Adding context information to video analysis for surveillance applications

Research output: Chapter in Book/Report/Conference proceedingChapterAcademicpeer-review

Abstract

Smart surveillance systems become more meaningful if they both grow in reliability and robustness, while simultaneously offering a higher semantic level of understanding. To achieve a higher level of semantic scene understanding, the objects and their actions have to be interpreted in the given context, so that the extraction of contextual information is required. This chapter explores several techniques for extracting the contextual information such as spatial, motion, depth and co-occurrence, depending on applications. Afterwards, the chapter provides specific case studies to evaluate the usefulness of context information, based on: (1) region labeling of the surroundings of objects, (2) motion analysis of the water for moving ships, (3) traffic sign recognition for safety event evaluation and (4) the use of depth signals for obstacle detection. The chapter shows that the previous cases can be solved in an improved way with respect to robustness and semantic understanding. Case studies indicate up to 6.8% improvement of reliable correct object understanding and the novel possibility of labeling scene events as safe/unsafe depending on the object behavior and the detected surrounding context. In this chapter, it is shown that using contextual information improves automated video surveillance analysis, as it not only improves the reliability of moving object detection, but also enables scene understanding that is far beyond object understanding.

LanguageEnglish
Title of host publicationBiometrics
Subtitle of host publicationconcepts, methodologies, tools, and applications
Place of Publications.l.
PublisherIGI Global
Pages1656-1700
Number of pages45
ISBN (Electronic)9781522509844
ISBN (Print)9781522509837
DOIs
StatePublished - 30 Aug 2016

Fingerprint

Semantics
Labeling
Traffic signs
Ships
Water
Motion analysis
Object detection

Cite this

Javanbakhti, S., Sanberg, W. P., Bao, X., van de Wouw, D. W. J. M., Creusen, I., Dubbelman, G., ... de With, P. H. N. (2016). Adding context information to video analysis for surveillance applications. In Biometrics: concepts, methodologies, tools, and applications (pp. 1656-1700). s.l.: IGI Global. DOI: 10.4018/978-1-5225-0983-7.ch070
Javanbakhti, Solmaz ; Sanberg, Willem P. ; Bao, Xinfeng ; van de Wouw, D.W.J.M. ; Creusen, Ivo ; Dubbelman, Gijs ; Hazelhoff, Lykele ; Zinger, Svitlana ; de With, Peter H.N./ Adding context information to video analysis for surveillance applications. Biometrics: concepts, methodologies, tools, and applications. s.l. : IGI Global, 2016. pp. 1656-1700
@inbook{1ede979cb4bf4d2097f052741ae7d41f,
title = "Adding context information to video analysis for surveillance applications",
abstract = "Smart surveillance systems become more meaningful if they both grow in reliability and robustness, while simultaneously offering a higher semantic level of understanding. To achieve a higher level of semantic scene understanding, the objects and their actions have to be interpreted in the given context, so that the extraction of contextual information is required. This chapter explores several techniques for extracting the contextual information such as spatial, motion, depth and co-occurrence, depending on applications. Afterwards, the chapter provides specific case studies to evaluate the usefulness of context information, based on: (1) region labeling of the surroundings of objects, (2) motion analysis of the water for moving ships, (3) traffic sign recognition for safety event evaluation and (4) the use of depth signals for obstacle detection. The chapter shows that the previous cases can be solved in an improved way with respect to robustness and semantic understanding. Case studies indicate up to 6.8{\%} improvement of reliable correct object understanding and the novel possibility of labeling scene events as safe/unsafe depending on the object behavior and the detected surrounding context. In this chapter, it is shown that using contextual information improves automated video surveillance analysis, as it not only improves the reliability of moving object detection, but also enables scene understanding that is far beyond object understanding.",
author = "Solmaz Javanbakhti and Sanberg, {Willem P.} and Xinfeng Bao and {van de Wouw}, D.W.J.M. and Ivo Creusen and Gijs Dubbelman and Lykele Hazelhoff and Svitlana Zinger and {de With}, {Peter H.N.}",
year = "2016",
month = "8",
day = "30",
doi = "10.4018/978-1-5225-0983-7.ch070",
language = "English",
isbn = "9781522509837",
pages = "1656--1700",
booktitle = "Biometrics",
publisher = "IGI Global",

