Lightweight deep models for video anomaly detection: a comparative study of autoencoders and MobileNetV2 on the avenue dataset
New Trends in Computer Sciences · 2025
DOI: 10.3846/ntcs.2025.25567 ↗Kurz gefasst
Fachartikel in der Zeitschrift New Trends in Computer Sciences, 2025. Verfasst von SeyedMohammad Vahedi und 1 weiteren Autor:innen. Die Arbeit nennt 32 Literaturangaben.
Abstract (Originalsprache)
Video anomaly detection aims to identify unusual events in surveillance footage, yet many existing deep learning solutions remain too computationally heavy for real-time deployment on resource-limited hardware. This study presents a systematic comparison of three lightweight deep learning models for frame-level anomaly detection on the Avenue dataset, including a baseline 2D convolutional autoencoder, an enhanced reconstruction-based autoencoder with refined feature representation and decoding strategy, and a MobileNetV2-based supervised classifier fine-tuned for anomaly recognition. The baseline autoencoder achieves moderate detection performance, with an approximately AUC of 0.75. In contrast, the enhanced autoencoder improves reconstruction quality and raises the AUC to approximately 0.84 through more effective feature abstraction rather than increased architectural depth. The strongest results are obtained by the MobileNetV2 classifier, which achieves an AUC close to 0.99, high precision and recall, and a stable confusion matrix. These results demonstrate that lightweight architectures, when combined with appropriate training strategies and careful handling of class imbalance, can outperform more complex models. Overall, the study confirms that architectural efficiency and learning paradigm selection are more critical than model depth alone, making lightweight models well-suited to practical, real-time video anomaly detection scenarios. First published online 02 February 2026
Zitieren
APA
Vahedi, S., & Stefanovič, P. (2025). Lightweight deep models for video anomaly detection: a comparative study of autoencoders and MobileNetV2 on the avenue dataset. New Trends in Computer Sciences. https://doi.org/10.3846/ntcs.2025.25567
Vancouver
Vahedi S, Stefanovič P. Lightweight deep models for video anomaly detection: a comparative study of autoencoders and MobileNetV2 on the avenue dataset. New Trends in Computer Sciences. 2025. doi:10.3846/ntcs.2025.25567
BibTeX
@article{Vahedi2025,
author = {Vahedi, SeyedMohammad and Stefanovič, Pavel},
title = {Lightweight deep models for video anomaly detection: a comparative study of autoencoders and MobileNetV2 on the avenue dataset},
journal = {New Trends in Computer Sciences},
year = {2025},
doi = {10.3846/ntcs.2025.25567}
}
EUVIMED