Here’s a great lecture from Stanford University introducing the core concepts of convolutional neural networks for computer vision.
Dr Mike Pound on the Viola/Jones algorithm, a face detection algorithm that does not use deep learning, but is so good that it’s still in use today.
The original Viola/Jones Paper: http://bit.ly/C_RapidObjectDetectPaper
One of the key attributes of a self-driving car is being able to detect what lane the car should be driving in. Here’s a great tutorial on how to do just that in Python with OpenCV.
One of the great sample apps that show off the art of the possible is the Intelligent Kiosk sample application. In this video, Noelle LaCharite shows how to use this sample application to learn cognitive services and test applications that you are infusing with AI.
Computer Vision made easy: from pre-trained models to custom ones, Cognitive Services has you covered.
In this video, Kelly Freed, PM on the Azure Cognitive Services team, and learn about the latest technologies in Computer Vision such as analyzing images, extracting insights from your pictures and videos, recognizing common objects, and more.
Yesterday, I was in Philadelphia presenting a session at AI Discovery Day on Computer Vision Cognitive Services.
The labs for this session are on GitHub: https://github.com/Azure/LearnAI-Bootcamp/tree/master/lab01.1-computer_vision
These events will be taking place across the US. Here are a few dates and links to registration.
Press the play button below to listen here or visit the show page at DataDriven.tv
Earlier today, I wrote a blog post about Video-to-Video synthesis done by researchers at Nvidia. The Washington Post highlights how the Silicon Valley company founded in 1993, best known for graphics cards, has embedded itself in nearly every autonomous vehicle effort.
See why in this video and how their AI deep learning is changing autonomous vehicles.
If you thought the technology behind Deep Fakes was impressive, then you will be floored by this demonstration of “Video-to-Video Synthesis.”
Best of all: the code is available on GitHub
Here’s another great Two Minute Papers video on DeepMind’s venture into computer vision.