Advanced Intelligent Monitoring Systems for Traffic Scene Analysis and Anomaly Detection

Mahbod, Abbas

Advanced Intelligent Monitoring Systems for Traffic Scene Analysis and Anomaly Detection

dc.contributor.advisor	Leung, Henry
dc.contributor.author	Mahbod, Abbas
dc.contributor.committeemember	Behjat, Laleh
dc.contributor.committeemember	Yanushkevich, Svetlana
dc.date	2025-05
dc.date.accessioned	2024-12-24T16:24:58Z
dc.date.available	2024-12-24T16:24:58Z
dc.date.issued	2024-12-20
dc.description.abstract	This thesis presents an advanced Intelligent Monitoring System (IMS) specifically designed for comprehensive traffic scene analysis and video anomaly detection. As urban environments increasingly depend on CCTV technology, the demand for automated systems capable of efficiently analyzing vast amounts of video data has become critical. The proposed IMS integrates both appearance and motion analysis modules, enabling the effective monitoring of traffic environments. By extracting features in different levels, the proposed system facilitates accurate detection and localization of objects within dynamic scenes. A key innovation of this research is the development of a novel anomaly detection algorithm that classifies detected anomalies into three categories: point, collective, and contextual. This classification is further enhanced by investigating the underlying causes of anomalies, providing deeper insights into abnormal behaviors within traffic scenarios. The system also employs multiple assessment baselines, allowing for adaptive analysis of incoming video frames, which enables the differentiation of anomalies that may be deemed normal in one context but anomalous in another. Extensive simulations conducted on real-world datasets, including data from the City of Calgary, showcase the significant advancements in detection performance achieved by the proposed methodologies. The proposed IMS not only processes individual frames but also generates comprehensive reports detailing object detection, classification, and motion characteristics. By effectively distinguishing between different types of anomalies and considering multiple baselines, the system provides valuable insights into traffic behaviors and incident responses. Overall, this research contributes a robust end-to-end IMS equipped with a cutting-edge anomaly detection algorithm that surpasses traditional methods, establishing a versatile framework for real-time video monitoring applications. This work lays a strong foundation for future advancements in intelligent surveillance systems, ultimately contributing to improved urban traffic management and safety.
dc.identifier.citation	Mahbod, A. (2024). Advanced intelligent monitoring systems for traffic scene analysis and anomaly detection (Doctoral thesis, University of Calgary, Calgary, Canada). Retrieved from https://prism.ucalgary.ca.
dc.identifier.uri	https://hdl.handle.net/1880/120293
dc.language.iso	en
dc.publisher.faculty	Graduate Studies
dc.publisher.institution	University of Calgary
dc.rights	University of Calgary graduate students retain copyright ownership and moral rights for their thesis. You may use this material in any way that is permitted by the Copyright Act or through licensing that has been assigned to the document. For uses that are not allowable under copyright legislation or licensing, you are required to seek permission.
dc.subject	Intelligent Monitoring System
dc.subject	Anaomly Detection
dc.subject	Deep Learning
dc.subject	Machine Learning
dc.subject	Computer Vision
dc.subject.classification	Education--Technology
dc.title	Advanced Intelligent Monitoring Systems for Traffic Scene Analysis and Anomaly Detection
dc.type	doctoral thesis
thesis.degree.discipline	Engineering – Electrical & Computer
thesis.degree.grantor	University of Calgary
thesis.degree.name	Doctor of Philosophy (PhD)
ucalgary.thesis.accesssetbystudent	I do not require a thesis withhold – my thesis will have open access and can be viewed and downloaded publicly as soon as possible.