HN Theater @HNTheaterMonth

The best talks and videos of Hacker News.

Hacker News Comments on
Level Up - AI Director

Google Cloud APAC · Youtube · 3 HN points · 1 HN comments
HN Theater has aggregated all Hacker News stories and comments that mention Google Cloud APAC's video "Level Up - AI Director".
Youtube Summary
Welcome to Level Up! the show where we show you how to build solutions hands-on with Google Cloud Platform.

In this episode, Solutions Architect Markku Lepistö will show you how to analyze camera feeds with AI, using the Google Coral USB Accelerator. And then how to switch between cameras automatically, with both OBS Studio, and Blackmagic ATEM Mini Pro.

01:22 - Introduction to Google Coral USB Accelerator
01:32 - What is the Coral PoseNet Machine Learning model
02:06 - Creating a Coral Edge TPU client in Python code
02:13 - Inference response from PoseNet ML model
02:55 - Analyzing which camera the presenter is facing
03:36 - Switching cameras programmatically with OBS Studio
05:06 - Controlling OBS scene switching with AI
06:01 - Blackmagic ATEM Mini and atemOSC
06:36 - Controlling ATEM Mini camera switching with AI

Free Trial: Google Cloud Platform → https://goo.gle/2u5itEB

Hands-on training with Qwiklabs
→ Application Development - Python - https://goo.gle/36hUejw
→ Machine Learning APIs - https://goo.gle/2RIUqmq
→ Google Cloud Platform Essentials - https://goo.gle/2vdcFcf

Follow us on Twitter
→ https://twitter.com/googlecloud_ANZ
→ https://twitter.com/googlecloud_IN
→ https://twitter.com/googlecloud_SG

Subscribe to our Google Cloud APAC channel for more for more episodes where we dive deeper and build on previous examples → https://goo.gle/2EsiSCC

References:
PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model. George Papandreou, Tyler Lixuan Zhu et al
https://arxiv.org/abs/1803.08225

Coral PoseNet. Mike Tyka et al
https://github.com/google-coral/project-posenet
HN Theater Rankings

Hacker News Stories and Comments

All the comments and stories posted to Hacker News that reference this video.
If you're looking for an even easier & cheaper way to start experimenting with an Edge TPU, the $59 Coral USB Accelerator has been out for a while now: https://coral.ai/products/accelerator

Check out the Level Up series for getting started: https://www.youtube.com/watch?v=-RpNI4ZrfIM

And here's a fun real-life application: https://www.youtube.com/watch?v=jIyM_qT9RZw

lxchase
I’m not versed in this field so curious, in that real life application, why not just use the computer you’re broadcasting from to run the camera switching client and ML inference. Does the USB accelerator do something that a standard desktop can’t?
kordlessagain
I put it on my Raspberry Pi 4 with some mobile-resnet version (88 objects) to do real time object detection from a Pi camera. It's quite a small package.
my123
The accelerator is much slower than just running on the host PC... an RTX 3070 has 81TOPs at FP16 and 162TOPs at INT8 for example.
lilSebastian
Doesn't the 3070 cost much more than a basic PC and the accelerator? Isn't this targets at those wanting to get their feet wet without vast outlay?
roseway4
Real-world use cases wouldn’t typically have a powerful computer broadcasting video. Rather, this board would be used at the edge to drive a camera and offer on-device, low-power inference.

Useful for robotics/drones, surveillance cameras, vehicles, consumer devices etc.

Aug 24, 2020 · 1 points, 0 comments · submitted by 9nGQluzmnq3M
Aug 20, 2020 · 2 points, 0 comments · submitted by 9nGQluzmnq3M
HN Theater is an independent project and is not operated by Y Combinator or any of the video hosting platforms linked to on this site.
~ yaj@
;laksdfhjdhksalkfj more things
yahnd.com ~ Privacy Policy ~
Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.