ADNet: Temporal Anomaly Detection in Surveillance Videos
25th International Conference on Pattern Recognition Workshops, ICPR 2021, Virtual, Online, İtalya, 10 - 15 Ocak 2021, cilt.12664 LNCS, ss.88-101, (Tam Metin Bildiri)
- Yayın Türü: Bildiri / Tam Metin Bildiri
- Cilt numarası: 12664 LNCS
- Doi Numarası: 10.1007/978-3-030-68799-1_7
- Basıldığı Şehir: Virtual, Online
- Basıldığı Ülke: İtalya
- Sayfa Sayıları: ss.88-101
- Anahtar Kelimeler: Surveillance videos, Temporal anomaly detection, Temporal anomaly localization
- Açık Arşiv Koleksiyonu: AVESİS Açık Erişim Koleksiyonu
- Hacettepe Üniversitesi Adresli: Evet
Özet
Anomaly detection in surveillance videos is an important research problem in computer vision. In this paper, we propose ADNet, an anomaly detection network, which utilizes temporal convolutions to localize anomalies in videos. The model works online by accepting consecutive windows of video clips. Features extracted from video clips in a window are fed to ADNet, which allows to localize anomalies in videos effectively. We propose the AD Loss function to improve abnormal segment detection performance of ADNet. Additionally, we propose to use F1@k metric for temporal anomaly detection. F1@k is a better evaluation metric than AUC in terms of not penalizing minor shifts in temporal segments and punishing short false positive temporal segment predictions. Furthermore, we extend UCF Crime [29] dataset by adding two more anomaly classes and providing temporal anomaly annotations for all classes. Finally, we thoroughly evaluate our model on the extended UCF Crime dataset. ADNet produces promising results with respect to F1@k metric. Code and dataset extensions are publicly at https://github.com/hibrahimozturk/temporal_anomaly_detection.