3D Convolutional Neural network for Home Monitoring using Low Resolution Thermal-sensor Array

التفاصيل البيبلوغرافية
العنوان: 3D Convolutional Neural network for Home Monitoring using Low Resolution Thermal-sensor Array
المؤلفون: Ziqi Zhang, Melvyn L. Smith, Yanguo Jing, Timothy Volonakis, Bo Tan, Lili Tao
المصدر: 3rd IET International Conference on Technologies for Active and Assisted Living (TechAAL 2019).
بيانات النشر: Institution of Engineering and Technology, 2019.
سنة النشر: 2019
مصطلحات موضوعية: Thermal sensors, Sensor array, business.industry, Computer science, Low resolution, Computer vision, Artificial intelligence, Fall detection, Sensitivity (control systems), business, Representation (mathematics), Convolutional neural network, Image resolution
الوصف: The recognition of daily actions, such as walking, sitting or standing, in the home is informative for assisted living, smart homes and general health care. A variety of actions in complex scenes can be recognised using visual information. However cameras succumb to privacy concerns. In this paper, we present a home action recognition system using an 8×8 infared sensor array. This low spatial resolution retains user visual privacy, but is still a powerful representation of actions in a scene. Actions are recognised using a 3D convolutional neural network, extracting not only spatial but temporal information from video sequences. Experimental results obtained from a publicly available dataset Infra-ADL2018 demonstrate a better performance of the proposed approach compared to the state-of-the-art. We show that the sensor is considered better at detecting the occurrence of falls and actions of daily living. Our method achieves an overall accuracy of 97.22% across 7 actions with a fall detection sensitivity of 100% and specificity of 99.31%.
DOI: 10.1049/cp.2019.0100
URL الوصول: https://explore.openaire.eu/search/publication?articleId=doi_________::db83efbe8a997624d5a1d886c8b05d01
https://doi.org/10.1049/cp.2019.0100
رقم الانضمام: edsair.doi...........db83efbe8a997624d5a1d886c8b05d01
قاعدة البيانات: OpenAIRE