Visual monitoring of people in private spaces. From the “Big Brother” to the “Good Brother”
Visual monitoring of people in private spaces.
From the “Big Brother” to the “Good Brother”
Faculty of Science, Engineering and Computing, Kingston University
Digital Imaging Research Centre
Interdisciplinary Hub for the Study of Health and Age-related conditions (IhSHA)
Technology is gradually gaining acceptance as a
means to complement the work of caregivers by
monitoring and assisting persons with reduced
physical or cognitive capacity in their day-to-day
living. Ambient Assisted Living (AAL)
environments make use of a variety of sensors
that collect information from the environment or
its dwellers. These sensors that monitor the
persons and their interactions with other people
or objects allow the recognition of activities of
daily living or dangerous situations, e.g. falls.
While monitoring technology for public security
is relatively mature, attention is now focussed on
the use of sensing technology embedded in
devices used to promote health and enhance
wellbeing and safety. However, monitoring is
often seen as intrusive and as violating rights to
privacy. Acceptance of such technologies is low
because they create a sense of Orwellian “Big
Legal, ethical, and regulatory responsibilities
require that data is protected in order to
The main objective of is to provide an
ICT-based solution to support and relieve the
burden experienced by informal carers (relatives,
friends, neighbours…) and improve the quality of
life of both the carer and the person who is being
cared for. The platform is composed of two
different modules, namely the AAL home system
and the informal caregiver tool.
The AAL home system consists of a group of
cameras and an array of sensors installed at the
assisted person´s home and is responsible for
collecting information on a daily basis and in an
automatic way about the routine, moods,
behaviour and activities of the assisted person.
The informal caregiver tool is based on a Web
platform that provides, to the carer, guidance and
support to improve their working conditions and
enable, as a result, a better quality of care.
Activities and events to be detected:
• Recognition of activities of daily living (ADL): wake-
up, going to the toilet, sleeping…
• Activity level: light, moderate, intensive
• Location and tracking of the persons in the home
• Risky situations: fall detection, dangerous objects;
fire, flood, gas alarms…
• Social activity: leaving home, receiving visits, use of
• Detection of basic and advanced activities:
cooking, watching TV…
3. Privacy by context
Privacy-Enhancing Technologies is a system of
ICT measures protecting informational privacy by
eliminating or minimising personal data thereby
preventing unnecessary or unwanted processing
of personal data, without the loss of functionality
of the information system.
We propose a privacy-by-context paradigm for
remote visual monitoring of assisted persons,
following a level-based scheme to access video
data (although it could be extended to any
personal data) in order to protect privacy. Each
level establishes the way in which the video
stream is modified and displayed and, therefore,
which protection degree is provided.
The context should provide enough information to
empower the assisted persons to adapt privacy
to their preferences, in such a way that they can
decide who, how, and when their carers can
An individual can then select in advance a
visualisation level to any situation that could be
modelled by the context, i.e. giving different
permissions to access the video stream to the
various different carers in different ways according
to what is happening at the assisted person’s
4. Visual privacy
We have implemented our level-based scheme
considering eight visualisation models.
Original Blur Pixelating
Skeleton Avatar Invisilibity
This tests have been carried out using a RGB-D
camera, i.e. Microsoft Kinect
5. Validation in real environments
Use of omnidirectional RGB cameras located on
the ceiling of each room
Activity Status of the assisted person
6. More information
Padilla-López, J.R.; Chaaraoui, A.A.; Gu, F.; Flórez-Revuelta, F.
(2015). Visual privacy by context: proposal and evaluation of a
level-based visualisation scheme. Sensors, 15(6), 12959-12982.
Padilla-López, J.R.; Chaaraoui, A.A.; Flórez-Revuelta, F. (2015).
Visual privacy protection methods: A survey. Expert Systems
With Applications, 42(9), 4177-4195.
Flórez-Revuelta, F.; Gu. F.; Pierscionek, B.; Remagnino, P.
(2015). White paper on AAL systems and associated privacy
issues. Public report, BREATHE Consortium.
Padilla-López, J.R.; Flórez-Revuelta, F.; Monekosso, D.N.;
Remagnino, P. (2012). The “Good” Brother: Monitoring People
Activity in Private Spaces. In Distributed Computing and Artificial
Intelligence (pp. 49-56). Springer Berlin Heidelberg.
This work has been supported by the Ambient Assisted Living Joint Programme and Innovate
UK under Project “BREATHE – Platform for self-assessment and efficient management for
informal caregivers” (AAL-JP-2012-5-045).