PyCharm, Raspberry Pi Compute Module 4, & POE Variants
Our update covers a few topics this week. First up, we made a quick video guide on using PyCharm with DepthAI. Then, a first look at the Raspberry 4 Compute Module Edition prototype. Finally, we are also about to order our first POE DepthAI Onboard Cameras edition, so we are asking for your feedback! Read the full update.
A Whole Bunch of New DepthAI Capabilities
Hi DepthAI Backers! Thanks again for all the continued support and interest in the platform. So we've been hard at work adding a TON of DepthAI functionalities, including RGB-depth alignment, Subpixel capability, and more. You can also check out our recent interview with Chris Gammel at Amp Hour. Read the full update.
Pure Embedded DepthAI Under Development
So, we've proof-of-concepted an SPI-only interface for DepthAI and it's working well (proof of concept done with MSP430 and Raspberry Pi over SPI). Read the full update.
New Spatial AI Capabilities & Multi-Stage Inference
We have a super-interesting feature-set coming to DepthAI: 3D feature localization (e.g. finding facial features) in physical space, parallel-inference-based 3D object localization, two-stage neural inference support. Read the full update.
DepthAI Now Supports the Raspberry Pi HQ Camera
More great news coming at you! We've accomplished so much so fast recently that it's hard to keep up with the updates. Over the weekend we wrote a driver for the IMX477 used in the Raspberry Pi HQ Camera. Read the full update.
Announcing DepthAI Experiments GitHub
We are excited to announce a new addition to the open-source DepthAI ecosystem: DepthAI Experiments. Read the full update.
Fighting COVID-19!
Hello DepthAI Fans! We're super excited to share that Luxonis DepthAI and megaAI are being used to help used to help fight COVID-19! How? To know where people are in relation to a Violet, Akara's UV-cleaning robot. Read the full update.
Announcing megaAI Campaign
Introducing megaAI! Luxonis has made a new product dubbed megaAI and we're launching a new Crowd Supply campaign today. What is it? A MEGA-powerful yet physically-tiny 4k/60 camera powered by the machine learning technology behind DepthAI. Read the full update.
Open Hardware
As promised, we have open sourced the DepthAI hardware! Now you can integrate the power of DepthAI into your custom prototypes and products at the board level. Read the full update.
Custom Training & Other Progress
We're continuing to work hard on DepthAI resources, so we have an exciting slew of updates for you! Most importantly, we now have a Custom Training Tutorial which uses Google Colab, so you can train your own custom models for DepthAI completely for free. Read the full update.
New Product & Delivery Status
From all of us here at Luxonis we hope you are all staying healthy and our hearts are out to any of you who may be suffering during this pandemic. We have a new DepthAI product available - USB3 with Onboard Cameras - and are happy to announce that pending pre-orders will be shipping soon. Read the full update.
Multi-Device Support
We just got multi-DepthAI support working yesterday and successfully tested today! We're working with Akara.ai to make a UV-based cleaning robot to help fight COVID-19 to clean public spaces without having to risk infecting people. And to clean things (like sensitive medical equipment) which can't be cleaned chemically. Read the full update.
Shipping Begins Next Week
We've packed and shipped your hardware to Crowd Supply and put the finishing touches on the software. Crowd Supply will be shipping out your orders next week. Now is a good time to check your shipping address and update it if needed. Read the full update.
Live help via our Slack community
We know you'll have questions as you get started, so we thought: why not create a Slack Community for our backers? So, we did! Read the full update.
Hardware Builds Complete
We have now finished doing assembly and tests on all of the units. Read the full update.
USB3 and SoM PCB Assembly Complete
An update on which PCBAs are finished and which are still being assembled. This year, Chinese New Year is January 18th through February 2nd. Our strategy on fulfillment is (and has been) to conclude all the China-involved production prior to January 11th, doing the remainder of the full-system assembly and test in the United States while China is offline. It looks like we're still on schedule to hit this, but it going to be close! Read the full update.
Goal Adjustment and Production Progress
We're adjusting the goal to account for a couple post-funding cancellations. More importantly, we are making great progress on production so far. The bare PCBs for everything are completed and under assembly now. Check out some pictures of the incoming hardware and bare PCBs! Read the full update.
Everything Ordered
Hi DepthAI Fans! So we ordered the last of everything for our first production run last Friday (December 13th). Read the full update.
Power and Stability Comparison
So we got great news from one of our Alpha testers. They are using the DepthAI: System on Module (SoM) in their own custom board and have reported infinitely better stability and 1W less power use. Read on for details. Read the full update.
Funding Goal Change
We're confident in the success of the future of DepthAI - so we're adjusting our funding goal. Here is why. Read the full update.
New Features
We've been hard at work adding support for various network architectures through our Python API. Check out our progress on object detector models, neural models, and more! Read the full update.
Human Level Perception
So we wanted to share a bit of the background on object detection, our experience with it, and why we made DepthAI to allow object localization. Read the full update.
Object Detection vs. Localization
Out of the questions we've received in the campaign so far, we've realized that we haven't done a great job of showing what object detection is vs. object localization. So we made an animation to clarify! Also, yesterday we kicked off our first large production run of the DepthAI SoM. Read the full update.
Progress & Pre-Alpha Feedback
Over the past week the DepthAI team has been busy with a slew of efforts. Read the full update.
Demo with Integrated Raspberry Pi
Today we share some examples of the power and convenience of having an integrated Raspberry Pi in DepthAI. The great thing about having the integrated Raspberry Pi is that it works with so many peripherals cleanly. An example of this is live-demoing DepthAI in Dublin last week, plugging DepthAI directly into the projector for the first time live during the presentation. And it went without a hitch. Read the full update.
Backstory - Commute Guardian
The 'why' of the DepthAI (that satisfyingly rhymes) is we're actually shooting for a final product which we hope will save the lives of people who ride bikes, and help to make bike commuting possible again for many. What we envisioned is a technology-equivalent of a person riding backwards on your bike holding a fog horn and an ambulance-LED strip, who would tap you on the shoulder when they noticed a distracted driver, and would use the LED strip and the horn judiciously to get the attention of distracted drivers - to get them to swerve out of the way. Video demos included! Read the full update.
We're Live!
This campaign is now live! DepthAI is a platform built around the Myriad X to combine depth perception, object detection (neural inference), and object tracking that gives you this power in a simple, easy-to-use Python API. It's a one-stop shop for folks who want to combine and harness the power of AI, depth, and tracking. Read the full update.