Birdseye hyperspectral science: Ningaloo as you’ve never seen it before
31 January 2017Meet the new face of environmental monitoring – a combination of unmanned aerial vehicles (UAV) and a highly specialised camera that was once so big and expensive only satellites and airplanes could carry them.
QUT remote sensing researchers and UAV engineers are pioneering the use of new miniaturised hyperspectral cameras to monitor the health of Australian landscapes in more detail than ever before.
Project leader Associate Professor Felipe Gonzalez said his team was among the first in the world to obtain aerial hyperspectral imagery of a coral reef in extraordinary resolution – the pristine Ningaloo Reef at the Ningaloo Coast World Heritage site in Western Australia – in a data-gathering mission that will help inform future research.
“Normal cameras record images in three bands of the visible spectrum – red, green and blue – mixing those bands together to create colours as humans see them,” said Professor Gonzalez, from QUT’s Institute for Future Environments (IFE).
“By comparison, the hyperspectral camera captures 270 bands in the visible and near-infrared portions of the spectrum, providing far more detail than the human eye can see.
“And, as we’re flying it on small UAVs at 30-100m over the water, the data collected is of an incredibly high resolution.”
At 290 kilometres, Ningaloo Reef is one of the longest and structurally complex nearshore reefs in the world.
Professor Gonzalez said new lightweight hyperspectral cameras would open many possibilities for reef monitoring and collaborations with marine researchers.
IFE researchers are already working on integrating a hyperspectral camera unit into an underwater housing for marine robots.
“UAVs are a cost-effective sensor platform and a great complementary tool to existing satellite, manned aircraft and underwater surveys,” Professor Gonzalez said.
“Large-scale, high-altitude surveys of the Ningaloo and Great Barrier reefs may lack the resolution necessary to identify individual corals, so this is the niche for low-altitude UAV surveys.”
Using data collected by engineers in the IFE’s Research Engineering Facility (REF), Professor Gonzalez and his team are developing revolutionary software to quickly analyse the airborne hyperspectral information from Ningaloo reef, and for a wide range of other environmental purposes, including detecting invasive plants in Western Australia and diseases in wheat crops.
The system is backed by a state-of the-art, REF-designed and manufactured gimbal that enables stabilised image capture from the hyperspectral camera onboard QUT’s unmanned aerial vehicles.
QUT research engineer Dr Dmitry Bratanov said the hyperspectral UAV system surveyed approximately 40ha of Ningaloo Reef in 30 minutes at a flight height of 100m.
“This provides us with a spatial resolution of approximately 15cm per pixel – more than enough detail to detect and monitor individual coral species” Mr Bratanov said.
“The really special thing about the hyperspectral camera is that it takes images across 270 slices of the spectrum. This huge amount of information allows for the classification of coral species, sand and algae based on their unique spectral signatures.”
Professor Gonzalez said these signatures act very much like fingerprints.
“We’re building artificial intelligence algorithms that can automatically recognise and classify these unique signatures – the hyperspectral equivalent of a police ‘fingerprint database’, Professor Gonzalez said.
“This database will become increasing valuable to all environmental researchers into the future.”
NASA’s Coral Reef Airborne Laboratory (CORAL) mission is currently conducting hyperspectral mapping of the Great Barrier Reef at high altitude with manned aircraft.
“The CORAL system provides a resolution of 7.5m per pixel compared to QUT’s UAV system at 15cm per pixel, and our manned aircraft fitted with a hyperspectral camera which captures data at 35cm per pixel at 230 m off the ground,” Professor Gonzalez said.
“Our data would make for a fascinating comparison between a remote pristine reef in Western Australia and a reef system under pressure from human activities along the Queensland coast.
“There are many advantages to using smaller hyperspectral cameras and a UAV – it’s cost-effective, quick to deploy and flexible – a mission can be scheduled any time in strategic locations where a higher level of detail is required.
“It’s exciting to be at the forefront of a new approach to monitoring and managing the Australian environment.”
RELATED STORIES
The robot eyes have it: cutting-edge tool for koala conservation
Crown-of-thorns starfish – nailed it!
Aerial robots, artificial intelligence and statistics revolutionise wildlife tracking and research
Media contacts
Kate Haggman, QUT Media, 07 3138 0358, kate.haggman@qut.edu.au
After hours Rose Trapnell, QUT Media team leader, 0407 585 901, media@qut.edu.au
QUT is part of a national collaborative group of five major Australian universities that form the ATN (Australian Technology Network of Universities).
The robot eyes have it: cutting-edge tool for koala conservation
19 October 2016Local councils are testing a new tool for protecting their vulnerable koala populations – drones equipped with artificial intelligence (AI) and backed by powerful statistical analysis.
