Anomaly Detection in Surveillance Videos by Future Appearance-motion Prediction - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Anomaly Detection in Surveillance Videos by Future Appearance-motion Prediction

Résumé

Anomaly detection in surveillance videos is the identification of rare events which produce different features from normal events. In this paper, we present a survey about the progress of anomaly detection techniques and introduce our proposed framework to tackle this very challenging objective. Our approach is based on the more recent state-of-the-art techniques and casts anomalous events as unexpected events in future frames. Our framework is so flexible that you can replace almost important modules by existing state-of-the-art methods. The most popular solutions only use future predicted information as constraints for training a convolutional encode-decode network to reconstruct frames and take the score of the difference between both original and reconstructed information. We propose a fully future prediction based framework that directly defines the feature as the difference between both future predictions and ground truth information. This feature can be fed into various types of learning model to assign anomaly label. We present our experimental plan and argue that our framework’s performance will be competitive with state-of-the art scores by presenting early promising results in feature extraction.
Fichier principal
Vignette du fichier
91467.pdf (1.09 Mo) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-04490869 , version 1 (05-03-2024)

Licence

Copyright (Tous droits réservés)

Identifiants

Citer

Tuan-Hung Vu, Sebastien Ambellouis, Jacques Boonaert, Abdelmalik Taleb-Ahmed. Anomaly Detection in Surveillance Videos by Future Appearance-motion Prediction. 15th International Conference on Computer Vision Theory and Applications, Feb 2020, Valletta, France. pp.484-490, ⟨10.5220/0009146704840490⟩. ⟨hal-04490869⟩
12 Consultations
8 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More