Locating occupants in preschool classrooms using a multiple RGB-D sensor system

Nicholas Walczak, Joshua Fasching, William D. Toczyski, Vassilios Morellas, Guillermo Sapiro, Nikolaos P Papanikolopoulos

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

2 Citations (Scopus)

Abstract

Presented are results demonstrating that, in developing a system with its first objective being the sustained detection of adults and young children as they move and interact in a normal preschool setting, the direct application of the straightforward RGB-D innovations presented here significantly outperforms even far more algorithmically advanced methods relying solely on images. The use of multiple RGB-D sensors by this project for depth-aware object localization economically resolves numerous issues regularly frustrating earlier vision-only detection and human surveillance methods, issues such as occlusions, illumination changes, unexpected postures, atypical morphologies, erratic or unanticipated motions, reflections, and misleading textures and colorations. This multiple RGB-D installation forms the front-end for a multi-step pipeline, the first portion of which seeks to isolate, in situ, 3D renderings of classroom occupants sufficient for a later analysis of their behaviors and interactions. Towards this end, a voxel-based approach to foreground/background separation and an effective adaptation of supervoxel clustering for 3D were developed, and 3D and image-only methods were tested and compared. The project's setting is highly challenging, but then so are its longer term goals: the automated detection of early childhood precursors, ofttimes very subtle, to a number of increasingly common developmental disorders.

Original languageEnglish (US)
Title of host publicationIROS 2013
Subtitle of host publicationNew Horizon, Conference Digest - 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems
Pages2166-2172
Number of pages7
DOIs
StatePublished - Dec 1 2013
Event2013 26th IEEE/RSJ International Conference on Intelligent Robots and Systems: New Horizon, IROS 2013 - Tokyo, Japan
Duration: Nov 3 2013Nov 8 2013

Other

Other2013 26th IEEE/RSJ International Conference on Intelligent Robots and Systems: New Horizon, IROS 2013
CountryJapan
CityTokyo
Period11/3/1311/8/13

Fingerprint

Pipelines
Textures
Innovation
Lighting
Sensors

Cite this

Walczak, N., Fasching, J., Toczyski, W. D., Morellas, V., Sapiro, G., & Papanikolopoulos, N. P. (2013). Locating occupants in preschool classrooms using a multiple RGB-D sensor system. In IROS 2013: New Horizon, Conference Digest - 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems (pp. 2166-2172). [6696659] https://doi.org/10.1109/IROS.2013.6696659

Locating occupants in preschool classrooms using a multiple RGB-D sensor system. / Walczak, Nicholas; Fasching, Joshua; Toczyski, William D.; Morellas, Vassilios; Sapiro, Guillermo; Papanikolopoulos, Nikolaos P.

IROS 2013: New Horizon, Conference Digest - 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems. 2013. p. 2166-2172 6696659.

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

Walczak, N, Fasching, J, Toczyski, WD, Morellas, V, Sapiro, G & Papanikolopoulos, NP 2013, Locating occupants in preschool classrooms using a multiple RGB-D sensor system. in IROS 2013: New Horizon, Conference Digest - 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems., 6696659, pp. 2166-2172, 2013 26th IEEE/RSJ International Conference on Intelligent Robots and Systems: New Horizon, IROS 2013, Tokyo, Japan, 11/3/13. https://doi.org/10.1109/IROS.2013.6696659
Walczak N, Fasching J, Toczyski WD, Morellas V, Sapiro G, Papanikolopoulos NP. Locating occupants in preschool classrooms using a multiple RGB-D sensor system. In IROS 2013: New Horizon, Conference Digest - 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems. 2013. p. 2166-2172. 6696659 https://doi.org/10.1109/IROS.2013.6696659
Walczak, Nicholas ; Fasching, Joshua ; Toczyski, William D. ; Morellas, Vassilios ; Sapiro, Guillermo ; Papanikolopoulos, Nikolaos P. / Locating occupants in preschool classrooms using a multiple RGB-D sensor system. IROS 2013: New Horizon, Conference Digest - 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems. 2013. pp. 2166-2172
@inproceedings{3adb1e904c324e5d8887a4c742fcf754,
title = "Locating occupants in preschool classrooms using a multiple RGB-D sensor system",
abstract = "Presented are results demonstrating that, in developing a system with its first objective being the sustained detection of adults and young children as they move and interact in a normal preschool setting, the direct application of the straightforward RGB-D innovations presented here significantly outperforms even far more algorithmically advanced methods relying solely on images. The use of multiple RGB-D sensors by this project for depth-aware object localization economically resolves numerous issues regularly frustrating earlier vision-only detection and human surveillance methods, issues such as occlusions, illumination changes, unexpected postures, atypical morphologies, erratic or unanticipated motions, reflections, and misleading textures and colorations. This multiple RGB-D installation forms the front-end for a multi-step pipeline, the first portion of which seeks to isolate, in situ, 3D renderings of classroom occupants sufficient for a later analysis of their behaviors and interactions. Towards this end, a voxel-based approach to foreground/background separation and an effective adaptation of supervoxel clustering for 3D were developed, and 3D and image-only methods were tested and compared. The project's setting is highly challenging, but then so are its longer term goals: the automated detection of early childhood precursors, ofttimes very subtle, to a number of increasingly common developmental disorders.",
author = "Nicholas Walczak and Joshua Fasching and Toczyski, {William D.} and Vassilios Morellas and Guillermo Sapiro and Papanikolopoulos, {Nikolaos P}",
year = "2013",
month = "12",
day = "1",
doi = "10.1109/IROS.2013.6696659",
language = "English (US)",
isbn = "9781467363587",
pages = "2166--2172",
booktitle = "IROS 2013",