Koala experts with Logan, Gold Coast and Tweed councils are working with a multi-disciplinary team of QUT researchers and unmanned aerial vehicle (UAV) specialists to develop and trial technologies they hope will prove cheaper and more accurate than current tracking methods.
The researchers have been conducting test flights over koala habitats in each region, coinciding ground-based koala counts.
QUT aerospace engineer Associate Professor Felipe Gonzalez said the team had developed a unique combination of UAV with thermal imaging, statistical modelling and AI.
“Using small drones to take images is becoming more common but we know of no others combining this with cutting-edge analytical technologies that draw meaning from those images,” Professor Gonzalez said.
“We’ve found thermal imaging can detect even well-camouflaged koalas effectively and our counting and tracking algorithms can allow us to differentiate the shape of a koala from a possum, bird or other animal.
“This project is concentrating on koala populations but the technology can easily be adapted for other species, be they native or pest species, like wild dogs or feral cats.”
The project has already proved the technology can save councils valuable time. In one test, it took humans more than two hours to conduct the same survey a UAV took just 30 minutes to complete.
QUT ecology and statistics experts Dr Grant Hamilton and Dr Sandra Johnson said the technology would not only count koalas but monitor their movements and population fluctuations over time.
“Understanding the abundance of a species in an area is fundamental to the management of that species – and the more regularly and accurately you can monitor the health of the population, the better,” Dr Hamilton said.
“This combination of technology can provide councils with a wealth of rich data a human cannot, such as exact GPS locations and high-resolution imaging.”
City of Gold Coast Planning Committee Chair Councillor Cameron Caldwell said the unique project enabled a coordinated approach to koala monitoring and population assessment.
“This project not only enhances our existing Koala Conservation Plans it strengthens our koala management opportunities by partnering with our two neighbouring local government areas,” Cr Caldwell said.
“Hopefully the results of the trial will prove useful when it comes to monitoring our resident koala populations and future planning for their protection.”
Logan City Council Deputy Mayor Cherie Dalley said having access to this information would go a long way in helping Council better manage its koala population.
“Logan residents are lucky to share their backyard with one of the largest koala parks in the world,” Cr Dalley said.
“The Daisy Hill Koala Centre takes in 435 hectares of open eucalypt forest and the data collected by drones will help us get a better understanding of Koala numbers to ensure their long term survival.”
Mayor of Tweed Councillor Katie Milne said this technology could be a very important tool.
“We know our koalas are on the brink of extinction but we don’t know exactly how close,” Cr Milne said.
“Our residents are determined to maintain our coastal koala population. An all-out, full-on, last-ditch effort is needed with the whole community, developers and government if we are to succeed.”
The project is expected to wrap up within the next few months, after which final results will be shared with the councils.
Aerial robots, artificial intelligence and statistics revolutionise wildlife tracking and research
26 February 2015Monitoring the movements and populations of koalas, dingos, feral pigs and other wildlife will be a lot easier thanks to a QUT collaboration involving a dynamic blend of high profile research areas including aerial robots, artificial intelligence and Bayesian statistics.
Earlier this month the Australia Zoo Wildlife Hospital provided support to the project by allowing test flights with an aerial robot using infrared imaging to assess koala population in surrounding bushland.
Project leader Dr Felipe Gonzalez from the Australian Research Centre for Aerospace Automation (ARCAA) at QUT said the project was exploring Bayesian statistical modelling, artificial intelligence, wireless technology and the use of aerial robots or unmanned aerial vehicles (UAVs) to improve the accuracy of population estimates of koalas and other wildlife.
“A digital camera does not easily or accurately capture the koalas in their habitat but thermal imaging from an airborne vantage point can better assist in determining how many are in a given space,” Dr Gonzalez said.
“This dynamic combination of expertise and technology opens up many exciting possibilities in wildlife conservation of vulnerable or endangered species, as well as invasive species’ populations.
“It will enable us to respond earlier and in a more targeted way to critical issues whether it’s the relocation and reintroduction of endangered species, the rehabilitation of injured animals or the control of invasive and destructive species like feral pigs, cats and wild dogs.
“We use artificial intelligence and machine learning to develop counting and tracking algorithms with results so far showing a significant improvement in detection rates and more accurate population counts.”
Amber Gillett, Senior Veterinarian at the Australia Zoo Wildlife Hospital said the implications of being able to monitor koalas and other wildlife from the air were far-reaching.
“Detecting koalas in bushland from the ground is a very hard task. It requires a lot of resources and manpower to survey an area for koalas. Even in our small plantation pen where we hold about 10 koalas, and know what trees the koalas often sit in, it may require up to 3 staff and more than half an hour to identify them all each day,” Ms Gillett said.
