Detection of snatch theft based on temporal differences in motion flow field orientation histograms

Norazlin Ibrahim, Mohd. Marzuki Mustafa, Siti Salasiah Mokri, Lee Yee Siong, Aini Hussain

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

This paper presents a technique for detecting abnormal pedestrian movement for use in video surveillance to automatically detect snatch theft. The proposed technique is based on analysis of the global motion pattern of pixels prior to and after the moment preceding the event that is considered a necessary condition for snatch theft. This technique is based on the premise that the scenes prior to and after snatching will have different movement patterns. Compared to high-level feature detection algorithms which identify and track behavior of individual persons in a scene, the use of low-level features in this technique results in more robust detection as it can handle images where individual pedestrians cannot be properly segmented due to occlusion and other environmental factors. Based on experiments, we are able to detect snatch crime events at a higher rate than other techniques.

Original languageEnglish
Pages (from-to)308-317
Number of pages10
JournalInternational Journal of Advancements in Computing Technology
Volume4
Issue number12
DOIs
Publication statusPublished - Jun 2012

Fingerprint

Crime
Flow fields
Pixels
Experiments

Keywords

  • Low level features
  • Optical flow
  • Snatch theft

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

@article{cb159f05bb8549eca646915587397bbc,
title = "Detection of snatch theft based on temporal differences in motion flow field orientation histograms",
abstract = "This paper presents a technique for detecting abnormal pedestrian movement for use in video surveillance to automatically detect snatch theft. The proposed technique is based on analysis of the global motion pattern of pixels prior to and after the moment preceding the event that is considered a necessary condition for snatch theft. This technique is based on the premise that the scenes prior to and after snatching will have different movement patterns. Compared to high-level feature detection algorithms which identify and track behavior of individual persons in a scene, the use of low-level features in this technique results in more robust detection as it can handle images where individual pedestrians cannot be properly segmented due to occlusion and other environmental factors. Based on experiments, we are able to detect snatch crime events at a higher rate than other techniques.",
keywords = "Low level features, Optical flow, Snatch theft",
author = "Norazlin Ibrahim and Mustafa, {Mohd. Marzuki} and Mokri, {Siti Salasiah} and Siong, {Lee Yee} and Aini Hussain",
year = "2012",
month = "6",
doi = "10.4156/ijact.vol4.issue 12.36",
language = "English",
volume = "4",
pages = "308--317",
journal = "International Journal of Advancements in Computing Technology",
issn = "2005-8039",
publisher = "Advanced Institute of Convergence Information Technology Research Center",
number = "12",

}

TY - JOUR

T1 - Detection of snatch theft based on temporal differences in motion flow field orientation histograms

AU - Ibrahim, Norazlin

AU - Mustafa, Mohd. Marzuki

AU - Mokri, Siti Salasiah

AU - Siong, Lee Yee

AU - Hussain, Aini

PY - 2012/6

Y1 - 2012/6

N2 - This paper presents a technique for detecting abnormal pedestrian movement for use in video surveillance to automatically detect snatch theft. The proposed technique is based on analysis of the global motion pattern of pixels prior to and after the moment preceding the event that is considered a necessary condition for snatch theft. This technique is based on the premise that the scenes prior to and after snatching will have different movement patterns. Compared to high-level feature detection algorithms which identify and track behavior of individual persons in a scene, the use of low-level features in this technique results in more robust detection as it can handle images where individual pedestrians cannot be properly segmented due to occlusion and other environmental factors. Based on experiments, we are able to detect snatch crime events at a higher rate than other techniques.

AB - This paper presents a technique for detecting abnormal pedestrian movement for use in video surveillance to automatically detect snatch theft. The proposed technique is based on analysis of the global motion pattern of pixels prior to and after the moment preceding the event that is considered a necessary condition for snatch theft. This technique is based on the premise that the scenes prior to and after snatching will have different movement patterns. Compared to high-level feature detection algorithms which identify and track behavior of individual persons in a scene, the use of low-level features in this technique results in more robust detection as it can handle images where individual pedestrians cannot be properly segmented due to occlusion and other environmental factors. Based on experiments, we are able to detect snatch crime events at a higher rate than other techniques.

KW - Low level features

KW - Optical flow

KW - Snatch theft

UR - http://www.scopus.com/inward/record.url?scp=84864584195&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84864584195&partnerID=8YFLogxK

U2 - 10.4156/ijact.vol4.issue 12.36

DO - 10.4156/ijact.vol4.issue 12.36

M3 - Article

AN - SCOPUS:84864584195

VL - 4

SP - 308

EP - 317

JO - International Journal of Advancements in Computing Technology

JF - International Journal of Advancements in Computing Technology

SN - 2005-8039

IS - 12

ER -