Tracking the invisible man: hidden-object detection for complex visual scene understanding

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

Abstract

Reliable detection of objects of interest in complex visual scenes is of prime importance for video-surveillance applications. While most vision approaches deal with tracking visible or partially visible objects in single or multiple video streams, we propose a new approach to automatically detect all objects of interest being part of an analyzed scene, even those entirely hidden in a camera view whereas being present in the scene. For that, we have developed an innovative artificial-intelligence framework embedding a computer vision process fully integrating symbolic knowledge-based reasoning. Our system has been evaluated on standard datasets consisting of video streams with real-world objects evolving in cluttered, outdoor environment under difficult lighting conditions. Our proposed approach shows excellent performance both in detection accuracy and robustness, and outperforms state-of-the-art methods.
Original languageEnglish
Title of host publicationProceedings of the 8th International Conference on Agents and Artificial Intelligence
Subtitle of host publicationICAART
PublisherSciTePress
Pages223-229
Number of pages7
Volume2
ISBN (Print)978-989-758-172-4
DOIs
Publication statusPublished - 2016
Externally publishedYes

Fingerprint

Computer vision
Artificial intelligence
Lighting
Cameras
Object detection

Keywords

  • Surveillance Application
  • Visual Scene Analysis
  • Automated Scene Understanding
  • Knowledge Representation
  • Spatio-temporal Visual Ontology
  • Symbolic Reasoning
  • Computer Vision
  • Pattern Recognition

Cite this

Olszewska, J. I. (2016). Tracking the invisible man: hidden-object detection for complex visual scene understanding. In Proceedings of the 8th International Conference on Agents and Artificial Intelligence: ICAART (Vol. 2, pp. 223-229). SciTePress. https://doi.org/10.5220/0005852302230229
Olszewska, Joanna Isabelle. / Tracking the invisible man : hidden-object detection for complex visual scene understanding. Proceedings of the 8th International Conference on Agents and Artificial Intelligence: ICAART. Vol. 2 SciTePress, 2016. pp. 223-229
@inproceedings{c718777f96b543a79da9fb7265b86208,
title = "Tracking the invisible man: hidden-object detection for complex visual scene understanding",
abstract = "Reliable detection of objects of interest in complex visual scenes is of prime importance for video-surveillance applications. While most vision approaches deal with tracking visible or partially visible objects in single or multiple video streams, we propose a new approach to automatically detect all objects of interest being part of an analyzed scene, even those entirely hidden in a camera view whereas being present in the scene. For that, we have developed an innovative artificial-intelligence framework embedding a computer vision process fully integrating symbolic knowledge-based reasoning. Our system has been evaluated on standard datasets consisting of video streams with real-world objects evolving in cluttered, outdoor environment under difficult lighting conditions. Our proposed approach shows excellent performance both in detection accuracy and robustness, and outperforms state-of-the-art methods.",
keywords = "Surveillance Application, Visual Scene Analysis, Automated Scene Understanding, Knowledge Representation, Spatio-temporal Visual Ontology, Symbolic Reasoning, Computer Vision, Pattern Recognition",
author = "Olszewska, {Joanna Isabelle}",
year = "2016",
doi = "10.5220/0005852302230229",
language = "English",
isbn = "978-989-758-172-4",
volume = "2",
pages = "223--229",
booktitle = "Proceedings of the 8th International Conference on Agents and Artificial Intelligence",
publisher = "SciTePress",
address = "Portugal",

}

Olszewska, JI 2016, Tracking the invisible man: hidden-object detection for complex visual scene understanding. in Proceedings of the 8th International Conference on Agents and Artificial Intelligence: ICAART. vol. 2, SciTePress, pp. 223-229. https://doi.org/10.5220/0005852302230229

Tracking the invisible man : hidden-object detection for complex visual scene understanding. / Olszewska, Joanna Isabelle.

Proceedings of the 8th International Conference on Agents and Artificial Intelligence: ICAART. Vol. 2 SciTePress, 2016. p. 223-229.

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

TY - GEN

T1 - Tracking the invisible man

T2 - hidden-object detection for complex visual scene understanding

AU - Olszewska, Joanna Isabelle

PY - 2016

Y1 - 2016

N2 - Reliable detection of objects of interest in complex visual scenes is of prime importance for video-surveillance applications. While most vision approaches deal with tracking visible or partially visible objects in single or multiple video streams, we propose a new approach to automatically detect all objects of interest being part of an analyzed scene, even those entirely hidden in a camera view whereas being present in the scene. For that, we have developed an innovative artificial-intelligence framework embedding a computer vision process fully integrating symbolic knowledge-based reasoning. Our system has been evaluated on standard datasets consisting of video streams with real-world objects evolving in cluttered, outdoor environment under difficult lighting conditions. Our proposed approach shows excellent performance both in detection accuracy and robustness, and outperforms state-of-the-art methods.

AB - Reliable detection of objects of interest in complex visual scenes is of prime importance for video-surveillance applications. While most vision approaches deal with tracking visible or partially visible objects in single or multiple video streams, we propose a new approach to automatically detect all objects of interest being part of an analyzed scene, even those entirely hidden in a camera view whereas being present in the scene. For that, we have developed an innovative artificial-intelligence framework embedding a computer vision process fully integrating symbolic knowledge-based reasoning. Our system has been evaluated on standard datasets consisting of video streams with real-world objects evolving in cluttered, outdoor environment under difficult lighting conditions. Our proposed approach shows excellent performance both in detection accuracy and robustness, and outperforms state-of-the-art methods.

KW - Surveillance Application

KW - Visual Scene Analysis

KW - Automated Scene Understanding

KW - Knowledge Representation

KW - Spatio-temporal Visual Ontology

KW - Symbolic Reasoning

KW - Computer Vision

KW - Pattern Recognition

U2 - 10.5220/0005852302230229

DO - 10.5220/0005852302230229

M3 - Conference contribution

SN - 978-989-758-172-4

VL - 2

SP - 223

EP - 229

BT - Proceedings of the 8th International Conference on Agents and Artificial Intelligence

PB - SciTePress

ER -

Olszewska JI. Tracking the invisible man: hidden-object detection for complex visual scene understanding. In Proceedings of the 8th International Conference on Agents and Artificial Intelligence: ICAART. Vol. 2. SciTePress. 2016. p. 223-229 https://doi.org/10.5220/0005852302230229