“Koalas can be very hard to see amongst the leaves of trees, even when you know they are there. Subsequently, visual detection from the ground of koalas for population estimates often drastically underestimates the real number of koalas.
“Technology like this is extremely exciting. We need better and more accurate ways to determine wild koala numbers, particularly in areas where decline is evident, as currently estimates are really only ‘estimates’ and not each and every koala being counted.”
Dr Sandra Johnson, ARC Centre of Excellence for Mathematical and Statistical Frontiers(ACEMS) at QUT, said the use of Bayesian statistics is highly suited to modelling areas and populations most at risk, estimating population size and incorporating uncertainty in decision making.
“Bayesian statistical modelling is not new but its popularity still remains high, mainly due to advances in modern simulation computer software and its suitability to tackle challenging real-life issues such as making informed decisions under uncertainty and to predict outcomes for koalas and other species,” Dr Johnson said.
“We see this project as being of significant use to Biosecurity Queensland and other wildlife agencies.
“The combination of aerial robotics, tracking, statistical modelling and wireless identification devices are invaluable in monitoring the health and reintegration of rehabilitated injured animals into their previous habitat, or for reintroduction and relocation of endangered and threatened species.”
The aerial robot was flown using manual control and programmed to fly autonomously across a section of bushland around Australia Zoo’s Wildlife Hospital above and parallel to the tree line.
To view vision captured by the aerial robot, visit https://www.youtube.com/watch?v=tVplwN7xP1w&feature=youtu.be
QUT is the base of the Australian Research Council Centre of Excellence in Robotic Vision which aims to deliver the breakthrough science and technologies to create a new generation of robots that can visually sense and understand complex and unstructured real-world environments.
Media contact:
Amanda Weaver, QUT Media, 07 3138 9449, amanda.weaver@qut.edu.au
After hours: Rose Trapnell, 0407 585 901.
QUT’s new unmanned aerial systems funding to target plant pests
22 September 2014QUT is the Queensland lead in a new international biosecurity research program involving unmanned aerial systems (UAS).
Under the three-year project UA (unmanned aircraft) will be fitted with new high-tech imaging equipment to test how effective they are in identifying pests and diseases in horticultural and grains industries.
Australia’s Plant Biosecurity Cooperative Research Centre (PBCRC) is providing $1.74 million towards the new $6.5 million project, Optimising Surveillance Protocols Using Unmanned Aerial Systems.
The project will be led by CRC participants at Kansas State University (K-State), with QUT and the Victorian Department of Environment and Primary Industries as research partners.
QUT UAS project leader Dr Felipe Gonzalez said the university’s proven track record in relation to UAS and plant biosecurity cemented its place in the project.
“It’s very timely and a great opportunity to create the next generation of surveillance and UA for plant pest detection,” Dr Gonzalez said.
Dr Gonzalez said QUT would develop new surveillance protocols and advanced software for existing high-tech imaging equipment (hyperspectral and multispectral) that would pinpoint pests such as Stripe Rust found in wheat and Myrtle Rust currently threatening horticulture as well as native plants such as tea tree and bottle brush.
“We hope to show that the use of UA in detecting pests is both accurate and cost effective; that they enable more territory to be covered more cheaply and detect more pests,” he said.
“Pest surveillance in forest land in particular can be very dangerous in a conventional helicopter and the use of UA will enable us to fly closer so the imaging technology can be used to full advantage.
“Early detection and monitoring of harmful plant pest or disease incursions is time consuming but extremely important for plant biosecurity.”
Other QUT researchers involved in the project include Dr Grant Hamilton and Professor Duncan Campbell.
Dr Grant Hamilton, a specialist in analysing pests and invasive species, is responsible for using UASs to detect Yellow Stripe Rust in wheat crops.
“Part of detecting pests is to understand when they are likely to be there,” he said.
“We aim to incorporate these new technologies with better predictions, so ultimately farmers will have a cost effective way to detect pests.”
Dr Gonzalez said the project would also enable researchers to determine the optimal flying distance from target plants to enable better detection rates and the best image quality.
Professor Duncan Campbell, who is the director of the QUT-led Australian Research Centre for Aerospace Automation said the project had enormous potential to further knowledge of UAS technology.
He said Kansas State University in the US would target Russian Wheat Aphid and Wheat Stripe Rust and that the collaboration between the universities would have significant benefits to the aerospace and agricultural industries.
Media contact: Rose Trapnell, QUT media team leader, 07 3138 2361 or 0407 585 901 rose.trapnell@qut.edu.au
Integrated Intelligent Airborne Sensing 