A new project, jointly led by the University of Stirling and Dutch startup Hack the Planet, has developed for the first time an artificial intelligence (AI)-powered wildlife camera that can greatly benefit conservation by identifying human-animal conflict in real time.
The technology, which can detect different species of animals and humans in real time, has the potential to detect conflicts between people and wildlife, as well as illegal activities in protected areas, and provide live alerts to environmental rangers.
Trail cameras are regularly used in wildlife surveys to detect threats to the ecosystem, but are often hampered in remote areas by a lack of broadband connectivity. The use of AI-powered wildlife cameras can solve this problem by providing instant alerts without the need for WiFi, long-range wireless or cellular coverage, helping to better preserve, protect and restore ecosystems as a result.
The study, titled “Real-time Alerts from AI-Enabled Camera Traps Using the Iridium Satellite Network: A Case Study in Gabon, Central Africa,” was published in Methods in ecology and evolutionElephants and humans have been pinpointed in remote areas of Gabon, where the technology has been deployed.
The pilot from researchers and engineers at the University of Stirling and Hack the Planet, part of digital products studio Q42, shows that these smart cameras can help spot poachers and prevent elephant conflicts that often occur in African rainforests, among other places.
The smart camera trap they have developed can instantly label images thanks to artificial intelligence and, if necessary, send a warning, for example, to the guards or the village.
Research shows that remote monitoring and offline analytics can be performed reliably. The system is also able to prevent conflict between humans and animals by deterring elephants from entering the village in search of food.
It is the first time that this innovative camera system has been rigorously tested under the challenging conditions of a rainforest. By combining an AI model, off-the-shelf camera traps, and custom hardware with satellite communication, it is now possible to send real-time information to sentinels from remote locations. Research shows that reliable analyzes can be done with the aim of preserving nature and the environment.
“Real-time data from smart cameras and other sensors can revolutionize how we monitor and protect the world’s most threatened ecosystems,” said Dr. Robin Whitock, a postdoctoral researcher at the University of Stirling at the time of the study. Progress made in this study shows that Real-time data can be used to make better decisions during critical situations.”
Tim van Deursen, founder of Hack The Planet, said, “With this beta, we have proven that AI-powered camera technology works and can have a positive impact on nature conservation. Our solution does not depend on installing additional network infrastructure in the landscape and can Posted in the field by non-experts anywhere in the world.”
“Fewer of our conservationists will die, and more poachers will be arrested, if we can deploy this technology,” Gabonese Minister of Water, Forests, Sea and Environment told me White.
During the test flight in the rainforests of Gabon, five camera systems took more than 800 images in 72 days. 217 photos of elephants were taken. The AI model achieved an accuracy of 82% in recognizing elephants. The Rangers received a system alert within an average of seven minutes.
Robin C. Whytock et al., Real-time alerts from AI-enhanced camera traps using the Iridium satellite network: a case study in Gabon, Central Africa, Methods in ecology and evolution (2023). DOI: 10.1111/2041-210X.14036
Provided by the University of Stirling
the quote: New AI Wildlife Camera Developed to Improve Conservation (2023, January 9) Retrieved January 9, 2023 from https://phys.org/news/2023-01-ai-wildlife-camera.html
This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without written permission. The content is provided for informational purposes only.