Abstract
With an ageing population, the healthcare sector struggles to cope worldwide. Home monitoring using technology is increasingly used to release the pressure on healthcare professionals and keep elderly at home for longer. However, current solutions present technical (i.e. low resolution and convenience) and ethical issues. In this paper, we used 2D LiDAR, as a sensor that can provide significant information on patient’s activities, whilst still ensuring their privacy (i.e. 2D LiDAR only produces anonymous point clouds). Particularly, we developed an algorithm that uses clustering on the raw 2D LiDAR data, object tracking on cluster centroids to identify a user in a room, and semantic enrichment using metadata about the room (i.e. areas of interest and furniture position) to associate stationary and non-stationary points with every day activities (e.g. relaxing on the couch, working at the desk, standing by the window, and walking). We tested our method across different users (N = 3) and two rooms for a total 60 randomly ordered activity sequences, with five activities per sequence and each activity performed for 30 s. We obtained an overall accuracy in identifying the activities of 0.88 (standard deviation [SD], 0.06). Walking was the activity with the highest F1 score, with values of 0.97 (SD, 0.04) and 1.00 (SD, 0.00). As expected, activities where occlusion from pieces of furniture might be in the way had worse performance with an F1 score of 0.81 (SD, 0.24). Although performed on a limited sample, our paper shows potential for 2D LiDAR to be used for remote monitoring of mobility and daily activities of elderly in their home.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
World Report on Ageing and Health. World Health Organisation, Geneva (2015)
Majumder, S., et al.: Smart homes for elderly healthcare–recent advances and research challenges. Sensors 17(11), 2496 (2017). https://doi.org/10.3390/s17112496
Uddin, M.Z., Khaksar, W., Torresen, J.: Ambient sensors for elderly care and independent living: a survey. Sensors 18(7), 2027 (2018)
Marikyan, D., Papagiannidis, S., Alamanos, E.: A systematic review of the smart home literature: a user perspective. Technol. Forecast. Soc. Change 138, 139–154 (2019). https://doi.org/10.1016/j.techfore.2018.08.015
Zhao, M., et al.: Through-wall human pose estimation using radio signals. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recogniton, pp. 7356–7365 (2018)
Dong, P., Chen, Q.: LiDAR Remote Sensing and Applications. CRC Press, New York (2017)
Guerrero-Higueras, Á.M., et al.: Tracking people in a mobile robot from 2D LIDAR scans using full convolutional neural networks for security in cluttered environments. Front. Neurorobotics 12, 85 (2019). https://doi.org/10.3389/fnbot.2018.00085
Álvarez-Aparicio, C., Guerrero-Higueras, Á.M., Rodríguez-Lera, F.J., Ginés Clavero, J., Martín Rico, F., Matellán, V.: People detection and tracking using LIDAR sensors. Robotics 8(3), 75 (2019)
Bodanese, E., Ma, Z., Bigham, J., et al.: Device-free daily life (ADL) recognition for smart home healthcare using a low-cost (2D) lidar. In: 2018 IEEE Global Communications Conference (GLOBECOM) (2018). https://ieeexplore.ieee.org/document/8647251
SlamTech. https://www.slamtec.com/en/Lidar/A2, RPLiDAR A2
IBM Cloud Object Storage. https://www.ibm.com/uk-en/cloud/object-storage
Ester, M., Kriegel, H.-P., Sander, J., Xu, X.: A density-based algorithm for discovering clusters in large spatial databases with noise. In: KDD 1996 (1996). https://dl.acm.org/doi/10.5555/3001460.3001507
van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579–2605 (2008)
Colleens, T., Colleens, J.: Occupancy grid mapping: an empirical evaluation. In: 2007 Mediterranean Conference on Control & Automation, pp. 1–6 (2007). https://ieeexplore.ieee.org/document/4433772
Wikipedia, Orthogonal Conven Hull. https://en.wikipedia.org/wiki/Orthogonal_convex_hull
Fraccaro, P., Lavery-Blackie, S., Van der Veer, S.N., Peek, N.: Behavioural phenotyping of daily activities relevant to social functioning based on smartphone-collected geolocation data. Stud. Health Technol. Inform. 264, 945–949 (2019)
Duque, G.: Age-related physical and physiologic changes and comorbidities in older people: association with falls. In: Huang, A.R., Mallet, L. (eds.) Medication-Related Falls in Older People, pp. 67–73. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-32304-6_6
Blackman, S.S.: Multiple hypothesis tracking for multiple target tracking. IEEE Aerosp. Electron. Syst. Mag. 19(1), 5–18 (2004)
Premebida, C.: Segmentation and geometric primitives extraction from 2d laser range data for mobile robot applications. Robotica 2005 (2005). https://www.semanticscholar.org/paper/Segmentation-and-Geometric-Primitives-Extraction-2D-Premebida/b0017df5fe86501e8338ff737077c13777d55a9d
Acknowledgements
This work was supported by the STFC Hartree Centre’s Innovation Return on Research programme, funded by the UK Department for Business, Energy & Industrial Strategy. XE was supported by the IBM Research internship program during summer 2019.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Fraccaro, P., Evangelopoulos, X., Edwards, B. (2020). Development and Preliminary Evaluation of a Method for Passive, Privacy-Aware Home Care Monitoring Based on 2D LiDAR Data. In: Michalowski, M., Moskovitch, R. (eds) Artificial Intelligence in Medicine. AIME 2020. Lecture Notes in Computer Science(), vol 12299. Springer, Cham. https://doi.org/10.1007/978-3-030-59137-3_15
Download citation
DOI: https://doi.org/10.1007/978-3-030-59137-3_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-59136-6
Online ISBN: 978-3-030-59137-3
eBook Packages: Computer ScienceComputer Science (R0)