A Unified GAN-Based Framework for Unsupervised Video Anomaly Detection Using Optical Flow and RGB Cues
Sensors · 19.09.2025 · 25 (18) · 5869
DOI: 10.3390/s25185869 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 19.09.2025. Verfasst von Seung-Hun Kang und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Information and Communication Engineering, School of Electrical and Computer Engineering, Chungbuk National University, Cheongju-si 286…. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Basic Science Research Program through the National Research Foundation of Korea (NRF), funded by the Ministry of Education, partly by the Innovative Human Resource Development for Local Intellectualization program through the Institute of Information & Communications Technology Plan…, Ministry of Science and ICT.
Abstract (Originalsprache)
Video anomaly detection in unconstrained environments remains a fundamental challenge due to the scarcity of labeled anomalous data and the diversity of real-world scenarios. To address this, we propose a novel unsupervised framework that integrates RGB appearance and optical flow motion via a unified GAN-based architecture. The generator features a dual encoder and a GRU–attention temporal bottleneck, while the discriminator employs ConvLSTM layers and residual-enhanced MLPs to evaluate temporal coherence. To improve training stability and reconstruction quality, we introduce DASLoss—a composite loss that incorporates pixel, perceptual, temporal, and feature consistency terms. Experiments were conducted on three benchmark datasets. On XD-Violence, our model achieves an Average Precision (AP) of 80.5%, outperforming other unsupervised methods such as MGAFlow and Flashback. On Hockey Fight, it achieves an AUC of 0.92 and an F1-score of 0.85, demonstrating strong performance in detecting short-duration violent events. On UCSD Ped2, our model attains an AUC of 0.96, matching several state-of-the-art models despite using no supervision. These results confirm the effectiveness and generalizability of our approach in diverse anomaly detection settings.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Information and Communication Engineering, School of Electrical and Computer Engineering, Chungbuk National University, Cheongju-si 28644, Republic of Korea.
ORCID-Profile: Seung-Hun Kang, Hyun-Soo Kang
Förderung
- the Basic Science Research Program through the National Research Foundation of Korea (NRF), funded by the Ministry of Education
- partly by the Innovative Human Resource Development for Local Intellectualization program through the Institute of Information & Communications Technology Plan…
- Ministry of Science and ICT
- Innovative Human Resource Development for Local Intellectualization program through the Institute of Information & Communications Technology Planning &…
Zitieren
APA
Kang, S. H., & Kang, H. S. (2025). A Unified GAN-Based Framework for Unsupervised Video Anomaly Detection Using Optical Flow and RGB Cues. Sensors, 25(18), 5869. https://doi.org/10.3390/s25185869
Vancouver
Kang SH, Kang HS. A Unified GAN-Based Framework for Unsupervised Video Anomaly Detection Using Optical Flow and RGB Cues. Sensors. 2025;25(18):5869. doi:10.3390/s25185869
BibTeX
@article{Kang2025,
author = {Kang, Seung-Hun and Kang, Hyun-Soo},
title = {A Unified GAN-Based Framework for Unsupervised Video Anomaly Detection Using Optical Flow and RGB Cues},
journal = {Sensors},
year = {2025},
volume = {25},
number = {18},
pages = {5869},
doi = {10.3390/s25185869}
}
EUVIMED