Unsupervised Discovery of Normal and Abnormal Activity Patterns in Indoor and Outdoor Environments

Dario Dotti, Mirela Popa, Stylianos Asteriadis

2017

Abstract

In this paper we propose an adaptive system for monitoring indoor and outdoor environments using movement patterns. Our system is able to discover normal and abnormal activity patterns in absence of any prior knowledge. We employ several feature descriptors, by extracting both spatial and temporal cues from trajectories over a spatial grid. Moreover, we improve the initial feature vectors by applying sparse autoencoders, which help at obtaining optimized and compact representations and improved accuracy. Next, activity models are learnt in an unsupervised manner using clustering techniques. The experiments are performed on both indoor and outdoor datasets. The obtained results prove the suitability of the proposed system, achieving an accuracy of over 98% in classifying normal vs. abnormal activity patterns for both scenarios. Furthermore, a semantic interpretation of the most important regions of the scene is obtained without the need of human labels, highlighting the flexibility of our method.

References

  1. Abrams, A., Tucek, J., Jacobs, N., and Pless, R. (2012). LOST: Longterm Observation of Scenes (with Tracks). In IEEE Workshop on Applications of Computer Vision (WACV), pages 297-304.
  2. Bermejo, E., Deniz, O., Bueno, G., and Sukthankar, R. (2011). Violence detection in video using computer vision techniques. In Int. Conf. on Computer Analysis of Images and Patterns, pages 332-339.
  3. Deng, Z.-A., Hu, Y., Yu, J., and Na, Z. (2015). Extended Kalman filter for real time indoor localization by fusing WiFi and smartphone inertial sensors. Micromachines, 6:523-543.
  4. Efros, A., Berg, A., Mori, G., and Malik, J. (2003). Recognizing action at a distance. In IEEE Int. Conf. on Computer Vision, pages 726-733.
  5. Hoque, E., Dickerson, R. F., Preum, S. M., Hanson, M., Barth, A., and Stankovic, J. A. (2015). Holmes: A comprehensive anomaly detection system for daily inhome activities. In 11th IEEE Int. Conf. on Distributed Computing in Sensor Systems.
  6. Jiang, F., Wu, Y., and Katsaggelos, A. K. (2009). A dynamic hierarchical clustering method for trajectorybased unusual video event detection. IEEE Trans. on Image Processing, 18(4):907-913.
  7. Kasteren, T. v., Englebienne, G., and Krse, B. (2010). Activity recognition using semi-markov models on real world smart home datasets. J. Ambient Intell. Smart Environ., 2:311-325.
  8. Li, W., Mahadevan, V., and Vasconcelos, N. (2014). Anomaly detection and localization in crowded scenes. IEEE Trans. on Pattern Analysis and Machine Intelligence (PAMI), 36(1):18-32.
  9. Masci, J., Meier, U., Ciresan, D., and Schmidhuber, J. (2011). Stacked convolutional auto-encoders for hierarchical feature extraction. In 21th Int. Conf. on Artificial Neural Networks (ICAN'11) , pages 52-59.
  10. Mousavi, H., M., Perina, A., Chellali, R., and Mur, V. (2015). Analyzing tracklets for the detection of abnormal crowd behavior. In Proc. of the IEEE Winter Conf. on Applications of Computer Vision (WACV 2015), pages 148-155.
  11. Nef, T., Urwyler, P., Bchler, M., Tarnanas, I., Stucki, R., Cazzoli, D., Mri, R., and Mosimann, U. (2015). Evaluation of Three State-of-the-Art Classifiers for Recognition of Activities of Daily Living from Smart Home Ambient Data. Sensors, 15(5):11725-11740.
  12. Ngiam, J., Khosla, A., and Kim, M. (2010). Multimodal deep learning. NIPS 2010 Workshop on Deep Learning and Unsupervised Feature Learning, pages 1-9.
  13. Nievas, E. B., Suarez, O. D., GarcĂ­a, G. B., and Sukthankar, R. (2011). Violence detection in video using computer vision techniques. In Proc. of the 14th Int. Conf. on Computer Analysis of Images and Patterns (CAIP'11), pages 332-339.
  14. Paliyawan, P., Nukoolkit, C., and Mongkolnam, P. (2014). Prolonged Sitting Detection for Office Workers Syndrome Prevention Using Kinect. In 11th Int. Conf. on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON), pages 1-6.
  15. Raptis, M. and Soatto, S. (2010). Tracklet descriptors for action modeling and video analysis. Lecture Notes in Computer Science (LNCS), 6311:577-590.
  16. Saenz-de Urturi, Z. and Soto, G. Z. B. (2016). Kinect-Based Virtual Game for the Elderly that Detects Incorrect Body Postures in Real Time. Sensors, 16(5).
  17. See, J. and Tan, S. (2014). Lost World: Looking for Anomalous Tracks in Long-term Surveillance Videos. In Proc. of the Image and Vision Computing New Zealand (IVCNZ), pages 224-229.
  18. Shin, J., Kim, S., Kang, S., Lee, S.-W., Paik, J., Abidi, B., and Abidi, M. (2005). Optical flow-based real-time object tracking using non-prior training active feature model. RealTime Imaging, 11(3):204-218.
  19. Uribe-Quevedo, A., Perez-Gutierrez, B., and GuerreroRincon, C. (2013). Seated tracking for correcting computer work postures. In 29th Southern Biomedical Engineering Conf. (SBEC), pages 169-170.
  20. Wong, K. B.-Y., Zhang, T., and Aghajan, H. (2014). Data Fusion with a Dense Sensor Network for Anomaly Detection in Smart Homes. Human Behavior Understanding in Networked Sensing, pages 45-73.
  21. Yang, L., Ren, Y., and Zhang, W. (2016). 3D depth image analysis for indoor fall detection of elderly people. Digital Communications and Networks, 2(1):24-34.
  22. Zhou, Z., Chen, X., Chung, Y.-C., He, Z., Han, T. X., and Keller, J. M. (2008). Activity analysis, summarization, and visualization for indoor human activity monitoring. IEEE Trans. on Circuits and Systems for Video Technology, 18(11):1489-1498.
Download


Paper Citation


in Harvard Style

Dotti D., Popa M. and Asteriadis S. (2017). Unsupervised Discovery of Normal and Abnormal Activity Patterns in Indoor and Outdoor Environments . In Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, (VISIGRAPP 2017) ISBN 978-989-758-226-4, pages 210-217. DOI: 10.5220/0006116902100217


in Bibtex Style

@conference{visapp17,
author={Dario Dotti and Mirela Popa and Stylianos Asteriadis},
title={Unsupervised Discovery of Normal and Abnormal Activity Patterns in Indoor and Outdoor Environments},
booktitle={Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, (VISIGRAPP 2017)},
year={2017},
pages={210-217},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006116902100217},
isbn={978-989-758-226-4},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, (VISIGRAPP 2017)
TI - Unsupervised Discovery of Normal and Abnormal Activity Patterns in Indoor and Outdoor Environments
SN - 978-989-758-226-4
AU - Dotti D.
AU - Popa M.
AU - Asteriadis S.
PY - 2017
SP - 210
EP - 217
DO - 10.5220/0006116902100217