Video sequence learning and recognition via dynamic SOM

Qiong Liu, Yong Rui, Thomas Huang, Stephen Levinson

Research output: Contribution to conferencePaperpeer-review


Information contained in the video sequences is crucial for an autonomous robot or a computer to learn and respond to its surrounding environment. In the past, robot vision is 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 on 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.

Original languageEnglish (US)
Number of pages5
StatePublished - 1999
EventInternational Conference on Image Processing (ICIP'99) - Kobe, Jpn
Duration: Oct 24 1999Oct 28 1999


OtherInternational Conference on Image Processing (ICIP'99)
CityKobe, Jpn

ASJC Scopus subject areas

  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering


Dive into the research topics of 'Video sequence learning and recognition via dynamic SOM'. Together they form a unique fingerprint.

Cite this