Coral reef conservation
assisted by AI camera
Project reveals health of subsea environment
JASON FORD reports
7 June 2020 / www.theengineer.co.uk
Artifi cial intelligence is being
used in the Philippines to
monitor, characterise and
analyse the resilience of
coral reefs.
Over 800 species of coral
provide a habitat for around a
quarter of the world’s marine
life, but they are being degraded
by overfi shing, bo om trawling,
warming temperatures and
unsustainable coastal development.
According to Ewen Plougastel,
managing director and ASEAN
delivery lead, Accenture Applied
Intelligence, a video camera
equipped with AI is working
in depths between fi ve and 10
metres to give marine biologists
at the Sulubaaï Environmental
Foundation (SEF) a be er
understanding of the subsea
environment.
Since 2019 Accenture, Intel
and SEF have established Project:
CORaiL, which has included
the installation of an artifi cial,
concrete reef dubbed the Sulu-Reef
Prosthesis (SRP). The SRP was
placed in the reef surrounding
Pangatalan Island before fragments
of living coral were planted on it to
grow, expand and provide a hybrid
habitat for fi sh and marine life.
Underwater video cameras
- equipped with the Accenture
Applied Intelligence Video
Analytics Services Platform
(VASP) - detect and photograph
fi sh as they pass by. VASP uses AI,
powered by Intel Xeon, Intel FPGA
Programmable Acceleration Cards
and Intel Movidius VPU, to count
and classify the marine life. 4G
technology transfers the data via
a wireless router to shore where it
provides analytics and trends in
real-time.
Plougastel said: “The fi rst
version of the software deployed on
the camera is used to purely collect
images of fi sh to create a dataset
that we could use to train a deep
learning model that would then
be capable of classifying marine
life automatically. This version is
equipped with classic computer
vision algorithms detecting
movements and saving an image of
the “object” - here the fi sh or other
marine species - that passed by the
camera.
“The second version of the
software will be automatically
detecting and classifying the fi sh
in real-time. The detections will
then be sent to a centralised server
with more processing power that
will run further analytics to derive
more details about the marine life
species.”
Marine biologists at the
Sulubaaï foundation move the
camera once a week to get a variety
of angles and locations on the reef.
Since being deployed in May 2019,
it has collected roughly 40,000
images.
VACCINE FUNDING
The government has injected
£84m into UK efforts to develop
and manufacture a vaccine
for Covid-19. The funding
follows a global licensing
agreement between Oxford
University and AstraZeneca
for the commercialisation and
manufacturing of a potential
vaccine. If Oxford University’s
vaccine is successful,
AstraZeneca will work to make up
to 30 million doses available by
September for people in Britain,
as part of an agreement to deliver
100 million doses in total.
ROLLING STOCK
Transport for London has received
a £1.6bn funding and fi nancing
package from the Department for
Transport to protect key services,
ensure passenger safety and
support London’s recovery
from the Covid-19 pandemic.
“People should avoid using
public transport and work from
home wherever possible, but as
measures are slowly
lifted it is vital that
Londoners who need to
use TFL services feel
safe and secure,” said
Transport Secretary,
Grant Shapps.
FAST TRACK
Administrative barriers to the
import of personal protective
equipment (PPE) and hand
sanitiser are to be eased.
Measures introduced by Business
Secretary Alok Sharma include
asking the Health and Safety
Executive and Local Authorities
to fast-track PPE through the
product safety assessment
process. Furthermore, new
suppliers and businesses that
produce ingredients for safe hand
sanitiser and PPE will be able to
bring their products to market in a
matter of days.
Read more at
www.theengineer.co.uk
Engineers at online grocer Ocado
Technology have successfully
trialled a humanoid robot able to help
workers with maintenance tasks at
its automated warehouse in Hatfi eld,
Hertfordshire.
The result of a fi ve-year long
collaborative project involving a number
of European partners, the so-called
ARMAR-6 robot is able to respond to
natural language commands; hold and
pass objects of a wide range of shapes
and sizes; and even proactively step
in when it judges that one of its human
colleagues needs a hand.
The technology was developed
through the Horizon2020 SecondHands
project by a consortium including Ocado
Technology, Ecole Polytechnique Fédérale
de Lausanne (EPFL), Karlsruhe Institute
of Technology (KIT) Sapienza, University
of Rome and University College London
(UCL).
According to those involved, the
project has led to a number of key
breakthroughs in robotic perception,
task planning and human-robot
interaction that pave the way towards
the development of intelligent humanoid
robots that could ultimately be used in a
range of applications
The robot incorporates two
compliant 8 degree of freedom arms
with underactuated hands, a head with
fi ve cameras and a wheeled holonomic
platform that enables it to move freely
around a space.
Not only is the system able to use
both of its hands to grasp and manipulate
objects and use tools such as power
drills and hammers, but thanks to a high
level of hardware-software integration,
can recognise human activities and
intentions, reason about situations, and
interact with humans in a natural way –
for instance working in collaboration with
human to manipulate large objects. JE
HUMANOID ROBOT IN
UK WAREHOUSE TEST
NEWS IN BRIEF
technology NEWS
/www.theengineer.co.uk
/www.theengineer.co.uk