I Built the AI Security Camera I Always Wanted
Vložit
- čas přidán 27. 06. 2024
- This nearly got me evicted…
*Product Links*
Raspberry Pi 5 👉 amzn.to/4autbm7
Coral Dual TPI 👉 amzn.to/3WTyTeg
External LCD Screen 👉 amzn.to/3QUWZRL
Pine Board Dual TPU Hat 👉 pineboards.io/products/hat-ai...
1x PCIE Expansion for RPi 5 👉 geekworm.com/products/x1010
Generic Web Cam 👉 amzn.to/3Rj3xdt
ReoLink IP Camera 👉 amzn.to/3UQ3feL
Contents:
00:00 - Intro
01:20 - Coral AI Hardware
01:48 - Power Draw
02:00 - Dual Edge TPU
02:16 - Pineboards Dual Hat
03:20 - Hardware setup
04:59 - Pineboard Dual TPU Hat
05:40 - Dual TPU Installation
07:56 - Optics
10:15 - Frigate Setup
14:07 - Surveillance Setup
Tutorial For Use With Generic Web Cam
/ how-to-setup-the-coral...
Dual TPU Install Script for RPi5
gist.github.com/dataslayermed...
frigate.video/
Join us as we dive into one of the most exciting DIY tech projects of 2024, leveraging the newly compatible Raspberry Pi 5 with Google's Coral AI Dual Edge TPU. This advanced setup introduces a cutting-edge approach to home surveillance, surpassing traditional systems like the Amazon Ring by eliminating subscription fees and enhancing privacy.
Key Features and Setup
Enhanced Compatibility: Utilize the power of the Raspberry Pi 5 combined with Google's Coral AI Dual Edge TPU to create a formidable DIY security camera system.
Advanced Hardware: Explore the capabilities of Coral AI hardware, specifically the DUAL PCIE edge accelerator which offers exceptional local AI processing power on a modest budget and energy consumption.
Complex Installation: Detailed walkthrough on setting up the dual TPU on Raspberry Pi 5, including hardware requirements like the M.2 slot and PCIE expansion board to accommodate the advanced dual TPU setup.
Software Configuration: Installation of necessary drivers and packages on the Raspberry Pi OS, along with setting up Frigate NVR for efficient video feed processing and model running.
Real-world Testing and Applications
Practical Demonstration: Test the system's effectiveness with a live scenario involving a Chick-fil-A order to monitor and track the delivery person.
Versatile Uses: The technology isn't just for security cameras; possibilities include nanny cams or pet monitors, illustrating the chip's flexibility even in professional setups like Google's enterprise conferencing hardware.
Closing Thoughts
Impact on DIY Tech and Home Automation: This project not only pushes the boundaries of home DIY projects but also opens up numerous possibilities for integrating AI in everyday home automation.
Future Projects and Innovations: Encourages viewers to think about further applications and innovations that can be achieved with Raspberry Pi and Coral AI technology.
Check out this breakthrough in DIY home security and AI technology, and discover how you can implement these advanced systems in your own home without the hassle of high costs or privacy compromises. - Věda a technologie
I used the Lenovo ThinkCentre 720Q. A refurb was less than an RPi. It's got an Intel I5 so way more power, comes with NVME 256, 8 gigs, ready to rock. Install Ubuntu. It's got a proprietary PCIx8 for which you get a riser adapter for $20, from there to the M.2 coral PCIx2 to 1 adapter to the M.2 coral edge TPU. You have to remove the external eSATA adapter from motherboard so card fits. Used a jigsaw to cut a hole for chassis fan for active cooling. Worked right away and never gets above 45 deg, under sustained stress tests. The M.2 to PCI coral adapter has a 12v via for fan leads. The whole setup has a nice enclosed profile only slightly larger than RPi jankery.
Thanks, great project.
I hope you can upload new video explaining about the frigate after installation, maybe u can implement some models so you show how the computer vision works. Thanks man
Your neighbor seems like a super fun guy to be around 🙄
Data Slayer, You're so talented! I had to hit the like button!
I found a real gem I guess. Perfect channel, gratz
Great work ...thanks
will this work on thunderbolt 4 to m.2 pcie?
100% chance it was your neighbor who narc'd on you. Pick the lock on his apartment and fill it with 1000 live crickets..call building security and complain your neighbor is doing something weird with insects.
15:24 - that chicken store name :D
Thx for sharing...
Seems like alot of lag in that processing pipeline. I am getting several hundred frames per second from the dual TPU's baseline. For full object segmentation using several models I see sub 20ms per frame with one TPU.
A raspberry pi 5 and no hardware acceleration , no the best set up .
@@peteradshead2383 @Sven_Dongle also running the Pi over wifi on a TPLink router. Lot's of hmmmmm going on with that.
I would have put MQTT in a container as well. Just simpler to manage when an update comes out.
Aren't coral tpus out of stock?
I bought a dual edge coral tpu and I follow every step carefully, changing config.txt, kernel and headers. But only apex_0 is detected. what is missing?
What all hardware are you using?
@@DataSlayerMedia sorry..I am using wrong pineboard hat. Thanks for your response
next project: ai robodialing my neighbor until he goes insane
not a critique just an fyi - your video has a lot of low frequency audio that is a bit distracting (mostly during typing). most folks don't have a subwoofer that goes down to
So what's the AI part of this project?😊 I thought it was going to recognize the person that let you know?
You Neighbor isn’t happening lol😂him got recorded
why oh why ? , why a dual TPU ? , my frigate set up is 6 cameras using a usb TPU and a ryzen 5900g running proxmox .
With a raspberry PI 5 the CPU and GPU would be the limiting factor before you would need a dual TPU , every camera needs to transcode the stream and remove the audio , frigate works by looking for movement and scaling parts down and passing the frame to the TPU to analyze , so most of the work is done with the CPU / GPU the only time the TPU comes into play is with movement to check is it a cat , dog , bird or superman etc .
Subscribed af
I like the subject but why I never know what are you talking about?
bro bring new video on miner