Privacy Preserving Human Fall Detection using Video Data

Umar Asif, Benjamin Mashford, Stefan Von Cavallar, Shivanthan Yohanandan, Subhrajit Roy, Jianbin Tang, Stefan Harrer
Proceedings of the Machine Learning for Health NeurIPS Workshop, PMLR 116:39-51, 2020.

Abstract

Falling can have fatal consequences for the elderly people especially if the fallen person is unable to call for help due to loss of consciousness or any other associated injury. Automatic fall detection systems can assist in overcoming this issue through prompt fall alarms which then allow the triggering of a third party response, and to minimize the fear of falling when living independently at home. Vision-based fall detection systems detect human regions in the scene and use information from these regions to train classifiers for fall recognition. However, the performance of these systems lack generalization to unseen environments due to factors such as errors in the human detection stage and the unavailability of large-scale fall datasets to learn robust features for fall recognition. In this paper, we present a deep learning based framework towards automatic fall detection from RGB images captured by a single camera. Our framework learns human skeleton and segmentation based fall representations purely from synthetic data generated in a virtual environment. This de-identifies personal information contained in the original images and preserves privacy which is highly desirable in health informatics. Experiments on challenging real-world fall datasets show that our framework performs successful transfer of fall recognition knowledge from synthetic to real-world data and achieves high sensitivity and specificity scores showcasing its generalization capability for highly accurate fall detection in unseen real-world environments.

Cite this Paper


BibTeX
@InProceedings{pmlr-v116-asif20a, title = {{Privacy Preserving Human Fall Detection using Video Data}}, author = {Asif, Umar and Mashford, Benjamin and {Von Cavallar}, Stefan and Yohanandan, Shivanthan and Roy, Subhrajit and Tang, Jianbin and Harrer, Stefan}, booktitle = {Proceedings of the Machine Learning for Health NeurIPS Workshop}, pages = {39--51}, year = {2020}, editor = {Dalca, Adrian V. and McDermott, Matthew B.A. and Alsentzer, Emily and Finlayson, Samuel G. and Oberst, Michael and Falck, Fabian and Beaulieu-Jones, Brett}, volume = {116}, series = {Proceedings of Machine Learning Research}, month = {13 Dec}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v116/asif20a/asif20a.pdf}, url = {https://proceedings.mlr.press/v116/asif20a.html}, abstract = {Falling can have fatal consequences for the elderly people especially if the fallen person is unable to call for help due to loss of consciousness or any other associated injury. Automatic fall detection systems can assist in overcoming this issue through prompt fall alarms which then allow the triggering of a third party response, and to minimize the fear of falling when living independently at home. Vision-based fall detection systems detect human regions in the scene and use information from these regions to train classifiers for fall recognition. However, the performance of these systems lack generalization to unseen environments due to factors such as errors in the human detection stage and the unavailability of large-scale fall datasets to learn robust features for fall recognition. In this paper, we present a deep learning based framework towards automatic fall detection from RGB images captured by a single camera. Our framework learns human skeleton and segmentation based fall representations purely from synthetic data generated in a virtual environment. This de-identifies personal information contained in the original images and preserves privacy which is highly desirable in health informatics. Experiments on challenging real-world fall datasets show that our framework performs successful transfer of fall recognition knowledge from synthetic to real-world data and achieves high sensitivity and specificity scores showcasing its generalization capability for highly accurate fall detection in unseen real-world environments.} }
Endnote
%0 Conference Paper %T Privacy Preserving Human Fall Detection using Video Data %A Umar Asif %A Benjamin Mashford %A Stefan Von Cavallar %A Shivanthan Yohanandan %A Subhrajit Roy %A Jianbin Tang %A Stefan Harrer %B Proceedings of the Machine Learning for Health NeurIPS Workshop %C Proceedings of Machine Learning Research %D 2020 %E Adrian V. Dalca %E Matthew B.A. McDermott %E Emily Alsentzer %E Samuel G. Finlayson %E Michael Oberst %E Fabian Falck %E Brett Beaulieu-Jones %F pmlr-v116-asif20a %I PMLR %P 39--51 %U https://proceedings.mlr.press/v116/asif20a.html %V 116 %X Falling can have fatal consequences for the elderly people especially if the fallen person is unable to call for help due to loss of consciousness or any other associated injury. Automatic fall detection systems can assist in overcoming this issue through prompt fall alarms which then allow the triggering of a third party response, and to minimize the fear of falling when living independently at home. Vision-based fall detection systems detect human regions in the scene and use information from these regions to train classifiers for fall recognition. However, the performance of these systems lack generalization to unseen environments due to factors such as errors in the human detection stage and the unavailability of large-scale fall datasets to learn robust features for fall recognition. In this paper, we present a deep learning based framework towards automatic fall detection from RGB images captured by a single camera. Our framework learns human skeleton and segmentation based fall representations purely from synthetic data generated in a virtual environment. This de-identifies personal information contained in the original images and preserves privacy which is highly desirable in health informatics. Experiments on challenging real-world fall datasets show that our framework performs successful transfer of fall recognition knowledge from synthetic to real-world data and achieves high sensitivity and specificity scores showcasing its generalization capability for highly accurate fall detection in unseen real-world environments.
APA
Asif, U., Mashford, B., Von Cavallar, S., Yohanandan, S., Roy, S., Tang, J. & Harrer, S.. (2020). Privacy Preserving Human Fall Detection using Video Data. Proceedings of the Machine Learning for Health NeurIPS Workshop, in Proceedings of Machine Learning Research 116:39-51 Available from https://proceedings.mlr.press/v116/asif20a.html.

Related Material