Suspicious Behavior Detection with Temporal Feature Extraction and Time-Series Classification for Shoplifting Crime Prevention

The rise in crime rates in many parts of the world, coupled with advancements in computer vision, has increased the need for automated crime detection services. To address this issue, we propose a new approach for detecting suspicious behavior as a means of preventing shoplifting. Existing methods a...

Full description

Saved in:
Bibliographic Details
Main Author: Nazir, Amril (author)
Other Authors: Mitra, Rohan (author), Sulieman, Hana (author), Kamalov, Firuz (author)
Format: article
Published: 2023
Subjects:
Online Access:https://hdl.handle.net/11073/32529
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513432873598976
author Nazir, Amril
author2 Mitra, Rohan
Sulieman, Hana
Kamalov, Firuz
author2_role author
author
author
author_facet Nazir, Amril
Mitra, Rohan
Sulieman, Hana
Kamalov, Firuz
author_role author
dc.creator.none.fl_str_mv Nazir, Amril
Mitra, Rohan
Sulieman, Hana
Kamalov, Firuz
dc.date.none.fl_str_mv 2023
2025-12-08T07:05:01Z
2025-12-08T07:05:01Z
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv Nazir, A.; Mitra, R.; Sulieman, H.; Kamalov, F. Suspicious Behavior Detection with Temporal Feature Extraction and Time-Series Classification for Shoplifting Crime Prevention. Sensors 2023, 23, 5811. https://doi.org/10.3390/s23135811
1424-8220
https://hdl.handle.net/11073/32529
10.3390/s23135811
dc.language.none.fl_str_mv en_US
dc.publisher.none.fl_str_mv MDPI
dc.relation.none.fl_str_mv https://doi.org/10.3390/s23135811
dc.subject.none.fl_str_mv Automated crime detection
Suspicious behavior
Crime prevention
Temporal features
Time-series classification
dc.title.none.fl_str_mv Suspicious Behavior Detection with Temporal Feature Extraction and Time-Series Classification for Shoplifting Crime Prevention
dc.type.none.fl_str_mv Peer-Reviewed
Published version
info:eu-repo/semantics/publishedVersion
info:eu-repo/semantics/article
description The rise in crime rates in many parts of the world, coupled with advancements in computer vision, has increased the need for automated crime detection services. To address this issue, we propose a new approach for detecting suspicious behavior as a means of preventing shoplifting. Existing methods are based on the use of convolutional neural networks that rely on extracting spatial features from pixel values. In contrast, our proposed method employs object detection based on YOLOv5 with Deep Sort to track people through a video, using the resulting bounding box coordinates as temporal features. The extracted temporal features are then modeled as a time-series classification problem. The proposed method was tested on the popular UCF Crime dataset, and benchmarked against the current state-of-the-art robust temporal feature magnitude (RTFM) method, which relies on the Inflated 3D ConvNet (I3D) preprocessing method. Our results demonstrate an impressive 8.45-fold increase in detection inference speed compared to the state-of-the-art RTFM, along with an F1 score of 92%,outperforming RTFM by 3%. Furthermore, our method achieved these results without requiring expensive data augmentation or image feature extraction.
format article
id aus_47b1d567a1bf6d61d062fb744c059703
identifier_str_mv Nazir, A.; Mitra, R.; Sulieman, H.; Kamalov, F. Suspicious Behavior Detection with Temporal Feature Extraction and Time-Series Classification for Shoplifting Crime Prevention. Sensors 2023, 23, 5811. https://doi.org/10.3390/s23135811
1424-8220
10.3390/s23135811
language_invalid_str_mv en_US
network_acronym_str aus
network_name_str aus
oai_identifier_str oai:repository.aus.edu:11073/32529
publishDate 2023
publisher.none.fl_str_mv MDPI
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
spelling Suspicious Behavior Detection with Temporal Feature Extraction and Time-Series Classification for Shoplifting Crime PreventionNazir, AmrilMitra, RohanSulieman, HanaKamalov, FiruzAutomated crime detectionSuspicious behaviorCrime preventionTemporal featuresTime-series classificationThe rise in crime rates in many parts of the world, coupled with advancements in computer vision, has increased the need for automated crime detection services. To address this issue, we propose a new approach for detecting suspicious behavior as a means of preventing shoplifting. Existing methods are based on the use of convolutional neural networks that rely on extracting spatial features from pixel values. In contrast, our proposed method employs object detection based on YOLOv5 with Deep Sort to track people through a video, using the resulting bounding box coordinates as temporal features. The extracted temporal features are then modeled as a time-series classification problem. The proposed method was tested on the popular UCF Crime dataset, and benchmarked against the current state-of-the-art robust temporal feature magnitude (RTFM) method, which relies on the Inflated 3D ConvNet (I3D) preprocessing method. Our results demonstrate an impressive 8.45-fold increase in detection inference speed compared to the state-of-the-art RTFM, along with an F1 score of 92%,outperforming RTFM by 3%. Furthermore, our method achieved these results without requiring expensive data augmentation or image feature extraction.American University of SharjahZayed UniversityMDPI2025-12-08T07:05:01Z2025-12-08T07:05:01Z2023Peer-ReviewedPublished versioninfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfNazir, A.; Mitra, R.; Sulieman, H.; Kamalov, F. Suspicious Behavior Detection with Temporal Feature Extraction and Time-Series Classification for Shoplifting Crime Prevention. Sensors 2023, 23, 5811. https://doi.org/10.3390/s231358111424-8220https://hdl.handle.net/11073/3252910.3390/s23135811en_UShttps://doi.org/10.3390/s23135811oai:repository.aus.edu:11073/325292025-12-08T11:21:28Z
spellingShingle Suspicious Behavior Detection with Temporal Feature Extraction and Time-Series Classification for Shoplifting Crime Prevention
Nazir, Amril
Automated crime detection
Suspicious behavior
Crime prevention
Temporal features
Time-series classification
status_str publishedVersion
title Suspicious Behavior Detection with Temporal Feature Extraction and Time-Series Classification for Shoplifting Crime Prevention
title_full Suspicious Behavior Detection with Temporal Feature Extraction and Time-Series Classification for Shoplifting Crime Prevention
title_fullStr Suspicious Behavior Detection with Temporal Feature Extraction and Time-Series Classification for Shoplifting Crime Prevention
title_full_unstemmed Suspicious Behavior Detection with Temporal Feature Extraction and Time-Series Classification for Shoplifting Crime Prevention
title_short Suspicious Behavior Detection with Temporal Feature Extraction and Time-Series Classification for Shoplifting Crime Prevention
title_sort Suspicious Behavior Detection with Temporal Feature Extraction and Time-Series Classification for Shoplifting Crime Prevention
topic Automated crime detection
Suspicious behavior
Crime prevention
Temporal features
Time-series classification
url https://hdl.handle.net/11073/32529