Information contained in video sequences is crucial
for an autonomous robot or a computer to learn and
respond to its surrounding environment. In the past,
robot vision mainly concentrated on still image
processing and small “image cube”
processing. Continuous video sequence learning and
recognition is rarely addressed in the literature due
to its high requirement of dynamic processing. In this
paper, we propose a novel neural network structure
called dynamic self-organizing map (DSOM) for video
sequence processing. The proposed technique has been
tested on simulation data sets, and the results
validate its learning/recognition ability
%0 Conference Paper
%1 liu-video-dynamic-som-1999
%A Liu, Qiong
%A Rui, Yong
%A Huang, T.
%A Levinson, S.
%B Image Processing, 1999. ICIP 99. Proceedings. 1999
International Conference on
%D 1999
%K dynamic kohonen learning som
%P 93--97 vol.4
%R 10.1109/ICIP.1999.819526
%T Video sequence learning and recognition via dynamic
SOM
%U http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=819526
%V 4
%X Information contained in video sequences is crucial
for an autonomous robot or a computer to learn and
respond to its surrounding environment. In the past,
robot vision mainly concentrated on still image
processing and small “image cube”
processing. Continuous video sequence learning and
recognition is rarely addressed in the literature due
to its high requirement of dynamic processing. In this
paper, we propose a novel neural network structure
called dynamic self-organizing map (DSOM) for video
sequence processing. The proposed technique has been
tested on simulation data sets, and the results
validate its learning/recognition ability
@inproceedings{liu-video-dynamic-som-1999,
abstract = {Information contained in video sequences is crucial
for an autonomous robot or a computer to learn and
respond to its surrounding environment. In the past,
robot vision mainly concentrated on still image
processing and small “image cube”
processing. Continuous video sequence learning and
recognition is rarely addressed in the literature due
to its high requirement of dynamic processing. In this
paper, we propose a novel neural network structure
called dynamic self-organizing map (DSOM) for video
sequence processing. The proposed technique has been
tested on simulation data sets, and the results
validate its learning/recognition ability},
added-at = {2013-06-25T11:52:07.000+0200},
author = {Liu, Qiong and Rui, Yong and Huang, T. and Levinson, S.},
biburl = {https://www.bibsonomy.org/bibtex/274f3d5618fbd65a49b863982ff5af247/mhwombat},
booktitle = {Image Processing, 1999. ICIP 99. Proceedings. 1999
International Conference on},
doi = {10.1109/ICIP.1999.819526},
interhash = {1c1a6948ee4d2502cb90264f4b4a816a},
intrahash = {74f3d5618fbd65a49b863982ff5af247},
keywords = {dynamic kohonen learning som},
pages = {93--97 vol.4},
timestamp = {2016-07-12T19:25:30.000+0200},
title = {Video sequence learning and recognition via dynamic
{SOM}},
url = {http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=819526},
volume = 4,
year = 1999
}