A Novel Deep Learner for Human Behavior Prediction Over Public Video Surveillance

Identifying human behavior effectively is essential for spotting anomalies in video surveillance systems, particularly in dynamic environments. Conventional methods frequently have significant false detection rates, which restricts their use. This paper proposes a unique framework to improve anomaly...

Full description

Saved in:
Bibliographic Details
Main Authors: Bayan Alabdullah, Bisma Batool Fatima, Haifa F. Alhasson, Mohammed Alshehri, Yahya AlQahtani, Nouf Albhassabi, Hui Liu
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11036735/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849434005663907840
author Bayan Alabdullah
Bisma Batool Fatima
Haifa F. Alhasson
Mohammed Alshehri
Yahya AlQahtani
Nouf Albhassabi
Hui Liu
author_facet Bayan Alabdullah
Bisma Batool Fatima
Haifa F. Alhasson
Mohammed Alshehri
Yahya AlQahtani
Nouf Albhassabi
Hui Liu
author_sort Bayan Alabdullah
collection DOAJ
description Identifying human behavior effectively is essential for spotting anomalies in video surveillance systems, particularly in dynamic environments. Conventional methods frequently have significant false detection rates, which restricts their use. This paper proposes a unique framework to improve anomaly classification by combining improved preprocessing, feature extraction, optimization methods, and Remote Field-Based (RFB) video sensors. This work’s primary contribution is the creation of an all-encompassing system that uses feature-driven learning and optimization to minimize false alarms and achieve high detection accuracy. The UBI-Fight and PETS2009 datasets, which are often used in surveillance applications for human behavior detection, are used as validation standards by the framework. Key frame extraction is the first step in the procedure, which is then followed by sophisticated preprocessing methods like illumination correction, occlusion control, and noise reduction. Harris corner detection, Histogram of Oriented Gradients (HOG), and Particle Gradient Motion Analysis (PGMA) are used to extract motion and spatial data. By capturing high-resolution motion dynamics for improved data collection, the integration of RFB video sensors improves motion analysis and behavioral evaluation. While Particle Swarm Optimization (PSO) optimizes the classifiers to increase accuracy, a deep learning classification strategy is used for anomaly classification. The suggested methodology outperforms conventional techniques, achieving 93.4% accuracy on the PETS2009 dataset and 89.2% accuracy on the UBI-Fight dataset. These outcomes show how well feature extraction and optimization work together to improve the recognition of human behavior. Reliable security monitoring is ensured by the framework’s scalability and real-time applicability, which also considerably reduce false alarms and offer strong performance in a variety of public safety scenarios.
format Article
id doaj-art-94ced1ceee604c9394d140e581672dff
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-94ced1ceee604c9394d140e581672dff2025-08-20T03:26:49ZengIEEEIEEE Access2169-35362025-01-011310871810873110.1109/ACCESS.2025.357974911036735A Novel Deep Learner for Human Behavior Prediction Over Public Video SurveillanceBayan Alabdullah0Bisma Batool Fatima1Haifa F. Alhasson2Mohammed Alshehri3Yahya AlQahtani4Nouf Albhassabi5Hui Liu6https://orcid.org/0000-0002-6850-9570Department of Information Systems, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh, Saudi ArabiaFaculty of Computing and AI, Air University, Islamabad, PakistanDepartment of Information Technology, College of Computer, Qassim University, Buraydah, Saudi ArabiaDepartment of Computer Science, King Khalid University, Abha, Saudi ArabiaDepartment of Informatics and Computer Systems, King Khalid University, Abha, Saudi ArabiaDepartment of Cyber Security, College of Humanities, Umm Al-Qura University, Makkah, Saudi ArabiaGuodian Nanjing Automation Company Ltd., Nanjing, ChinaIdentifying human behavior effectively is essential for spotting anomalies in video surveillance systems, particularly in dynamic environments. Conventional methods frequently have significant false detection rates, which