@article{8720515,
  abstract     = {{Automating the analysis of surveillance video footage is of great interest when urban environments or industrial sites are monitored by a large number of cameras. As anomalies are often context-specific, it is hard to predefine events of interest and collect labeled training data. A purely unsupervised approach for automated anomaly detection is much more suitable. For every camera, a separate algorithm could then be deployed that learns over time a baseline model of appearance and motion related features of the objects within the camera viewport. Anything that deviates from this baseline is flagged as an anomaly for further analysis downstream. We propose a new neural network architecture that learns the normal behavior in a purely unsupervised fashion. In contrast to previous work, we use latent code predictions as our anomaly metric. We show that this outperforms frame reconstruction-based and prediction-based methods on different benchmark datasets both in terms of accuracy and robustness against changing lighting and weather conditions. By decoupling an appearance and a motion model, our model can also process 16 to 45 times more frames per second than related approaches which makes our model suitable for deploying on the camera itself or on other edge devices.}},
  articleno    = {{103249}},
  author       = {{Li, Bo and Leroux, Sam and Simoens, Pieter}},
  issn         = {{1077-3142}},
  journal      = {{COMPUTER VISION AND IMAGE UNDERSTANDING}},
  keywords     = {{Anomaly detection,Surveillance video,Unsupervised learning}},
  language     = {{eng}},
  pages        = {{8}},
  title        = {{Decoupled appearance and motion learning for efficient anomaly detection in surveillance video}},
  url          = {{http://doi.org/10.1016/j.cviu.2021.103249}},
  volume       = {{210}},
  year         = {{2021}},
}

Altmetric

View in Altmetric

Web of Science

Times cited: