(Preview) Animal tracking

 | Original air April’24 | Season 5 Episode 11 Trailer | Dejan hosts Lianjie, Shivang, and Alex in the next Hewlett Packard Labs podcast. They discuss the ancient skill of animal tracking in Africa, and how it is being preserved and modernized with HPE technologies. They also share their experience of raising kids in Africa and living in the Bay Area.

What is From Research to Reality: The Hewlett Packard Labs Podcast?

This is a podcast about the many phases of technology innovation: ideas, research, development, management, marketing, and many others. We’re talking to a wide range of people with diverse and rich backgrounds including all species of engineers, scientists, mathematicians, business people and technical managers. We hope you will enjoy these podcasts as much as we did making them.

Hello, everyone.

I would like to introduce you
to the next week's full podcast,

which will feature a spotlight
on animal tracking.

Here in studio, I have Shivang and Lianjie.
Hello, Shivang! Hello Lianjie!

And remotely, we have Alex in Africa.

Alex, can you give us a quick summary
what you will be talking about?

I'm just very excited by this world.

First project to create an app
that allows us

to digitize the ancient craft of animal
tracking for the first time.

It's going to allow people who enjoy
nature to go, to go into wilderness areas

and be able to make sense of all the marks
on the ground

through this,
this cutting edge technology with HPE.

And how did you accomplish this?

So in our system,
we use machine learning technology

to preprocess
the image, including, removing the noise

and the segmenting images
to identify all the footprints.

And if the images are already labeled,
then we use them as training data

in the future.

And if they are not, we're going to use
them, store them as a backup.

And then we use the machine
learning, technology.

We also use them
to infer the species of the footprints.

And then we use a, deep convolutional
neural network science to do that.

and we pre-trained a neural network
on large public datasets.

And then we also fine tune them using the
footprints Alex has already collected.

Shivang.

This seems extremely complicated.

Have you simplified it
somehow? Yeah, I'll talk about.

We will talk about that in the podcast
for sure.

a key component of simplifying
it is the system that we build around

the whole, algorithm
that Lianjie mentioned, right?

Where we host the algorithm.

Where are the images coming from?

So I'll talk about the apps that are there
and available for Android now,

and the web apps
and the backend system that we have.

Thank you.

Gentlemen, please join us.

extremely interesting topic.

A great benefit to humanity preserving
animal tracking and the art, thereof.