AI system developed to instantly identify and catch animal poachers
Image credit: DT
A new artificial intelligence (AI) system has been developed that can instantly detect poachers, enabling authorities in Botswana to catch them before the protected wildlife are killed.
Thousands of animals including elephants, tigers, rhinos, and gorillas are currently poached each year and many of the perpetrators are never caught.
Researchers at the USC Center for Artificial Intelligence in Society have long been applying AI to protect wildlife.
Initially, computer scientists were using AI and game theory to anticipate the poachers’ haunts. Now, they have further applied artificial intelligence and deep learning to spot poachers in near real-time.
Poachers are normally active at night. While tools such as infrared cameras are used to monitor living organisms, since both the poachers and the animals they are hunting give off heat, it is time-consuming and challenging to monitor infrared video streams for poachers all night.
A team of computer scientists, led by Elizabeth Bondi, a USC Viterbi School of Engineering PhD student in Professor Milind Tambe’s lab, labelled 180,000 humans and animals in infrared videos using a labelling tool they developed to expedite the process.
The researchers used these labelled images and leveraged an existing deep-learning algorithm known as Faster RCNN, which they modified to teach a computer to automatically distinguish infrared images of humans from infrared images of animals.
The challenge then was to deploy this algorithm to spot poachers in near-real time using the laptop computers at base stations in the field, where footage is streamed from the drones that are being used to patrol national parks in Zimbabwe and Malawi.
The algorithm, while functioning with accuracy, was taking 10 seconds to process each image - too long for the moving vehicles.
The goal was then to further modify the algorithm so it could be used by a regular laptop. The researchers changed the algorithm to work with Microsoft Azure, leveraging the power of the cloud to build a virtual computer that could do faster processing.
The researchers also developed an alternative solution for spotty interconnectivity in rural areas so that the software could still work from a laptop. The algorithm now works to detect poachers and animals in just over three-tenths of a second.
Named ‘Spot’, or Systematic POacher deTector, this algorithm will be deployed on a large scale across Botswana.
“Spot will ease the burden on those using drones for anti-poaching by automatically detecting people and animals in infrared imagery and by providing detections in near-real time,” Bondi said.
Last year, the horns of critically endangered black rhinos were implanted with sensors to allow park rangers to track their routines and whereabouts.