TR2021-028

Perceptual Metric Learning for Video Anomaly Detection


    •  Ramachandra, B., Jones, M.J., Vatsavai, R., "Perceptual Metric Learning for Video Anomaly Detection", Machine Vision and Applications, DOI: 0.1007/​s00138-021-01187-5, Vol. 32, No. 63, pp. 1-18, March 2021.
      BibTeX TR2021-028 PDF
      • @article{Ramachandra2021mar,
      • author = {Ramachandra, Bharathkumar and Jones, Michael J. and Vatsavai, Ranga},
      • title = {Perceptual Metric Learning for Video Anomaly Detection},
      • journal = {Machine Vision and Applications},
      • year = 2021,
      • volume = 32,
      • number = 63,
      • pages = {1--18},
      • month = mar,
      • doi = {0.1007/s00138-021-01187-5},
      • url = {https://www.merl.com/publications/TR2021-028}
      • }
  • MERL Contact:
  • Research Areas:

    Artificial Intelligence, Computer Vision, Machine Learning

Abstract:

This work introduces a new approach to localize anomalies in surveillance video. The main novelty is the idea of using a Siamese convolutional neural network (CNN) to learn a metric between a pair of video patches (spatio-temporal regions of video). The learned metric, which is not specific to the target video, is used to measure the perceptual distance between each video patch in the testing video and the video patches found in normal training video. If a testing video patch is far from all normal video patches then it must be anomalous. We further generalize the approach from operating on video patches from a fixed grid to arbitrary-sized region proposals. We compare our approaches to previously published algorithms using 4 evaluation measures and 3 challenging target benchmark datasets. Experiments show that our approaches either surpass or perform comparably to current state-of-the-art methods whilst enjoying other favorable properties.