Ontology-Coupled Active Contours for Dynamic Video Scene Understanding

Joanna I. Olszewska, Thomas L. McCluskey

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

17 Citations (Scopus)

Abstract

In this paper, we present an innovative approach coupling active contours with an ontological representation of knowledge, in order to understand scenes acquired by a moving camera and containing multiple non-rigid objects evolving over space and time. The developed active contours enable both segmentation and tracking of multiple targets in each captured scene over a video sequence with unknown camera calibration. Hence, this active contour technique provides information on the objects of interest as well as on parts of them (e.g. shape and position), and contains simultaneously low-level characteristics such as intensity or color features. The ontology we propose consists of concepts whose hierarchical levels map the granularity of the studied scene and of a set of inter- and intra-object spatial and temporal relations defined for this framework, object and sub-object characteristics e.g. shape, and visual concepts like color. The system obtained by coupling this ontology with active contours can study dynamic scenes at different levels of granularity, both numerically and semantically characterize each scene and its components i.e. objects of interest, and reason about spatiotemporal relations between them or parts of them. This resulting knowledge-based vision system was demonstrated on real-world video sequences containing multiple mobile highly-deformable objects.

Original languageEnglish
Title of host publication15th International Conference on Intelligent Engineering Systems, Proceedings (INES 2011)
PublisherIEEE
Pages369-374
Number of pages6
ISBN (Electronic)9781424489565
ISBN (Print)9781424489541
DOIs
Publication statusPublished - 14 Jul 2011
Event15th International Conference on Intelligent Engineering Systems - Poprad, Slovakia
Duration: 23 Jun 201125 Jun 2011
Conference number: 15

Publication series

NameINES 2011 - 15th International Conference on Intelligent Engineering Systems, Proceedings
PublisherIEEE
ISSN (Print)1543-9259

Conference

Conference15th International Conference on Intelligent Engineering Systems
Abbreviated titleINES 2011
CountrySlovakia
CityPoprad
Period23/06/1125/06/11

Fingerprint

Ontology
Cameras
Color
Calibration

Cite this

Olszewska, J. I., & McCluskey, T. L. (2011). Ontology-Coupled Active Contours for Dynamic Video Scene Understanding. In 15th International Conference on Intelligent Engineering Systems, Proceedings (INES 2011) (pp. 369-374). [5954775] (INES 2011 - 15th International Conference on Intelligent Engineering Systems, Proceedings). IEEE. https://doi.org/10.1109/INES.2011.5954775
Olszewska, Joanna I. ; McCluskey, Thomas L. / Ontology-Coupled Active Contours for Dynamic Video Scene Understanding. 15th International Conference on Intelligent Engineering Systems, Proceedings (INES 2011). IEEE, 2011. pp. 369-374 (INES 2011 - 15th International Conference on Intelligent Engineering Systems, Proceedings).
@inproceedings{b8af1abcbbb642ccb4776d1f1e7b6f8e,
title = "Ontology-Coupled Active Contours for Dynamic Video Scene Understanding",
abstract = "In this paper, we present an innovative approach coupling active contours with an ontological representation of knowledge, in order to understand scenes acquired by a moving camera and containing multiple non-rigid objects evolving over space and time. The developed active contours enable both segmentation and tracking of multiple targets in each captured scene over a video sequence with unknown camera calibration. Hence, this active contour technique provides information on the objects of interest as well as on parts of them (e.g. shape and position), and contains simultaneously low-level characteristics such as intensity or color features. The ontology we propose consists of concepts whose hierarchical levels map the granularity of the studied scene and of a set of inter- and intra-object spatial and temporal relations defined for this framework, object and sub-object characteristics e.g. shape, and visual concepts like color. The system obtained by coupling this ontology with active contours can study dynamic scenes at different levels of granularity, both numerically and semantically characterize each scene and its components i.e. objects of interest, and reason about spatiotemporal relations between them or parts of them. This resulting knowledge-based vision system was demonstrated on real-world video sequences containing multiple mobile highly-deformable objects.",
keywords = "Cameras, Deformation, Innovation, Knowledge based systems, Knowledge representation, Video recording, Ontology",
author = "Olszewska, {Joanna I.} and McCluskey, {Thomas L.}",
year = "2011",
month = "7",
day = "14",
doi = "10.1109/INES.2011.5954775",
language = "English",
isbn = "9781424489541",
series = "INES 2011 - 15th International Conference on Intelligent Engineering Systems, Proceedings",
publisher = "IEEE",
pages = "369--374",
booktitle = "15th International Conference on Intelligent Engineering Systems, Proceedings (INES 2011)",

}

Olszewska, JI & McCluskey, TL 2011, Ontology-Coupled Active Contours for Dynamic Video Scene Understanding. in 15th International Conference on Intelligent Engineering Systems, Proceedings (INES 2011)., 5954775, INES 2011 - 15th International Conference on Intelligent Engineering Systems, Proceedings, IEEE, pp. 369-374, 15th International Conference on Intelligent Engineering Systems, Poprad, Slovakia, 23/06/11. https://doi.org/10.1109/INES.2011.5954775

Ontology-Coupled Active Contours for Dynamic Video Scene Understanding. / Olszewska, Joanna I.; McCluskey, Thomas L.

15th International Conference on Intelligent Engineering Systems, Proceedings (INES 2011). IEEE, 2011. p. 369-374 5954775 (INES 2011 - 15th International Conference on Intelligent Engineering Systems, Proceedings).

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

TY - GEN

T1 - Ontology-Coupled Active Contours for Dynamic Video Scene Understanding

AU - Olszewska, Joanna I.

AU - McCluskey, Thomas L.

PY - 2011/7/14

Y1 - 2011/7/14

N2 - In this paper, we present an innovative approach coupling active contours with an ontological representation of knowledge, in order to understand scenes acquired by a moving camera and containing multiple non-rigid objects evolving over space and time. The developed active contours enable both segmentation and tracking of multiple targets in each captured scene over a video sequence with unknown camera calibration. Hence, this active contour technique provides information on the objects of interest as well as on parts of them (e.g. shape and position), and contains simultaneously low-level characteristics such as intensity or color features. The ontology we propose consists of concepts whose hierarchical levels map the granularity of the studied scene and of a set of inter- and intra-object spatial and temporal relations defined for this framework, object and sub-object characteristics e.g. shape, and visual concepts like color. The system obtained by coupling this ontology with active contours can study dynamic scenes at different levels of granularity, both numerically and semantically characterize each scene and its components i.e. objects of interest, and reason about spatiotemporal relations between them or parts of them. This resulting knowledge-based vision system was demonstrated on real-world video sequences containing multiple mobile highly-deformable objects.

AB - In this paper, we present an innovative approach coupling active contours with an ontological representation of knowledge, in order to understand scenes acquired by a moving camera and containing multiple non-rigid objects evolving over space and time. The developed active contours enable both segmentation and tracking of multiple targets in each captured scene over a video sequence with unknown camera calibration. Hence, this active contour technique provides information on the objects of interest as well as on parts of them (e.g. shape and position), and contains simultaneously low-level characteristics such as intensity or color features. The ontology we propose consists of concepts whose hierarchical levels map the granularity of the studied scene and of a set of inter- and intra-object spatial and temporal relations defined for this framework, object and sub-object characteristics e.g. shape, and visual concepts like color. The system obtained by coupling this ontology with active contours can study dynamic scenes at different levels of granularity, both numerically and semantically characterize each scene and its components i.e. objects of interest, and reason about spatiotemporal relations between them or parts of them. This resulting knowledge-based vision system was demonstrated on real-world video sequences containing multiple mobile highly-deformable objects.

KW - Cameras

KW - Deformation

KW - Innovation

KW - Knowledge based systems

KW - Knowledge representation

KW - Video recording

KW - Ontology

UR - http://www.scopus.com/inward/record.url?scp=80051722345&partnerID=8YFLogxK

U2 - 10.1109/INES.2011.5954775

DO - 10.1109/INES.2011.5954775

M3 - Conference contribution

AN - SCOPUS:80051722345

SN - 9781424489541

T3 - INES 2011 - 15th International Conference on Intelligent Engineering Systems, Proceedings

SP - 369

EP - 374

BT - 15th International Conference on Intelligent Engineering Systems, Proceedings (INES 2011)

PB - IEEE

ER -

Olszewska JI, McCluskey TL. Ontology-Coupled Active Contours for Dynamic Video Scene Understanding. In 15th International Conference on Intelligent Engineering Systems, Proceedings (INES 2011). IEEE. 2011. p. 369-374. 5954775. (INES 2011 - 15th International Conference on Intelligent Engineering Systems, Proceedings). https://doi.org/10.1109/INES.2011.5954775