Detail publikace
On-line human action detection using space-time interest points
ŘEZNÍČEK, I. ZEMČÍK, P.
Originální název
On-line human action detection using space-time interest points
Anglický název
On-line human action detection using space-time interest points
Jazyk
en
Originální abstrakt
The on-line human action detection is an important task in human-machine interaction and related applications. One of the possible approaches to the detection is exploitation of space-time interest points. Such points are typically identied using feature extractor and then they are processed and classified. The classification can be performed using codebooks built based on feature vectors statistics. The individual feature vectors are transformed into bag of words representation using such codebooks and then the code words are classied using SVM. The proposed approach improves the training process and extends the known approaches. The training part of the dataset is split into shorter shots with equal duration and these are annotated and classied using a SVM classier. This ensures that the time-local motion is captured by the SVM while the longer time behavior is left on further processing mechanisms, such as, e.g. HMMs. In the proposed approach, the output of the SVM classier is simply compared to a threshold and the presence of a value above the threshold indicates that the desired human activity occurred. The contribution describes the approach summarizes the achieved results and draws conclusions.
Anglický abstrakt
The on-line human action detection is an important task in human-machine interaction and related applications. One of the possible approaches to the detection is exploitation of space-time interest points. Such points are typically identied using feature extractor and then they are processed and classified. The classification can be performed using codebooks built based on feature vectors statistics. The individual feature vectors are transformed into bag of words representation using such codebooks and then the code words are classied using SVM. The proposed approach improves the training process and extends the known approaches. The training part of the dataset is split into shorter shots with equal duration and these are annotated and classied using a SVM classier. This ensures that the time-local motion is captured by the SVM while the longer time behavior is left on further processing mechanisms, such as, e.g. HMMs. In the proposed approach, the output of the SVM classier is simply compared to a threshold and the presence of a value above the threshold indicates that the desired human activity occurred. The contribution describes the approach summarizes the achieved results and draws conclusions.
Dokumenty
BibTex
@inproceedings{BUT76466,
author="Ivo {Řezníček} and Pavel {Zemčík}",
title="On-line human action detection using space-time interest points",
annote="The on-line human action detection is an important task in human-machine
interaction and related applications. One of the possible approaches to the
detection is exploitation of space-time interest points. Such points are
typically identied using feature extractor and then they are processed and
classified. The classification can be performed using codebooks built based on
feature vectors statistics. The individual feature vectors are transformed into
bag of words representation using such codebooks and then
the code words are classied using SVM. The proposed approach improves the
training process and extends the known approaches. The training part of the
dataset is split into shorter shots with equal duration and these are annotated
and classied using a SVM classier. This ensures that the time-local motion is
captured by the SVM while the longer time behavior is left on further processing
mechanisms, such as, e.g. HMMs. In the proposed approach, the
output of the SVM classier is simply compared to a threshold and the presence of
a value above the threshold indicates that the desired human activity occurred.
The contribution describes the approach summarizes the achieved results and draws
conclusions.",
address="Faculty of Mathematics and Physics, Charles University",
booktitle="Zborník príspevkov prezentovaných na konferencii ITAT, september 2011",
chapter="76466",
edition="NEUVEDEN",
howpublished="print",
institution="Faculty of Mathematics and Physics, Charles University",
year="2011",
month="september",
pages="39--45",
publisher="Faculty of Mathematics and Physics, Charles University",
type="conference paper"
}