Blog icon

The challenge

Easing the burdens of visual data collection

Gentoo penguins lay eggs in late November and usually have two chicks each summer.

Collecting information in remote or sensitive environments, where human interaction can interfere with natural processes, is a challenging task. In these locations, like Antarctica, collecting demographic data, such as animal breeding frequency, birth rates and juvenile survival and even the number of fishing vessels in an area helps provide valuable information for research.

Collecting this information can be very labour intensive and usually involves people with binoculars sequentially counting. This type of monitoring can often face many challenges including logistical, weather and disturbance issues.

Our response

Turning a robot into our binoculars

CSIRO's ruggedised autonomous gigapixel camera system (CRAGS) capturing the breeding season of Gentoo penguins on the Antarctic peninsula.

We've developed a high resolution camera that can withstand the harshest of landscapes.

The system is called CRAGS which stands for CSIRO Ruggedised Autonomous Gigapixel System. It can capture a large area, say an entire colony of penguins, down to the individual animal, or an area of ocean, down to the individual boat, using high spatial resolution imagery to provide visual landscape and time-series data via a zoomable time-lapse video.

Both the mother and father take turns sitting on the nest or foraging for food to feed their Shy Albatross chick.

Our system is cost-effective and has proved to be useful for collecting data for questions scoped at scales of 20m – 3km and 30 minutes to six months on a single battery. This platform is comparable with the spatial scale of aerial survey images but with the temporal coverage of standard camera traps.

CRAGS specs

  • Capture scale – 30m-3000m
  • Mass – three components that are less than 10kg each
  • Maximum deployment time on a single battery – six months
  • Battery and SD card changes in the field without interrupting capture scheduling
  • Autonomous control and scheduling system
  • CRAGS can be custom secured to almost anything
  • Output- zoomable high resolution timelapse video that can be shared online.

Processing several thousand camera images can be a daunting task. CRAGS gigapixel images are run through Time Machine software, which was developed by Carnegie Mellon University and adapted by CSIRO, to create months-long movies within the broader panorama of a site, which is zoomable, through time, down to an individual subject.

The results

Watching remote places through time and space

CRAGS has been successfully deployed across applications which include:

In the winter, this area is covered in snow and ice, but in the warmer months, Gentoo penguins colonise for breeding season.

  • monitoring of Gentoo and Chinstrap penguins, Antarctica
  • several studies of shy albatross breeding biology, Albatross Island, Tasmania
  • human disturbance to fur seal haul-out colonies, NSW
  • fishing effort at an offshore artificial reef, Sydney, NSW
  • patterns of human use within urban aquatic reserves, Sydney, NSW.

CRAGS allows researchers to follow an entire breeding season, instead of just visiting the site one or two times a year and from which researchers can examine the data from the comfort of their office.

CRAGS is a collaboration between the Coastal Development and Management and Engineering and Technology programs in CSIRO's Oceans and Atmosphere and supports critical research in wildlife and fisheries studies.

Do business with us to help your organisation thrive

We partner with small and large companies, government and industry in Australia and around the world.

Contact us now to start doing business

Contact us

Find out how we can help you and your business. Get in touch using the form below and our experts will get in contact soon!

CSIRO will handle your personal information in accordance with the Privacy Act 1988 (Cth) and our Privacy Policy.

First name must be filled in

Surname must be filled in

I am representing *

Please choose an option

Please provide a subject for the enquriy

0 / 100

We'll need to know what you want to contact us about so we can give you an answer

0 / 1900

You shouldn't be able to see this field. Please try again and leave the field blank.