EOGT: Video Anomaly Detection with Enhanced Object Information and Global Temporal Dependency
ACM Transactions on Multimedia Computing, Communications, and Applications · 31.10.2024 · 20 (10) · 1-21
DOI: 10.1145/3662185 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Multimedia Computing, Communications, and Applications, online erschienen am 12.09.2024. Verfasst von Ruoyan Pi und 3 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 75 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Video anomaly detection (VAD) aims to identify events or scenes in videos that deviate from typical patterns. Existing approaches primarily focus on reconstructing or predicting frames to detect anomalies and have shown improved performance in recent years. However, they often depend highly on local spatio-temporal information and face the challenge of insufficient object feature modeling. To address the above issues, this article proposes a video anomaly detection framework with E nhanced O bject Information and G lobal T emporal Dependencies (EOGT) and the main novelties are: (1) A L ocal O bject A nomaly S tream (LOAS) is proposed to extract local multimodal spatio-temporal anomaly features at the object level. LOAS integrates two modules: a D iffusion-based O bject R econstruction N etwork (DORN) with multimodal conditions detects anomalies with object RGB information; and an O bject P ose A nomaly Refiner (OPA) discovers anomalies with human pose information. (2) A G lobal T emporal S trengthening S tream (GTSS) with video-level temporal dependencies is proposed, which leverages video-level temporal dependencies to identify long-term and video-specific anomalies effectively. Both streams are jointly employed in EOGT to learn multimodal and multi-scale spatio-temporal anomaly features for VAD, and we finally fuse the anomaly features and scores to detect anomalies at the frame level. Extensive experiments are conducted to verify the performance of EOGT on three public datasets: ShanghaiTech Campus, CUHK Avenue, and UCSD Ped2.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Pi, R., Wu, P., He, X., & Peng, Y. (2024). EOGT: Video Anomaly Detection with Enhanced Object Information and Global Temporal Dependency. ACM Transactions on Multimedia Computing, Communications, and Applications, 20(10), 1-21. https://doi.org/10.1145/3662185
Vancouver
Pi R, Wu P, He X, Peng Y. EOGT: Video Anomaly Detection with Enhanced Object Information and Global Temporal Dependency. ACM Transactions on Multimedia Computing, Communications, and Applications. 2024;20(10):1-21. doi:10.1145/3662185
BibTeX
@article{Pi2024,
author = {Pi, Ruoyan and Wu, Peng and He, Xiangteng and Peng, Yuxin},
title = {EOGT: Video Anomaly Detection with Enhanced Object Information and Global Temporal Dependency},
journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
year = {2024},
volume = {20},
number = {10},
pages = {1--21},
doi = {10.1145/3662185}
}
EUVIMED