Fall detection for elderly-people monitoring using learned features and recurrent neural networks

Elderly care is becoming a relevant issue with the increase of population ageing. Fall injuries, with their impact on social and healthcare cost, represent one of the biggest concerns over the years. Researchers are focusing their attention on several fall-detection algorithms. In this paper, we present a deep-learning solution for automatic fall detection from RGB videos. The proposed approach achieved a mean recall of 0.916, prompting the possibility of translating this approach in the actual monitoring practice. Moreover to enable the scientific community making research on the topic the dataset used for our experiments will be released. This could enhance elderly people safety and quality of life, attenuating risks during elderly activities of daily living with reduced healthcare costs as a final result.

[1]  Ling Shao,et al.  A survey on fall detection: Principles and approaches , 2013, Neurocomputing.

[2]  Jürgen Schmidhuber,et al.  Framewise phoneme classification with bidirectional LSTM and other neural network architectures , 2005, Neural Networks.

[3]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[4]  Emanuele Frontoni,et al.  Preterm infants' limb-pose estimation from depth images using convolutional neural networks , 2019, 2019 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB).

[5]  Long Chen,et al.  Human fall detection in surveillance video based on PCANet , 2016, Multimedia Tools and Applications.

[6]  Muhammad Ashraf,et al.  A novel fall detection algorithm for elderly using SHIMMER wearable sensors , 2019, Health and Technology.

[7]  James J. Little,et al.  Video-based Human Fall Detection in Smart Homes Using Deep Learning , 2018, 2018 IEEE International Symposium on Circuits and Systems (ISCAS).

[8]  Emanuele Frontoni,et al.  A sequential deep learning application for recognising human activities in smart homes , 2020, Neurocomputing.

[9]  Danail Stoyanov,et al.  Deep Learning Based Robotic Tool Detection and Articulation Estimation With Spatio-Temporal Layers , 2019, IEEE Robotics and Automation Letters.

[10]  Miguel A. Labrador,et al.  Survey on Fall Detection and Fall Prevention Using Wearable and External Sensors , 2014, Sensors.