}

Javanbakhti, S, Sanberg, WP, Bao, X, van de Wouw, DWJM, Creusen, I, Dubbelman, G, Hazelhoff, L, Zinger, S & de With, PHN 2016, Adding context information to video analysis for surveillance applications. in Biometrics: concepts, methodologies, tools, and applications. IGI Global, s.l., pp. 1656-1700. DOI: 10.4018/978-1-5225-0983-7.ch070

Adding context information to video analysis for surveillance applications. / Javanbakhti, Solmaz; Sanberg, Willem P.; Bao, Xinfeng; van de Wouw, D.W.J.M.; Creusen, Ivo; Dubbelman, Gijs; Hazelhoff, Lykele; Zinger, Svitlana; de With, Peter H.N.

Biometrics: concepts, methodologies, tools, and applications. s.l. : IGI Global, 2016. p. 1656-1700.

Research output: Chapter in Book/Report/Conference proceedingChapterAcademicpeer-review

TY - CHAP

T1 - Adding context information to video analysis for surveillance applications

AU - Javanbakhti,Solmaz

AU - Sanberg,Willem P.

AU - Bao,Xinfeng

AU - van de Wouw,D.W.J.M.

AU - Creusen,Ivo

AU - Dubbelman,Gijs

AU - Hazelhoff,Lykele

AU - Zinger,Svitlana

AU - de With,Peter H.N.

PY - 2016/8/30

Y1 - 2016/8/30

N2 - Smart surveillance systems become more meaningful if they both grow in reliability and robustness, while simultaneously offering a higher semantic level of understanding. To achieve a higher level of semantic scene understanding, the objects and their actions have to be interpreted in the given context, so that the extraction of contextual information is required. This chapter explores several techniques for extracting the contextual information such as spatial, motion, depth and co-occurrence, depending on applications. Afterwards, the chapter provides specific case studies to evaluate the usefulness of context information, based on: (1) region labeling of the surroundings of objects, (2) motion analysis of the water for moving ships, (3) traffic sign recognition for safety event evaluation and (4) the use of depth signals for obstacle detection. The chapter shows that the previous cases can be solved in an improved way with respect to robustness and semantic understanding. Case studies indicate up to 6.8% improvement of reliable correct object understanding and the novel possibility of labeling scene events as safe/unsafe depending on the object behavior and the detected surrounding context. In this chapter, it is shown that using contextual information improves automated video surveillance analysis, as it not only improves the reliability of moving object detection, but also enables scene understanding that is far beyond object understanding.

AB - Smart surveillance systems become more meaningful if they both grow in reliability and robustness, while simultaneously offering a higher semantic level of understanding. To achieve a higher level of semantic scene understanding, the objects and their actions have to be interpreted in the given context, so that the extraction of contextual information is required. This chapter explores several techniques for extracting the contextual information such as spatial, motion, depth and co-occurrence, depending on applications. Afterwards, the chapter provides specific case studies to evaluate the usefulness of context information, based on: (1) region labeling of the surroundings of objects, (2) motion analysis of the water for moving ships, (3) traffic sign recognition for safety event evaluation and (4) the use of depth signals for obstacle detection. The chapter shows that the previous cases can be solved in an improved way with respect to robustness and semantic understanding. Case studies indicate up to 6.8% improvement of reliable correct object understanding and the novel possibility of labeling scene events as safe/unsafe depending on the object behavior and the detected surrounding context. In this chapter, it is shown that using contextual information improves automated video surveillance analysis, as it not only improves the reliability of moving object detection, but also enables scene understanding that is far beyond object understanding.

UR - http://www.scopus.com/inward/record.url?scp=85015834246&partnerID=8YFLogxK

U2 - 10.4018/978-1-5225-0983-7.ch070

DO - 10.4018/978-1-5225-0983-7.ch070

M3 - Chapter

SN - 9781522509837

SP - 1656

EP - 1700

BT - Biometrics

PB - IGI Global

CY - s.l.

ER -

Javanbakhti S, Sanberg WP, Bao X, van de Wouw DWJM, Creusen I, Dubbelman G et al. Adding context information to video analysis for surveillance applications. In Biometrics: concepts, methodologies, tools, and applications. s.l.: IGI Global. 2016. p. 1656-1700. Available from, DOI: 10.4018/978-1-5225-0983-7.ch070