Facial recognition to save elephants from poachers


Charlie Parker, The Times

Date Published

See link for photo.

Advanced facial recognition technology that will help conservationists to track elephants and send alerts when poachers are near by is being worked on by London Zoo and Google.

The software is already capable of recognising people within images, but now animal and tech experts hope that automatic cameras hidden in the wild and triggered by heat and motion will allow local authorities to monitor endangered species and keep them safe.

Elephants are among the mammals being tracked with the new technology. While the Google App imaging system was designed to scan people’s eyes, nose and chin, the conservation project will use it to identify trunks, tusks and tails.

As well as recognising animals, the Google machine learning software will also search for the shape of potential poachers and will send out warnings if they appear to be suspicious.

The Zoological Society of London (ZSL) said that the technology could be effective in the battle against poachers as it would be able to “get to know” pachyderms: very large mammals such as the elephant, rhinoceros and hippopotamus. 

When new animals are captured by the automatically activated cameras, a conservation worker will initially record their features and put the data into the system. If the same individual wanders into frame again, the software will manage new images independently and will be able to build a profile for the animal.

About 1.5 million of the animals on ZSL’s database have been scanned onto Google’s servers so far, including giraffes in Kenya and orangutans in Borneo. It is hoped that entire herds will eventually be tracked by the computers.

The software was released last week to allow organisations to build their own machine learning programmes without the need for specialists. 

The chief scientist at Google Cloud’s artificial intelligence branch said that the company had released a more user-friendly version of the software to “lower the barrier of entry” and make AI accessible to the “largest possible community”. It has already been put to use by businesses, with companies including Disney and Urban Outfitters using it to organise product categories and improve search and shopping on their websites.

Wildlife workers said that AI could also help to protect endangered species by saving manpower, removing the need for humans to trawl through large volumes of images. Technology developers also hope to program it to recognise when animals are injured.

“We are tracking wildlife populations to learn more about their distribution and better understand the impact humans are having on these species,” Sophie Maxwell, ZSL’s conservation technology chief, said. “We have deployed a series of camera traps in the wild that take pictures of animals when triggered by heat or motion. The millions of images captured by these devices are then manually analysed and annotated with the relevant species, such as elephants, lions and giraffes, which is a labour-intensive and expensive process.

“Our conservation technology unit has collaborated closely with Google’s Cloud team to help shape the development of this exciting technology, which ZSL aims to use to automate the tagging of these images.”