Detection of Falls from Non-Invasive Thermal Vision Sensors Using Convolutional Neural Networks

Proceedings

Nugent, Chris¹  Quero, Javier Medina²  Espinilla, Macarena³  Burns, Matthew⁴  Razzaq, Muhammad Asif⁵ 

[1] Author to whom correspondence should be addressed.;Department of Computer Science, University of Jaén, Campus Las Lagunillas, 23071 Jaén, Spain;Presented at the 12th International Conference on Ubiquitous Computing and Ambient Intelligence (UCAmI 2018), Punta Cana, Dominican Republic, 4–7 December 2018.;School of Computing, Ulster University, Newtownabbey, Co. Antrim, Northern Ireland BT15 1ED, UK;Ubiquitous Computing Lab in Kyung Hee University, Seoul 446-701, Korea

关键词: thermal vision sensor;    fall detection;    convolutional neural networks;   

DOI  :  10.3390/proceedings2191236

学科分类：社会科学、人文和艺术（综合）

来源: mdpi

【 摘 要 】

In this work, we detail a methodology based on Convolutional Neural Networks (CNNs) to detect falls from non-invasive thermal vision sensors. First, we include an agile data collection to label images in order to create a dataset that describes several cases of single and multiple occupancy. These cases include standing inhabitants and target situations with a fallen inhabitant. Second, we provide data augmentation techniques to increase the learning capabilities of the classification and reduce the configuration time. Third, we have defined 3 types of CNN to evaluate the impact that the number of layers and kernel size have on the performance of the methodology. The results show an encouraging performance in single-occupancy contexts, with up to 92 % of accuracy, but a 10 % of reduction in accuracy in multiple-occupancy. The learning capabilities of CNNs have been highlighted due to the complex images obtained from the low-cost device. These images have strong noise as well as uncertain and blurred areas. The results highlight that the CNN based on 3-layers maintains a stable performance, as well as quick learning.

【 授权许可】

CC BY