}

TY - GEN

T1 - Locating occupants in preschool classrooms using a multiple RGB-D sensor system

AU - Walczak, Nicholas

AU - Fasching, Joshua

AU - Toczyski, William D.

AU - Morellas, Vassilios

AU - Sapiro, Guillermo

AU - Papanikolopoulos, Nikolaos P

PY - 2013/12/1

Y1 - 2013/12/1

N2 - Presented are results demonstrating that, in developing a system with its first objective being the sustained detection of adults and young children as they move and interact in a normal preschool setting, the direct application of the straightforward RGB-D innovations presented here significantly outperforms even far more algorithmically advanced methods relying solely on images. The use of multiple RGB-D sensors by this project for depth-aware object localization economically resolves numerous issues regularly frustrating earlier vision-only detection and human surveillance methods, issues such as occlusions, illumination changes, unexpected postures, atypical morphologies, erratic or unanticipated motions, reflections, and misleading textures and colorations. This multiple RGB-D installation forms the front-end for a multi-step pipeline, the first portion of which seeks to isolate, in situ, 3D renderings of classroom occupants sufficient for a later analysis of their behaviors and interactions. Towards this end, a voxel-based approach to foreground/background separation and an effective adaptation of supervoxel clustering for 3D were developed, and 3D and image-only methods were tested and compared. The project's setting is highly challenging, but then so are its longer term goals: the automated detection of early childhood precursors, ofttimes very subtle, to a number of increasingly common developmental disorders.

AB - Presented are results demonstrating that, in developing a system with its first objective being the sustained detection of adults and young children as they move and interact in a normal preschool setting, the direct application of the straightforward RGB-D innovations presented here significantly outperforms even far more algorithmically advanced methods relying solely on images. The use of multiple RGB-D sensors by this project for depth-aware object localization economically resolves numerous issues regularly frustrating earlier vision-only detection and human surveillance methods, issues such as occlusions, illumination changes, unexpected postures, atypical morphologies, erratic or unanticipated motions, reflections, and misleading textures and colorations. This multiple RGB-D installation forms the front-end for a multi-step pipeline, the first portion of which seeks to isolate, in situ, 3D renderings of classroom occupants sufficient for a later analysis of their behaviors and interactions. Towards this end, a voxel-based approach to foreground/background separation and an effective adaptation of supervoxel clustering for 3D were developed, and 3D and image-only methods were tested and compared. The project's setting is highly challenging, but then so are its longer term goals: the automated detection of early childhood precursors, ofttimes very subtle, to a number of increasingly common developmental disorders.

UR - http://www.scopus.com/inward/record.url?scp=84893756786&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84893756786&partnerID=8YFLogxK

U2 - 10.1109/IROS.2013.6696659

DO - 10.1109/IROS.2013.6696659

M3 - Conference contribution

SN - 9781467363587

SP - 2166

EP - 2172

BT - IROS 2013

ER -