Embedded Real-Time Fall Detection Using Deep Learning For Elderly Care

This paper proposes a real-time embedded fall detection system using a DVS(Dynamic Vision Sensor) that has never been used for traditional fall detection, a dataset for fall detection using that, and a DVS-TN(DVS-Temporal Network). The first contribution is building a DVS Falls Dataset, which made our network to recognize a much greater variety of falls than the existing datasets that existed before and solved privacy issues using the DVS. Secondly, we introduce the DVS-TN : optimized deep learning network to detect falls using DVS. Finally, we implemented a fall detection system which can run on low-computing H/W with real-time, and tested on DVS Falls Dataset that takes into account various falls situations. Our approach achieved 95.5% on the F1-score and operates at 31.25 FPS on NVIDIA Jetson TX1 board.

[1]  Bernard Ghanem,et al.  ActivityNet: A large-scale video benchmark for human activity understanding , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Miao Yu,et al.  Deep learning for posture analysis in fall detection , 2014, 2014 19th International Conference on Digital Signal Processing.

[3]  Paola Pierleoni,et al.  A High Reliability Wearable Device for Elderly Fall Detection , 2015, IEEE Sensors Journal.

[4]  Thomas Serre,et al.  HMDB: A large video database for human motion recognition , 2011, 2011 International Conference on Computer Vision.

[5]  Miao Yu,et al.  A Posture Recognition-Based Fall Detection System for Monitoring an Elderly Person in a Smart Home Environment , 2012, IEEE Transactions on Information Technology in Biomedicine.

[6]  G. Fuller,et al.  Falls in the elderly. , 2000, American family physician.

[7]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[8]  Yeongjae Cheon,et al.  PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection , 2016, ArXiv.

[9]  J. Kim,et al.  Dynamic vision sensor for low power applications , 2014, The 18th IEEE International Symposium on Consumer Electronics (ISCE 2014).

[10]  Mubarak Shah,et al.  UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild , 2012, ArXiv.

[11]  Bo Chen,et al.  MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications , 2017, ArXiv.

[12]  R. Bajcsy,et al.  Wearable Sensors for Reliable Fall Detection , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[13]  Luc Van Gool,et al.  Temporal Segment Networks: Towards Good Practices for Deep Action Recognition , 2016, ECCV.