Computer vision
19
MENTIONS
5
EPISODES
5
PODCASTS
Search complete. 19 mentions across 5 episodes found for "Computer vision".
Sep 17, 2026
Nick TawilHOST
Well, what were you doing before this, before Herculaneum got onto your radar as a challenge? What were you doing before that?
Brent SealesGUEST
Well, I'm a computer vision and an imaging specialist, and I did my PhD work at the University of Wisconsin in the field of computer vision.
Brent SealesGUEST
Computer vision can be defined as sort of making computers and cameras work together to be able to either imitate what humans can do visually or to solve problems in the world autonomously.
Brent SealesGUEST
And so you see computer vision now every day succeeding with facial recognition, autonomous cars, all of the remote sensing
Nick TawilHOST
that happens.
Brent SealesGUEST
The early days when I started that work led me into applications like manufacturing cameras.
13 MINS LATER
Brent SealesGUEST
Okay.
Brent SealesGUEST
Uh, that's, we're not even close to that right now, but you know, imagine that you go to the, you know, scanner for your receipts from travel and, um, As long as it takes for it to scan is how long it takes for you to get the OCR and the thing to be uploaded, right? That happens right now for receipts and things like that for OCR.
Herman PoppleberryHOST
No learning involved.
Herman PoppleberryHOST
The MIT Computer Vision textbook has a whole chapter on it, and the chapter opens by saying, we could train a huge neural network to do this, but that would be no fun, so we're going to derive it from first principles instead.
Herman PoppleberryHOST
I respect a textbook with opinions.
Herman PoppleberryHOST
It's the right instinct for this problem, because the geometry is actually tractable.
13 MINS LATER
Herman PoppleberryHOST
Single view uses one image plus one known size.
Herman PoppleberryHOST
And the math is old.
Herman PoppleberryHOST
1999 is ancient in computer vision years.
Herman PoppleberryHOST
The cross ratio is older than that.
Martijn GraatHOST
Hello, I'm Martijn Gaat and this is Does Logistics Matter, a podcast about trends and innovations in supply chain and logistics.
Martijn GraatHOST
Answering yes to the question today are Herbert Den Haven, serial tech entrepreneur in AI, robotics and computer vision, and Peter Skolf, founder and CEO of Innoscale.
Martijn GraatHOST
In this episode, we talk about the evolution of warehouse automation, the challenges of brownfield versus greenfield implementations, the role of AI and robotics, and the importance of data and ROI.
Martijn GraatHOST
Please enjoy my conversation with Herbert ten Have and Pieter Skov.
21 MINS LATER
Peter SkovGUEST
Because also one of the discussions with some of my customers is the most labor-intensive is those picking stations.
Peter SkovGUEST
And there's two ways of doing it.
Peter SkovGUEST
You either put in computer vision, so you don't have to scan anymore.
Peter SkovGUEST
That would save a lot of money.
MehulGUEST
the most non-technical person in our team.
MehulGUEST
My knowledge of computer vision and robotics is enough to be dangerous.
MehulGUEST
So I've been always, I got very lucky in joining this startup called like.com LLK back in 2005.
MehulGUEST
And that was the first computer vision startup in Silicon Valley.
MehulGUEST
And And back in 2005, Computer Vision was a little bit like quantum computing today, super esoteric.
MehulGUEST
No one really knew much about it.
MehulGUEST
So I got very lucky in joining this company.
MehulGUEST
I was focused on product and marketing side of things.
Rajat BhageriaGUEST
And I was doing that.
Rajat BhageriaGUEST
But what happened is at the time, I started my real first company, I would say, which is called Third Eye and Computer Vision.
Rajat BhageriaGUEST
And it's just too hard to do all three things.
Rajat BhageriaGUEST
And kind of like the computer science courses, I had already taken a bunch of the basics, algorithms and data structures and all that stuff.