DMCA
Visual Event Perception (1999)
| Venue: | In Proceedings of the NEC Research Symposium |
| Citations: | 8 - 1 self |
BibTeX
@INPROCEEDINGS{Siskind99visualevent,
author = {Jeffrey Mark Siskind},
title = {Visual Event Perception},
booktitle = {In Proceedings of the NEC Research Symposium},
year = {1999},
pages = {91--154},
publisher = {University Press}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
This paper presents a novel framework for training models to recognise simple spatial-motion events, such as those described by the verbs pick up, put down, push, pull, drop, tip, and tap and classifying novel observations into previously trained classes. Simple colour- and motionbased segmentation and tracking techniques are used to produce a time series of feature vectors constructed from the 2D object positions, orientations, shapes, and sizes. Hidden Markov models are trained on this time series data and used to classify novel occurrences into previously trained classes. The particular choice of features used allows the system to construct meaningful semantic representations of the event classes that it has learned. KEYWORDS: Event classification, Motion analysis, Segmentation, Tracking, Learning, Hidden Markov models, Lexical semantics 1 Introduction People can describe what they see. If I were to pick up a block and ask you what you saw, you could say Jeff picked up the...
Keyphrases
visual event perception hidden markov model novel observation time series data motion analysis event classification feature vector object position novel framework simple colour novel occurrence time series particular choice meaningful semantic representation simple spatial-motion event introduction people
