Hello trend,
This is Satya Mallick from LearnOpenCV.com.
Today, we present a comprehensive Introduction to MediaPipe, a high-performance framework initially developed by Google for real-time video and audio analysis on YouTube.
Gradually it got integrated into many more products, such as perception system in NestCam, object detection by Google Lens, Augmented Reality Ads, Google Photos, Google Home, Gmail, and Cloud Vision API. In 2019, it was open-sourced!
We will learn about MediaPipe Toolkit: Framework and Solutions.
The MediaPipe Framework consists of APIs for high-performance application development.
MediaPipe Solutions help you integrate Face Detection, Face Mesh, Iris Detection, Hand Detection, Pose Estimation, Selfie Segmentation, Hair Segmentation, Object Detection, Box Tracking, and many more models in your application with just a few lines of code.
Interested to learn more? Let's get started.
| Introduction to MediaPipe |
There is no code associated with this post.
Kickstarter Update: Good & Bad News
First, the good news.
🔥 With the help of 360+ backers, we have raised more than $140K in our Kickstarter campaign for Deep Learning with Tensorflow & Keras.
🔓 This milestone unlocks our first stretch goal. We will add a new module on deploying models as a web application using Streamlit.
🙏 Thank you backers!
Now, the bad news.
The price of OAK-D-Lite add-on will go up in 6 hours (midnight Pacific Time). For now, you can still back it at $99.
Fun facts about OAK-D-Lite
Here are some fun facts about OAK-D-Lite.
- Launched with $1M Kickstarter campaign last year that brought affordable spatial AI to everyone.
- Spatial AI Competition : It is the hardware used by contestants of OpenCV Spatial AI Competition.
- Technical Specs & Features
- 4K RGB camera (30 FPS).
- Depth estimation: A 200 FPS stereo pair at 640x480.
- Powered by Intel's Myriad X : 4 Trillion Operations Per Second (TOPS) processing power. 1.4 TOPS for AI.
- Run any AI model, even custom architectured/built ones
- Computer vision: warp/dewarp, resize, crop, edge detection, feature tracking.
- Object tracking: 2D and 3D tracking.
- Encoding: H.264, H.265, MJPEG - 4K/30FPS, 1080P/60FPS.
Learn more about OAK-D-Lite here
How to get the OAK-D-Lite Add-on?
If you have already backed our campaign and want to change your pledge to include this add-on, please check out this video for instructions.
If you want to back our campaign including this add-on, please check out this video for instructions. In the same video we also show how to get the add-on without backing the course by pledging $1.
Shipping costs and customs duty for OAK-D-Lite
Please note that backers have to pay the shipping costs and customs duty.
You can get an indicative cost of shipping using the link below.
https://www.easyship.com/en-hk/shipping-rate-calculator/hongkong-to-usa?unit=lbs&weight=0.5
You can get an indicative view of customs duty and associated tax using the link below. There is no customs duty for shipping to US locations.
https://www.simplyduty.com/import-calculator/
Your credit card will not charged until the end of the campaign. You have about two weeks to change your mind, but only 6 hours to get OAK-D-Lite at this incredible price of $99.
| Kickstarter : DL with Tensorflow & Keras |
Cheers!
Satya
No comments:
Post a Comment
Note: Only a member of this blog may post a comment.