Nav: Home

Drones survey African wildlife

July 11, 2018

A new technique developed by Swiss researchers enables fast and accurate counting of gnu, oryx and other large mammals living in wildlife reserves. Drones are used to remotely photograph wilderness areas, and the images are then analysed using object recognition software and verified by humans. The work is reported in a paper published in the journal Remote Sensing of Environment. (*)

The challenge is daunting: some African national parks extend over areas that are half the size of Switzerland, says Devis Tuia, an SNSF Professor now at the University of Wageningen (Netherlands) and a member of the team behind the Savmap project, launched in 2014 at EPFL. "Automating part of the animal counting makes it easier to collect more accurate and up-to-date information."

No animal left uncounted

The drones make it possible to cover vast areas economically. But it's more complicated than simply sending them up to photograph the terrain: more than 150 images are taken per square kilometre. At first glance, it's hard to tell the animals from other features of the landscape such as shrubs and rocks.

To decipher this mass of raw visual data, the researchers used a kind of artificial intelligence (AI) known as "deep learning". Conceived by PhD candidate Benjamin Kellenberger, the algorithm enables researchers to immediately eliminate most of the images that contain no wildlife. In the other images, the algorithm highlights the patterns most likely to be animals.

This initial phase of elimination and sorting is the longest and most painstaking, says Tuia. "For the AI system to do this effectively, it can't miss a single animal. So it has to be have a fairly large tolerance, even if that means generating more false positives, such as bushes wrongly identified as animals, which then have to be manually eliminated."

The team started by preparing the data needed to train the AI system to recognise features of interest. During an international crowdsourcing campaign launched by EPFL, some 200 volunteers tracked animals in thousands of aerial photographs of the savannah taken by researchers at the Kuzikus wildlife reserve in Namibia.

These images were then analysed by the AI system, which had been trained by scoring based on different types of errors: the AI system is given one penalty point for mistaking a bush for an animal, whereas the penalty for missing an animal completely is 80 points. As a result, the software learns to distinguish wildlife from inanimate features, but especially not to miss any animals. Once the collection of images has been whittled down by the AI system, a human takes over the final sorting, made easier by coloured frames automatically placed around questionable features.

100 square kilometres per week

This semi-automated technique was developed in collaboration with biologists at the Kuzikus wildlife reserve in Namibia. Since 2014, the researchers have periodically flown over the reserve using drones designed and optimised by SenseFly, a Swiss company, and equipped with compact, standard cameras. "In the beginning we were rather sceptical," says Friedrich Reinhard, director of the reserve. "The drones produce so many images that I thought it would be difficult to use."

But, thanks to the sorting performed by the AI system, just one person can carry out a full count of the Namibian reserve - an area of around 100 square kilometres - in about a week. In contrast, conventional methods involve entire teams taken aboard a helicopter. These methods are both less accurate and so expensive that they are rarely used - once a year at most in Kuzikus.

The Swiss researchers are continuing their work with the Namibian reserve. EPFL students travel there regularly. The Kenyan authorities have also expressed interest, as has the Veluwe National Park in the Netherlands. Recently appointed professor at the University of Wageningen (Netherlands), Devis Tuia still works closely with the University of Zurich (where he was SNSF Professor) and EPFL, which coordinates the Savmap project.
-end-
(*) Detecting Mammals in UAV Images: Best Practices to address a substantially Imbalanced Dataset with Deep Learning, Remote Sensing of Environment (2018). DOI: 10.1016/j.rse.2018.06.028 https://authors.elsevier.com/a/1XKYp7qzSjUbR

Contact

Prof. Devis Tuia
Laboratory of Geo-information Science and Remote Sensing
Wageningen University & Research
Droevendaalsesteeg 3
6708 PB Wageningen
The Netherlands

Tel: +31 317 489 403
E-mail: devis.tuia@wur.nl

Promoting young researchers

The SNSF has launched a new funding scheme to support researchers aiming to obtain a professorship. SNSF Eccellenza Grants allow tenure-track assistant professors to form a new research team and lead an ambitious scientific project. SNSF Eccellenza Professorial Fellowships cover the salaries of assistant professors as well as their project costs. The new scheme replaces the SNSF professorship grant, which has supported 691 researchers since its launch in 2000 - with great success: around 80% of grantees went on to obtain a professorship at a higher education institution in Switzerland or abroad. http://www.snf.ch/fr/encouragement/carrieres/eccellenza

