Penguin watch: Data science firm Gramener counts penguins with help of AI

By: |
Published: January 25, 2020 12:05:48 AM

A new crowd counting solution helps researchers count penguin populations more accurately

Penguin, Data science, Gramener, British Antarctic Survey, Emperor penguin, Intel AI Builder, Naveen Gattu, Penguin Watch Project, Microsoft AI for Earth, Intel Xeon Scalable processor, Intel Optimization for PyTorch, Naveen Gattu
Antarctica’s penguin populations are at serious risk. According to a 2019 study from the British Antarctic Survey, the world’s largest Emperor penguin colony has suffered unprecedented breeding issues for the past three years, is uniquely vulnerable to ongoing and projected climate change, and could virtually disappear by the year 2100. In order to study penguin populations, researchers first need to accurately count them.

A new crowd counting solution from Intel AI Builder member and data science company Gramener could enable researchers to use computer vision to count penguin populations faster and more accurately.

It’s important to understand the impact we are having on penguin populations in Antarctica,” said Naveen Gattu, COO and co-founder of Gramener.

“We believe that AI has the power to help researchers identify what is causing their decline, and are proud to be using Intel AI technologies for applications of social impact. Our crowd counting solution has the potential to help us better understand penguin populations.”

Penguin, Data science, Gramener, British Antarctic Survey, Emperor penguin, Intel AI Builder, Naveen Gattu, Penguin Watch Project, Microsoft AI for Earth, Intel Xeon Scalable processor, Intel Optimization for PyTorch, Naveen GattuNaveen Gattu, COO and co-founder, Gramener

Gramener used an image dataset of Antarctica’s penguin colonies from the Penguin Watch Project, which included images from over 40 locations. In partnership with Microsoft AI for Earth, Gramener researchers trained a deep learning model to count the penguins. The model uses a density-based counting approach to approximate the number of penguins in clusters of different sizes from the images. This solution has been repurposed and benchmarked on Intel Xeon Scalable processors and the Intel Optimization for PyTorch for optimised performance.

This solution could help researchers overcome challenges in manually counting penguins from camera traps, which can be tricky due to perspective distortion, penguins standing too close together or clustering, and diversity of camera angles.

Get live Stock Prices from BSE and NSE and latest NAV, portfolio of Mutual Funds, calculate your tax by Income Tax Calculator, know market’s Top Gainers, Top Losers & Best Equity Funds. Like us on Facebook and follow us on Twitter.

Next Stories
1Google, Apple clash over web browser privacy
2Vivo’s iQOO set to launch 5G smartphone soon in India; Check date, time
3Shocking! Algorithms of online platforms maximise profits from hateful digital content