Human activity prediction by mapping grouplets to recurrent self-organizing map
Human activity prediction is defined as inferring the high-level activity category with the observation of only a few action units. It is very meaningful for time-critical applications such as emergency surveillance. For efficient prediction, we represent the ongoing human activity by using body par...
Saved in:
Main Authors: | , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2016
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/4453 https://ink.library.smu.edu.sg/context/sis_research/article/5456/viewcontent/Neurocomputing2015_sunqianru.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.sis_research-5456 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-54562019-11-28T07:51:46Z Human activity prediction by mapping grouplets to recurrent self-organizing map SUN, Qianru LIU, Hong LIU, Mengyuan ZHANG, Tianwei Human activity prediction is defined as inferring the high-level activity category with the observation of only a few action units. It is very meaningful for time-critical applications such as emergency surveillance. For efficient prediction, we represent the ongoing human activity by using body part movements and taking full advantage of inherent sequentiality, then find the best matching activity template by a proper aligning measurement.In streaming videos, dense spatio-temporal interest points (STIPs) are first extracted as low-level descriptors for their high detection efficiency. Then, sparse grouplets, i.e., clustered point groups, are located to represent body part movements, for which we propose a scale-adaptive mean shift method that can determine grouplet number and scale for each frame adaptively. To learn the sequentiality, located grouplets are successively mapped to Recurrent Self-Organizing Map (RSOM), which has been pre-trained to preserve the temporal topology of grouplet sequences. During this mapping, a growing RSOM trajectory, which represents the ongoing activity, is obtained. For the special structure of RSOM trajectory, a combination of dynamic time warping (DTW) distance and edit distance, called DTW-E distance, is designed for similarity measurement. Four activity datasets with different characteristics such as complex scenes and inter-class ambiguities serve for performance evaluation. Experimental results confirm that our method is very efficient for predicting human activity and yields better performance than state-of-the-art works. (C) 2015 Elsevier B.V. All rights reserved. 2016-02-12T08:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/4453 info:doi/10.1016/j.neucom.2015.11.061 https://ink.library.smu.edu.sg/context/sis_research/article/5456/viewcontent/Neurocomputing2015_sunqianru.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Human activity prediction Spatio-temporal interest points Mean shift Recurrent Self-Organizing Map Computer Engineering Software Engineering |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
Human activity prediction Spatio-temporal interest points Mean shift Recurrent Self-Organizing Map Computer Engineering Software Engineering |
spellingShingle |
Human activity prediction Spatio-temporal interest points Mean shift Recurrent Self-Organizing Map Computer Engineering Software Engineering SUN, Qianru LIU, Hong LIU, Mengyuan ZHANG, Tianwei Human activity prediction by mapping grouplets to recurrent self-organizing map |
description |
Human activity prediction is defined as inferring the high-level activity category with the observation of only a few action units. It is very meaningful for time-critical applications such as emergency surveillance. For efficient prediction, we represent the ongoing human activity by using body part movements and taking full advantage of inherent sequentiality, then find the best matching activity template by a proper aligning measurement.In streaming videos, dense spatio-temporal interest points (STIPs) are first extracted as low-level descriptors for their high detection efficiency. Then, sparse grouplets, i.e., clustered point groups, are located to represent body part movements, for which we propose a scale-adaptive mean shift method that can determine grouplet number and scale for each frame adaptively. To learn the sequentiality, located grouplets are successively mapped to Recurrent Self-Organizing Map (RSOM), which has been pre-trained to preserve the temporal topology of grouplet sequences. During this mapping, a growing RSOM trajectory, which represents the ongoing activity, is obtained. For the special structure of RSOM trajectory, a combination of dynamic time warping (DTW) distance and edit distance, called DTW-E distance, is designed for similarity measurement. Four activity datasets with different characteristics such as complex scenes and inter-class ambiguities serve for performance evaluation. Experimental results confirm that our method is very efficient for predicting human activity and yields better performance than state-of-the-art works. (C) 2015 Elsevier B.V. All rights reserved. |
format |
text |
author |
SUN, Qianru LIU, Hong LIU, Mengyuan ZHANG, Tianwei |
author_facet |
SUN, Qianru LIU, Hong LIU, Mengyuan ZHANG, Tianwei |
author_sort |
SUN, Qianru |
title |
Human activity prediction by mapping grouplets to recurrent self-organizing map |
title_short |
Human activity prediction by mapping grouplets to recurrent self-organizing map |
title_full |
Human activity prediction by mapping grouplets to recurrent self-organizing map |
title_fullStr |
Human activity prediction by mapping grouplets to recurrent self-organizing map |
title_full_unstemmed |
Human activity prediction by mapping grouplets to recurrent self-organizing map |
title_sort |
human activity prediction by mapping grouplets to recurrent self-organizing map |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2016 |
url |
https://ink.library.smu.edu.sg/sis_research/4453 https://ink.library.smu.edu.sg/context/sis_research/article/5456/viewcontent/Neurocomputing2015_sunqianru.pdf |
_version_ |
1770574843208531968 |