .
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2005, 78 (02) :141-156
[7]   Two-frame motion estimation based on polynomial expansion [J].
Farnebäck, G .
IMAGE ANALYSIS, PROCEEDINGS, 2003, 2749 :363-370
[8]   Growing neural gas efficiently [J].
Fiser, Daniel ;
Faigl, Jan ;
Kulich, Miroslav .
NEUROCOMPUTING, 2013, 104 :72-82
[9]   Following non-stationary distributions by controlling the vector quantization accuracy of a growing neural gas network [J].
Frezza-Buet, Herve .
NEUROCOMPUTING, 2008, 71 (7-9) :1191-1202
[10]   GROWING GRID - A SELF-ORGANIZING NETWORK WITH CONSTANT NEIGHBORHOOD RANGE AND ADAPTATION STRENGTH [J].
FRITZKE, B .
NEURAL PROCESSING LETTERS, 1995, 2 (05) :9-13
123