Exploring video descriptions for handwashing activities as part of an obsessive-compulsive disorder study

Joshua Fasching, Nicholas Walczak, Tasoulla Hadjiyanni, Gail A Bernstein, Kathryn R Cullen, Mackenzie Mikkelsen, Nathan Studanski, Vassilios Morellas, Nikolaos P Papanikolopoulos

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Analysis of behavior using video is a promising approach for identifying risk markers for psychopathology that can be applied in a wide range of populations. As part of a study on the environmental factors that relate to obsessive-compulsive disorder (OCD) behaviors, videos were recorded of everyday tasks being performed by two groups of children: a control group and a group diagnosed with OCD. One of the activities involved handwashing, since handwashing compulsions are frequent amongst those who suffer from OCD. Being able to classify these handwashing videos as showing behaviors associated with OCD or not is a step towards helping to automate important aspects of this psychiatric study. This paper explores using various feature descriptors sampled from dense motion trajectories to determine which combination of features and encodings would be best for video classification. Dense motion trajectories are computed for the videos from the OCD study and the points in these trajectories are described using several methods, including histograms of oriented gradient, histograms of optical flow, and motion boundary histograms. Various encoding techniques for these descriptors are also explored, including bag of words, pyramid bag of words, and sparse coding. To determine which feature/encoding techniques would perform the best, several dimensionality reduction techniques are used and the methods are ranked based on separability in the low dimensional space. This separability is measured by classifying using a linear discriminant and also by using kNN.

Original languageEnglish (US)
Title of host publication24th Mediterranean Conference on Control and Automation, MED 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1174-1179
Number of pages6
ISBN (Electronic)9781467383455
DOIs
StatePublished - Aug 5 2016
Event24th Mediterranean Conference on Control and Automation, MED 2016 - Athens, Greece
Duration: Jun 21 2016Jun 24 2016

Publication series

Name24th Mediterranean Conference on Control and Automation, MED 2016

Other

Other24th Mediterranean Conference on Control and Automation, MED 2016
CountryGreece
CityAthens
Period6/21/166/24/16

Fingerprint

Disorder
Trajectories
Histogram
Encoding
Trajectory
Separability
Optical flows
Descriptors
Motion
Sparse Coding
Environmental Factors
Optical Flow
Pyramid
Dimensionality Reduction
Discriminant
Classify
Gradient
Range of data
Psychiatry

Cite this

Fasching, J., Walczak, N., Hadjiyanni, T., Bernstein, G. A., Cullen, K. R., Mikkelsen, M., ... Papanikolopoulos, N. P. (2016). Exploring video descriptions for handwashing activities as part of an obsessive-compulsive disorder study. In 24th Mediterranean Conference on Control and Automation, MED 2016 (pp. 1174-1179). [7535917] (24th Mediterranean Conference on Control and Automation, MED 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/MED.2016.7535917

Exploring video descriptions for handwashing activities as part of an obsessive-compulsive disorder study. / Fasching, Joshua; Walczak, Nicholas; Hadjiyanni, Tasoulla; Bernstein, Gail A; Cullen, Kathryn R; Mikkelsen, Mackenzie; Studanski, Nathan; Morellas, Vassilios; Papanikolopoulos, Nikolaos P.

