Designing a Video Monitoring System for AAL applications: the SPHERE Case Study

Hall, Jake; Hannuna, Sion; Camplani, Massimo; Mirmehdi, Majid; Aldamen, Dima; Burghardt, Tilo; Tao, Lili; Paiement, Adeline; Craddock, Ian J

doi:10.1049/ic.2016.0061

Cited by 11 publications

(15 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A typical installation of a real-life home in the SPHERE project [6] provides for a camera in each communal room and corridor, and an accelerometer for each participant. Guests can visit the monitored house at any time but will not carry an accelerometer.…”

Section: Video-acceleration Matchingmentioning

confidence: 99%

“…While the presence of monitoring CCTV (Closed-Circuit Television) cameras is nowadays accepted in public spaces, such as shops and city centres, due to privacy reasons, people are often reluctant to install them in their own homes for any purpose other than security, for example, even for constant health monitoring [3][4][5]. Silhouettes constitute an alternative form of data for video monitoring in privacy-sensitive environments [6]. Due to their light weight representation, silhouettes are often the preferred form of data in Internet of Things (IoT) and AAL applications [7].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Person Re-ID by Fusion of Video Silhouettes and Wearable Signals for Home Monitoring Applications

Masullo

Burghardt

Damen

et al. 2020

Sensors

View full text Add to dashboard Cite

The use of visual sensors for monitoring people in their living environments is critical in processing more accurate health measurements, but their use is undermined by the issue of privacy. Silhouettes, generated from RGB video, can help towards alleviating the issue of privacy to some considerable degree. However, the use of silhouettes would make it rather complex to discriminate between different subjects, preventing a subject-tailored analysis of the data within a free-living, multi-occupancy home. This limitation can be overcome with a strategic fusion of sensors that involves wearable accelerometer devices, which can be used in conjunction with the silhouette video data, to match video clips to a specific patient being monitored. The proposed method simultaneously solves the problem of Person ReID using silhouettes and enables home monitoring systems to employ sensor fusion techniques for data analysis. We develop a multimodal deep-learning detection framework that maps short video clips and accelerations into a latent space where the Euclidean distance can be measured to match video and acceleration streams. We train our method on the SPHERE Calorie Dataset, for which we show an average area under the ROC curve of 76.3% and an assignment accuracy of 77.4%. In addition, we propose a novel triplet loss for which we demonstrate improving performances and convergence speed.

show abstract

Section: Video-acceleration Matchingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Person Re-ID by Fusion of Video Silhouettes and Wearable Signals for Home Monitoring Applications

Masullo

Burghardt

Damen

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…The focus of this paper is on the embedded IoT sensing devices of SPHERE, namely the environmental and wearable sensors. For further details on the video sub-system of SPHERE we refer the reader to [11]. The data generated from these sensing modalities is collected in a central server within each deployed house, named SPHERE Home Gateway, and stored in an encrypted solid state drive.…”

Section: The Sphere Systemmentioning

confidence: 99%

SPHERE Deployment Manager: A Tool for Deploying IoT Sensor Networks at Large Scale

Fafoutis

Elsts

Oikonomou

et al. 2018

Ad-Hoc, Mobile, and Wireless Networks

View full text Add to dashboard Cite

Internet of Things (IoT) technology has the potential to revolutionise several domains of everyday life, including the healthcare sector. In order to reach its full potential, IoT technology needs to be evaluated in the real world, beyond controlled environments, such as laboratories and test-beds. SPHERE is an experimental sensing platform for healthcare in a residential environment. Unlike other similar smart home health systems, SPHERE is deployed in a large number of properties of volunteers. Based on our experiences and lessons learned from SPHERE's large-scale deployments, this paper focuses on the challenge of effectively managing the sensor installation overhead, aiming at supporting our deployment technicians with achieving a satisfactory deployment throughput. In this context, this paper presents the SPHERE Deployment Manager: an open-source tool that facilitates the deployment of bespoke IoT networks by technicians that are not experts in IoT technology. We believe that the SPHERE Deployment Manager is a tool that can accelerate future IoT research deployments of similar nature and scale.

show abstract

“…There is also an RGB-D (depth sensing) camera in the room which is used to provide positional data on the occupants [5]. A head-mounted camera was used to record the actions of the participants during the study to allow for better annotation of the observations.…”

Section: Experimental Designmentioning

confidence: 99%

Recognition of unscripted kitchen activities and eating behaviour for health monitoring

Whitehouse

Yordanova

Paiement

et al. 2016

2nd IET International Conference on Technologies for Active and Assisted Living (TechAAL 2016)

Self Cite

View full text Add to dashboard Cite

Designing a Video Monitoring System for AAL applications: the SPHERE Case Study

Cited by 11 publications

References 27 publications

Person Re-ID by Fusion of Video Silhouettes and Wearable Signals for Home Monitoring Applications

Person Re-ID by Fusion of Video Silhouettes and Wearable Signals for Home Monitoring Applications

SPHERE Deployment Manager: A Tool for Deploying IoT Sensor Networks at Large Scale

Recognition of unscripted kitchen activities and eating behaviour for health monitoring

Contact Info

Product

Resources

About