It’s a storyline worthy of a crime drama. The remains of the victims have been discovered, and now it’s up to the investigators to find out who they were and where they came from. But the victims are not people, they are endangered tigers.
The tiger population in Asia has declined dramatically over the past 100 years. There are now believed to be less than 4,500 wild tigers in the world. The biggest culprit in the decline of the iconic animals has been poaching to feed the illegal trade in tiger parts.
Some of those illegal products are used in traditional medicines, but tiger skins are also highly valued as a decorative item.
However, the unique striped coats that have made them so sought-after are also helping conservationists tackle the poaching problem — and they should soon be getting a big helping hand in those efforts from artificial intelligence (AI).
PRAKASH MATHEMA/AFP/Getty
Campaigners have been working hard to build a database of photos of individual tiger skins. The idea is to identify and track where illegally traded pelts come from, to contact law enforcement agencies in different countries and help stop people smugglers.
“Each tiger’s stripe profile is unique, as are our fingerprints,” Debbie Banks, the Tigers & Wildlife Crime campaign manager at the London-based Environmental Investigation Agency (EIA), told France’s AFP news agency. “So we can use tiger stripes if we see images of tigers for sale online, or if we have images of tigers for sale in marketplaces or seized. We can use those images to compare with images of tigers in captivity that may have been commercially bred, and we can help identify the points where the tigers we see on the trade come from.”
Banks and her team at the EIA have studied thousands of often crowd-sourced photos of tiger skin carpets, carcasses and even stuffed tigers to match the stripe patterns with individual tigers to track where the animals came from, but it’s moving extremely slowly. work.
That, they hope, will change.
The EIA recently received one of the first grants from the Alan Turing Institute, a UK-based center for data, science and artificial intelligence named after the famous WWII codebreakerand it’s now developing a tool that uses AI to do the accurate comparison work.
“We have a database of images of tigers that have been put up for sale or that have been seized, and when new images appear, when our researchers get new images, we have to scan them with the database. Right now, we do that manually, looking at the individual stripe patterns of each new image we get and comparing them to the images we have in our database,” explains Banks. “The idea is that the artificial intelligence will do that — in effect, the scientists will create an algorithm, meaning they identify the individual stripe patterns of a unique individual tiger.”
The EIA has called on anyone who sees tigers, dead or alive, to submit photos, along with any identifying information available to help build the database.
“To develop, train and test the technology, we need thousands of images of individual tiger stripe patterns, sourced from EIA personnel, other organizations and you!” the group said in a press release announcing the project.
“This is a unique opportunity for tiger enthusiasts around the world to get started and actually contribute to the future conservation of tigers,” Banks said in a statement.
It is hoped that the technology will one day be used to help other vulnerable species, and bankrupt the people who exploit those species, but for now the focus is on putting it to use to help the big cats. to rescue.
.