SNSF project: Multimodal machine learning for remote sensing information fusion http://p3.snf.ch/project-150593

Savmap project, EPFL https://lasig.epfl.ch/savmap

Swiss National Science Foundation (SNSF)

Related Wildlife Articles:

Kids' wildlife preferences differ from island to mainland
When asked to name their favorite wildlife, Bahamian children chose feral cats, dogs and pigs - invasive species that can be more damaging in an island environment.
How reliable are traditional wildlife surveys?
To effectively manage a wildlife species, one of the most basic things you need to know is how many of them are out there.
Rangers fight loss of wildlife with fire
Native animals are declining on Australia's second largest island with brush-tailed rabbit-rats, black-footed tree-rats and northern brown bandicoots the worst hit.
Wildlife-snaring crisis in Asian forests
A very important article co-authored by WCS scientist Tony Lynam has been published in this week's Science about a crisis emerging in Asia from snaring, which is wiping out wildlife in unprecedented numbers.
Are herders and livestock bad for rare wildlife? It's complicated.
The Denver Zoological Foundation, WCS (Wildlife Conservation Society) and other partners have published a paper appearing in the early view edition of Conservation Biology that looks at the positive and negative relationships occurring between pastoralists, livestock, native carnivores and native herbivores in the world's largest unfenced grassland and desert.
Coastal wildlife more vulnerable to microplastics than expected
Coastal-dwelling marine wildlife, including crabs, lobsters and shellfish, which play a crucial role in the food chain, are more vulnerable to harmful plastic pollution than previously expected, a new study has found.
New book focuses on importance of Indian forests for wildlife
India's protected areas are at a crossroads, and a new book by top Indian scientists provides a roadmap on the way forward.
UK wildlife calendar reshuffled by climate change
Climate change is already reshuffling the UK's wildlife calendar, and it's likely this will continue into the future, according to new research published this week in the journal Nature.
Using drones without disturbing wildlife
Unmanned aerial vehicles (UAVs), more popularly known as drones, are increasingly employed to monitor and protect wildlife.
Call to minimize drone impact on wildlife
University of Adelaide environmental researchers have called for a 'code of best practice' in using unmanned aerial vehicles (drones) for wildlife monitoring and protection, and other biological field research.

Related Wildlife Reading:

Wildlife
by Richard Ford (Author)

Wildlife of the World (Dk Smithsonian)
by DK (Author), Don E. Wilson (Foreword)

North American Wildlife: An Illustrated Guide to 2,000 Plants and Animals
by Editors of Reader's Digest (Author)

National Geographic Illustrated Guide to Wildlife: From Your Back Door to the Great Outdoors
by National Geographic (Author), Catherine Herbert Howell (Author)

Wild Life
by Cynthia DeFelice (Author)

Where the Animals Go: Tracking Wildlife with Technology in 50 Maps and Graphics
by James Cheshire (Author), Oliver Uberti (Author)

Wildlife
by Jeff Menapace (Author)

Wildlife 911
by John Borkovich (Author)

Field Guide to Urban Wildlife: Common Animals of Cities & Suburbs How They Adapt & Thrive
by Julie Feinstein (Author)

Wild and Crazy: Photos from the Comedy Wildlife Photography Awards
by Paul Joynson-Hicks (Author), Tom Sullam (Author)

Best Science Podcasts 2018

We have hand picked the best science podcasts for 2018. Sit back and enjoy new science podcasts updated daily from your favorite science news services and scientists.
Now Playing: TED Radio Hour

Dying Well
Is there a way to talk about death candidly, without fear ... and even with humor? How can we best prepare for it with those we love? This hour, TED speakers explore the beauty of life ... and death. Guests include lawyer Jason Rosenthal, humorist Emily Levine, banker and travel blogger Michelle Knox, mortician Caitlin Doughty, and entrepreneur Lux Narayan.
Now Playing: Science for the People

#491 Frankenstein LIVES
Two hundred years ago, Mary Shelley gave us a legendary monster, shaping science fiction for good. Thanks to her, the name of Frankenstein is now famous world-wide. But who was the real monster here? The creation? Or the scientist that put him together? Tune in to a live show from Dragon Con 2018 in Atlanta, as we breakdown the science of Frankenstein, complete with grave robbing and rivers of maggots. Featuring Tina Saey, Lucas Hernandez, Travor Valle, and Nancy Miorelli. Moderated by our own Bethany Brookshire. Related links: Scientists successfully transplant lab-grown lungs into pigs, by Maria Temming on Science...