24th Mediterranean Conference on Control and Automation, MED 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 1174-1179 7535917 (24th Mediterranean Conference on Control and Automation, MED 2016).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Fasching, J, Walczak, N, Hadjiyanni, T, Bernstein, GA, Cullen, KR, Mikkelsen, M, Studanski, N, Morellas, V & Papanikolopoulos, NP 2016, Exploring video descriptions for handwashing activities as part of an obsessive-compulsive disorder study. in 24th Mediterranean Conference on Control and Automation, MED 2016., 7535917, 24th Mediterranean Conference on Control and Automation, MED 2016, Institute of Electrical and Electronics Engineers Inc., pp. 1174-1179, 24th Mediterranean Conference on Control and Automation, MED 2016, Athens, Greece, 6/21/16. https://doi.org/10.1109/MED.2016.7535917
Fasching J, Walczak N, Hadjiyanni T, Bernstein GA, Cullen KR, Mikkelsen M et al. Exploring video descriptions for handwashing activities as part of an obsessive-compulsive disorder study. In 24th Mediterranean Conference on Control and Automation, MED 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 1174-1179. 7535917. (24th Mediterranean Conference on Control and Automation, MED 2016). https://doi.org/10.1109/MED.2016.7535917
Fasching, Joshua ; Walczak, Nicholas ; Hadjiyanni, Tasoulla ; Bernstein, Gail A ; Cullen, Kathryn R ; Mikkelsen, Mackenzie ; Studanski, Nathan ; Morellas, Vassilios ; Papanikolopoulos, Nikolaos P. / Exploring video descriptions for handwashing activities as part of an obsessive-compulsive disorder study. 24th Mediterranean Conference on Control and Automation, MED 2016. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 1174-1179 (24th Mediterranean Conference on Control and Automation, MED 2016).
@inproceedings{93db0a4c597a46ffa4aa765a93ef7d4b,
title = "Exploring video descriptions for handwashing activities as part of an obsessive-compulsive disorder study",
abstract = "Analysis of behavior using video is a promising approach for identifying risk markers for psychopathology that can be applied in a wide range of populations. As part of a study on the environmental factors that relate to obsessive-compulsive disorder (OCD) behaviors, videos were recorded of everyday tasks being performed by two groups of children: a control group and a group diagnosed with OCD. One of the activities involved handwashing, since handwashing compulsions are frequent amongst those who suffer from OCD. Being able to classify these handwashing videos as showing behaviors associated with OCD or not is a step towards helping to automate important aspects of this psychiatric study. This paper explores using various feature descriptors sampled from dense motion trajectories to determine which combination of features and encodings would be best for video classification. Dense motion trajectories are computed for the videos from the OCD study and the points in these trajectories are described using several methods, including histograms of oriented gradient, histograms of optical flow, and motion boundary histograms. Various encoding techniques for these descriptors are also explored, including bag of words, pyramid bag of words, and sparse coding. To determine which feature/encoding techniques would perform the best, several dimensionality reduction techniques are used and the methods are ranked based on separability in the low dimensional space. This separability is measured by classifying using a linear discriminant and also by using kNN.",
author = "Joshua Fasching and Nicholas Walczak and Tasoulla Hadjiyanni and Bernstein, {Gail A} and Cullen, {Kathryn R} and Mackenzie Mikkelsen and Nathan Studanski and Vassilios Morellas and Papanikolopoulos, {Nikolaos P}",
year = "2016",
month = "8",
day = "5",
doi = "10.1109/MED.2016.7535917",
language = "English (US)",
series = "24th Mediterranean Conference on Control and Automation, MED 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1174--1179",
booktitle = "24th Mediterranean Conference on Control and Automation, MED 2016",

}

TY - GEN

T1 - Exploring video descriptions for handwashing activities as part of an obsessive-compulsive disorder study

AU - Fasching, Joshua

AU - Walczak, Nicholas

AU - Hadjiyanni, Tasoulla

AU - Bernstein, Gail A

AU - Cullen, Kathryn R

AU - Mikkelsen, Mackenzie

AU - Studanski, Nathan

AU - Morellas, Vassilios

AU - Papanikolopoulos, Nikolaos P

PY - 2016/8/5

Y1 - 2016/8/5

N2 - Analysis of behavior using video is a promising approach for identifying risk markers for psychopathology that can be applied in a wide range of populations. As part of a study on the environmental factors that relate to obsessive-compulsive disorder (OCD) behaviors, videos were recorded of everyday tasks being performed by two groups of children: a control group and a group diagnosed with OCD. One of the activities involved handwashing, since handwashing compulsions are frequent amongst those who suffer from OCD. Being able to classify these handwashing videos as showing behaviors associated with OCD or not is a step towards helping to automate important aspects of this psychiatric study. This paper explores using various feature descriptors sampled from dense motion trajectories to determine which combination of features and encodings would be best for video classification. Dense motion trajectories are computed for the videos from the OCD study and the points in these trajectories are described using several methods, including histograms of oriented gradient, histograms of optical flow, and motion boundary histograms. Various encoding techniques for these descriptors are also explored, including bag of words, pyramid bag of words, and sparse coding. To determine which feature/encoding techniques would perform the best, several dimensionality reduction techniques are used and the methods are ranked based on separability in the low dimensional space. This separability is measured by classifying using a linear discriminant and also by using kNN.

AB - Analysis of behavior using video is a promising approach for identifying risk markers for psychopathology that can be applied in a wide range of populations. As part of a study on the environmental factors that relate to obsessive-compulsive disorder (OCD) behaviors, videos were recorded of everyday tasks being performed by two groups of children: a control group and a group diagnosed with OCD. One of the activities involved handwashing, since handwashing compulsions are frequent amongst those who suffer from OCD. Being able to classify these handwashing videos as showing behaviors associated with OCD or not is a step towards helping to automate important aspects of this psychiatric study. This paper explores using various feature descriptors sampled from dense motion trajectories to determine which combination of features and encodings would be best for video classification. Dense motion trajectories are computed for the videos from the OCD study and the points in these trajectories are described using several methods, including histograms of oriented gradient, histograms of optical flow, and motion boundary histograms. Various encoding techniques for these descriptors are also explored, including bag of words, pyramid bag of words, and sparse coding. To determine which feature/encoding techniques would perform the best, several dimensionality reduction techniques are used and the methods are ranked based on separability in the low dimensional space. This separability is measured by classifying using a linear discriminant and also by using kNN.

UR - http://www.scopus.com/inward/record.url?scp=84986231549&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84986231549&partnerID=8YFLogxK

U2 - 10.1109/MED.2016.7535917

DO - 10.1109/MED.2016.7535917

M3 - Conference contribution

T3 - 24th Mediterranean Conference on Control and Automation, MED 2016

SP - 1174

EP - 1179

BT - 24th Mediterranean Conference on Control and Automation, MED 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -