Recognition of group activities using dynamic probabilistic networks
Dynamic Probabilistic Networks (DPNs) are exploited for modelling the temporal relationships among a set of dif-ferent object temporal events in the scene for a coherent and robust scene-level behaviour interpretation. In particu-lar, we develop a Dynamically Multi-Linked Hidden Markov Model (DML-HM...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Text |
Language: | English |
Subjects: | |
Online Access: | http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.643.8247 http://www.eecs.qmul.ac.uk/~txiang/publications/gong-xiang-iccv03-cameraReady.pdf |
id |
ftciteseerx:oai:CiteSeerX.psu:10.1.1.643.8247 |
---|---|
record_format |
openpolar |
spelling |
ftciteseerx:oai:CiteSeerX.psu:10.1.1.643.8247 2023-05-15T16:01:35+02:00 Recognition of group activities using dynamic probabilistic networks Shaogang Gong Tao Xiang The Pennsylvania State University CiteSeerX Archives application/pdf http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.643.8247 http://www.eecs.qmul.ac.uk/~txiang/publications/gong-xiang-iccv03-cameraReady.pdf en eng http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.643.8247 http://www.eecs.qmul.ac.uk/~txiang/publications/gong-xiang-iccv03-cameraReady.pdf Metadata may be used without restrictions as long as the oai identifier remains attached to it. http://www.eecs.qmul.ac.uk/~txiang/publications/gong-xiang-iccv03-cameraReady.pdf Hidden Markov Model (CHMM text ftciteseerx 2016-01-08T16:04:59Z Dynamic Probabilistic Networks (DPNs) are exploited for modelling the temporal relationships among a set of dif-ferent object temporal events in the scene for a coherent and robust scene-level behaviour interpretation. In particu-lar, we develop a Dynamically Multi-Linked Hidden Markov Model (DML-HMM) to interpret group activities involving multiple objects captured in an outdoor scene. The model is based on the discovery of salient dynamic interlinks among multiple temporal events using DPNs. Object temporal events are detected and labelled using Gaussian Mixture Models with automatic model order selection. A DML-HMM is built using Schwarz’s Bayesian Information Cri-terion based factorisation resulting in its topology being in-trinsically determined by the underlying causality and tem-poral order among different object events. Our experiments demonstrate that its performance on modelling group activ-ities in a noisy outdoor scene is superior compared to that of a Multi-Observation Hidden Markov Model (MOHMM), a Parallel Hidden Markov Model (PaHMM) and a Coupled Text DML Unknown |
institution |
Open Polar |
collection |
Unknown |
op_collection_id |
ftciteseerx |
language |
English |
topic |
Hidden Markov Model (CHMM |
spellingShingle |
Hidden Markov Model (CHMM Shaogang Gong Tao Xiang Recognition of group activities using dynamic probabilistic networks |
topic_facet |
Hidden Markov Model (CHMM |
description |
Dynamic Probabilistic Networks (DPNs) are exploited for modelling the temporal relationships among a set of dif-ferent object temporal events in the scene for a coherent and robust scene-level behaviour interpretation. In particu-lar, we develop a Dynamically Multi-Linked Hidden Markov Model (DML-HMM) to interpret group activities involving multiple objects captured in an outdoor scene. The model is based on the discovery of salient dynamic interlinks among multiple temporal events using DPNs. Object temporal events are detected and labelled using Gaussian Mixture Models with automatic model order selection. A DML-HMM is built using Schwarz’s Bayesian Information Cri-terion based factorisation resulting in its topology being in-trinsically determined by the underlying causality and tem-poral order among different object events. Our experiments demonstrate that its performance on modelling group activ-ities in a noisy outdoor scene is superior compared to that of a Multi-Observation Hidden Markov Model (MOHMM), a Parallel Hidden Markov Model (PaHMM) and a Coupled |
author2 |
The Pennsylvania State University CiteSeerX Archives |
format |
Text |
author |
Shaogang Gong Tao Xiang |
author_facet |
Shaogang Gong Tao Xiang |
author_sort |
Shaogang Gong |
title |
Recognition of group activities using dynamic probabilistic networks |
title_short |
Recognition of group activities using dynamic probabilistic networks |
title_full |
Recognition of group activities using dynamic probabilistic networks |
title_fullStr |
Recognition of group activities using dynamic probabilistic networks |
title_full_unstemmed |
Recognition of group activities using dynamic probabilistic networks |
title_sort |
recognition of group activities using dynamic probabilistic networks |
url |
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.643.8247 http://www.eecs.qmul.ac.uk/~txiang/publications/gong-xiang-iccv03-cameraReady.pdf |
genre |
DML |
genre_facet |
DML |
op_source |
http://www.eecs.qmul.ac.uk/~txiang/publications/gong-xiang-iccv03-cameraReady.pdf |
op_relation |
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.643.8247 http://www.eecs.qmul.ac.uk/~txiang/publications/gong-xiang-iccv03-cameraReady.pdf |
op_rights |
Metadata may be used without restrictions as long as the oai identifier remains attached to it. |
_version_ |
1766397377314291712 |