An Unsupervised Anomalous Event Detection Framework with Class Aware Source Separation

@article{Mudassar2018AnUA,
  title={An Unsupervised Anomalous Event Detection Framework with Class Aware Source Separation},
  author={Burhan Ahmad Mudassar and Jong Hwan Ko and Saibal Mukhopadhyay},
  journal={2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  year={2018},
  pages={2671-2675}
}
This paper presents a novel problem of detection and localization of anomalous events due to a certain class of objects in video data with applications to smart surveillance. A baseline system is proposed that uses a convolutional neural network (CNN) to generate pixel level masks corresponding to objects of a class of interest. A Restricted Boltzmann Machine (RBM) is then trained on the mask to learn patterns of normal behavior. The free energy of the RBM is used to detect the presence of an… CONTINUE READING

Similar Papers

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • We achieve an Equal Error Rate (EER) of 26.9% with 77.6 % Area Under the Curve (AUC).

References

Publications referenced by this paper.
SHOWING 1-10 OF 16 REFERENCES

Abnormal Event Detection at 150 FPS in MATLAB

  • 2013 IEEE International Conference on Computer Vision
  • 2013
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Anomaly detection in crowded scenes

  • 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 2010
VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

Learning Temporal Regularity in Video Sequences

  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
VIEW 3 EXCERPTS