Unsupervised video anomaly detection via normalizing flows with implicit latent features

Myeong Ah Cho, Taeoh Kim, Woo Jin Kim, Suhwan Cho, Sangyoun Lee

Research output: Contribution to journalArticlepeer-review

27 Citations (Scopus)

Abstract

In contemporary society, surveillance anomaly detection, i.e., spotting anomalous events such as crimes or accidents in surveillance videos, is a critical task. As anomalies occur rarely, most training data consists of unlabeled videos without anomalous events, which makes the task challenging. Most existing methods use an autoencoder (AE) to learn to reconstruct normal videos; they then detect anomalies based on their failure to reconstruct the appearance of abnormal scenes. However, because anomalies are distinguished by appearance as well as motion, many previous approaches have explicitly separated appearance and motion informationfor example, using a pre-trained optical flow model. This explicit separation restricts reciprocal representation capabilities between two types of information. In contrast, we propose an implicit two-path AE (ITAE), a structure in which two encoders implicitly model appearance and motion features, along with a single decoder that combines them to learn normal video patterns. For the complex distribution of normal scenes, we suggest normal density estimation of ITAE features through normalizing flow (NF)-based generative models to learn the tractable likelihoods and identify anomalies using out-of-distribution detection. NF models intensify ITAE performance by learning normality through implicitly learned features. Finally, we demonstrate the effectiveness of ITAE and its feature distribution modeling on six benchmarks, including databases that contain various anomalies in real-world scenarios.

Original languageEnglish
Article number108703
JournalPattern Recognition
Volume129
DOIs
Publication statusPublished - 2022 Sept

Bibliographical note

Publisher Copyright:
© 2022

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Unsupervised video anomaly detection via normalizing flows with implicit latent features'. Together they form a unique fingerprint.

Cite this