AI In Wildlife Conservation

Synced
Synced
Oct 19 · 4 min read

AI has demonstrated its versatility in recent years, stepping out of the research labs and business world and into the arena of social good. Image recognition technology in particular has come to play a valuable role in wildlife conservation, where endangered species are tallied and tracked so their numbers and migrations can be more accurately measured and understood. Image recognition tech is able to identify animals from pictures captured by surveillance cameras deployed in their habitats, giving conservationists and other researchers more insight than ever before.

The World Wildlife Fund (WWF) is working with Intel to apply AI to monitoring and protecting Siberian tigers in northeastern China. The parties are leveraging their advantages in protecting wild tigers and AI technology respectively, with an integrated solution comprising a front-end visual device and a back-end analysis and recognition platform. The Intel Movidius visual device is deployed in tigers’ habitats for surveillance and data collection, while the platform incorporates Intel’s deep-learning library MKL-DNN and TensorFlow tools optimized for Intel architecture to provide analysis on collected images and track tigers. This initiative is an extension of Intel’s Tech for Good project, which also protects polar bears and whales throughout the world.

DeepMind, the UK-based AI company that created AlphaGo, is using machine learning to detect and count animals, using millions of pictures taken in the Serengeti National Park in Tanzania. It used to take up to a year from capturing a photograph to identifying the animals using human volunteers. DeepMind’s AI speeds up the process, and is already able to recognize most animal species with high accuracy.

Other AI-powered software for protecting animals is not deployed in savannas or jungles but rather on the Internet. The Conservation X Project’s “ChimpFace” tags chimpanzees in photos on social media and e-commerce websites to help detect potential wildlife trafficking. The model reduces the time spent by humans monitoring online wildlife trafficking activities and is an efficient and scalable tool for conservation organizations and law enforcement alike.

Although image recognition is the most widely applied AI tech in wildlife conservation, researchers and startups have also leveraged other tech to create devices and systems to protect animals in more proactive ways. PAWS (protection assistance for wildlife securities) is an AI tool designed to help rangers in the fight against poachers. It collects historical data of poaching activities and suggests patrol routes according to where poaching is most likely to occur.

Developed by computer science professor Milind Tambe and PhD students at University of Southern California, PAWS’s core algorithm is based on security games — where a defender tries to optimize limited resources to prevent attacks. PAWS was first tested in Uganda’s Queen Elizabeth National Park, and taken to Malaysia for a larger trial in 2014. The tests show that PAWS-assisted patrols outperform traditional patrols in both human activities and animals seen per kilometer surveyed.

San Francisco based nonprofit Rainforest Connection is also using tech to fight poaching. The startup’s RFCx acoustic monitoring system can recognize patterns of activity related to bushmeat hunting, such as the presence of trucks, cars and motorcycles. The system has been tested in Africa on key roads that poachers use to enter the rainforest. Poaching-related vehicles and patterns are identified so that organizations that protect the rainforest are able to allocate their limited manpower to target the hours and days when poaching activities are predicted to be statistically high. This improves the efficiency of anti-poaching work, especially after dark and during weekends.

Many research papers have been published and workshops held on the topic of AI and endangered species. The most commonly used technology is still image recognition, and the majority of the projects aim to estimate populations for research purposes.

Considering how quickly many of today’s endangered species are vanishing, additional powerful and pro-active tools like PAWS and the ChimpFace app will be required to actively counter poaching. In the future, we can expect to see new smart approaches that link frontier tech, wildlife conservationists and law enforcement in the fight to help animals.


Author: Jingya Xu | Editor: Michael Sarazen


We know you don’t want to miss any stories. Subscribe to our popular Synced Global AI Weekly to get weekly AI updates.


Need a comprehensive review of the past, present and future of modern AI research development? Trends of AI Technology Development Report is out!


2018 Fortune Global 500 Public Company AI Adaptivity Report is out!
Purchase a Kindle-formatted report on Amazon.
Apply for Insight Partner Program to get a complimentary full PDF report.

SyncedReview

We produce professional, authoritative, and thought-provoking content relating to artificial intelligence, machine intelligence, emerging technologies and industrial insights.

Synced

Written by

Synced

AI Technology & Industry Review — syncedreview.com | Newsletter: goo.gl/Q4cP3B | Become Synced Insight Partner: goo.gl/ucXZDw | Twitter: @Synced_Global

SyncedReview

We produce professional, authoritative, and thought-provoking content relating to artificial intelligence, machine intelligence, emerging technologies and industrial insights.

Welcome to a place where words matter. On Medium, smart voices and original ideas take center stage - with no ads in sight. Watch
Follow all the topics you care about, and we’ll deliver the best stories for you to your homepage and inbox. Explore
Get unlimited access to the best stories on Medium — and support writers while you’re at it. Just $5/month. Upgrade