restricts their use. This paper proposes a unique framework to improve anomaly classification by combining improved preprocessing, feature extraction, optimization methods, and Remote Field-Based (RFB) video sensors. This work’s primary contribution is the creation of an all-encompassing system that uses feature-driven learning and optimization to minimize false alarms and achieve high detection accuracy. The UBI-Fight and PETS2009 datasets, which are often used in surveillance applications for human behavior detection, are used as validation standards by the framework. Key frame extraction is the first step in the procedure, which is then followed by sophisticated preprocessing methods like illumination correction, occlusion control, and noise reduction. Harris corner detection, Histogram of Oriented Gradients (HOG), and Particle Gradient Motion Analysis (PGMA) are used to extract motion and spatial data. By capturing high-resolution motion dynamics for improved data collection, the integration of RFB video sensors improves motion analysis and behavioral evaluation. While Particle Swarm Optimization (PSO) optimizes the classifiers to increase accuracy, a deep learning classification strategy is used for anomaly classification. The suggested methodology outperforms conventional techniques, achieving 93.4% accuracy on the PETS2009 dataset and 89.2% accuracy on the UBI-Fight dataset. These outcomes show how well feature extraction and optimization work together to improve the recognition of human behavior. Reliable security monitoring is ensured by the framework’s scalability and real-time applicability, which also considerably reduce false alarms and offer strong performance in a variety of public safety scenarios.https://ieeexplore.ieee.org/document/11036735/Activity recognitionclassificationdeep learningobject recognitioncomputer visionstatistical methods and learning algorithms
spellingShingle Bayan Alabdullah
Bisma Batool Fatima
Haifa F. Alhasson
Mohammed Alshehri
Yahya AlQahtani
Nouf Albhassabi
Hui Liu
A Novel Deep Learner for Human Behavior Prediction Over Public Video Surveillance
IEEE Access
Activity recognition
classification
deep learning
object recognition
computer vision
statistical methods and learning algorithms
title A Novel Deep Learner for Human Behavior Prediction Over Public Video Surveillance
title_full A Novel Deep Learner for Human Behavior Prediction Over Public Video Surveillance
title_fullStr A Novel Deep Learner for Human Behavior Prediction Over Public Video Surveillance
title_full_unstemmed A Novel Deep Learner for Human Behavior Prediction Over Public Video Surveillance
title_short A Novel Deep Learner for Human Behavior Prediction Over Public Video Surveillance
title_sort novel deep learner for human behavior prediction over public video surveillance
topic Activity recognition
classification
deep learning
object recognition
computer vision
statistical methods and learning algorithms
url https://ieeexplore.ieee.org/document/11036735/
work_keys_str_mv AT bayanalabdullah anoveldeeplearnerforhumanbehaviorpredictionoverpublicvideosurveillance
AT bismabatoolfatima anoveldeeplearnerforhumanbehaviorpredictionoverpublicvideosurveillance
AT haifafalhasson anoveldeeplearnerforhumanbehaviorpredictionoverpublicvideosurveillance
AT mohammedalshehri anoveldeeplearnerforhumanbehaviorpredictionoverpublicvideosurveillance
AT yahyaalqahtani anoveldeeplearnerforhumanbehaviorpredictionoverpublicvideosurveillance
AT noufalbhassabi anoveldeeplearnerforhumanbehaviorpredictionoverpublicvideosurveillance
AT huiliu anoveldeeplearnerforhumanbehaviorpredictionoverpublicvideosurveillance
AT bayanalabdullah noveldeeplearnerforhumanbehaviorpredictionoverpublicvideosurveillance
AT bismabatoolfatima noveldeeplearnerforhumanbehaviorpredictionoverpublicvideosurveillance
AT haifafalhasson noveldeeplearnerforhumanbehaviorpredictionoverpublicvideosurveillance
AT mohammedalshehri noveldeeplearnerforhumanbehaviorpredictionoverpublicvideosurveillance
AT yahyaalqahtani noveldeeplearnerforhumanbehaviorpredictionoverpublicvideosurveillance
AT noufalbhassabi noveldeeplearnerforhumanbehaviorpredictionoverpublicvideosurveillance
AT huiliu noveldeeplearnerforhumanbehaviorpredictionoverpublicvideosurveillance