I'm using a Raspberry Pi 5 and I'm trying to connect it with an OAK camera. I noticed online that every project that combines a Raspberry Pi and OAK camera it seems to be a Raspberry Pi 4. I have also noticed that there haven't been any projects involving the two online in the past 6 months. Is the Raspberry Pi 5 itself the problem? Or is the most recent Raspberry Pi OS not compatible with the depthai documentation?
Current Raspberry Pi OS and OAK cameras
Hi @izaac08
The OAKs should work just fine with RPI5. We have images available at: https://docs.luxonis.com/projects/hardware/en/latest/pages/guides/raspberrypi/#using-pre-configured-rpi-os-image
Thanks,
Jaka
6 days later
I've been using a Pi 5 with my FFC-3P for months now without issue, it's running Bookworm too. No issues at all.
- Edited
izaac08
My Pi5/PiOS Bookworm/GoPiGo3 Robot "GoPi5Go-Dave":
Oak-D-W-97 and Oak-D-Lite with PiOS Bookworm 64-bit desktop on Raspberry Pi 5 4gb with cooler on my GoPiGo3 robot:
Spatial Tiny YOLO v4 Performance on PiOS Bookworm 64-bit Desktop with Raspberry Pi 5 4GB (with Pi5 Cooler):
spatial_tiny_yolo.py: 25-30FPS uptime 5m load: 0.5 Temp 49degC Clock Freq 1.6GHz No Throttling (416x416 pixel tiny yolo v4 object recognition with depth active - console output only)
spatial_tiny_yolo.py -d: 25FPS uptime 5m load: 2.0 Temp 58degC Clock Freq 2.4GHz No Throttling (416x416 pixel tiny yolo v4 display with 1280x800 depth display and console out)
gui_spatial_tiny_yolo.py: 25FPS uptime 5m load: 1.3 Temp 56degC Clock Freq 2.4GHz No Throttling (416x416 pixel tiny yolo v4 display and console out - depth active but no separate depth display)
depthai-demo (the Raspberry Pi version)
This is my setup process on Pi5:
Setup GoPi5Go Oak-D-W-97
Created Systests/Oak-D-W-97/intro
Ref: https://learnopencv.com/introduction-to-opencv-ai-kit-and-depthai
Ref: https://docs.luxonis.com/projects/api/en/latest/install/
cd GoPi5Go/systests mkdir Oak-D-W-97 sudo curl -fL https://docs.luxonis.com/install_dependencies.sh | bash 1) Setup_USB_Rules.sh#/bin/bash
echo 'SUBSYSTEM=="usb", ATTRS{idVendor}=="03e7", MODE="0666"' | sudo tee /etc/udev/rules.d/80-movidius.rules
sudo udevadm control --reload-rules && sudo udevadm trigger
echo -e "RULES LOADED - NOW DISCONNECT AND RECONNECT THE USB CABLE TO THE OAK-D-LITE"
2) Setup Python3 venvpython3 -m venv --system-site-packages vdepthai
3) Install Dependenciescd ~/pi5desk/systests/vdepthai/
git clone luxonis/depthai.git
source bin/activate
pip3 install opencv-python opencv-contrib-python
cd depthai
python3 install_requirements.py
4) copied helloworld, spatial_yolo ... from wali_pi5
(https://github.com/slowrunner/GoPi5Go/tree/main/systests/Oak-D-W-97)
5) Get depthai-python repository (to get Tiny-YOLOv4 blob)cd vdepthai
source bin/activate
git clone luxonis/depthai-python.git
cd depthai-python/examples
python3 install_requirements.py
mkdir -p ~/GoPi5Go/models/depthai
cp /home/pi/GoPi5Go/systests/Oak-D-W-97/vdepthai/depthai-python/examples/models/yolo-v4-tiny-tf_openvino_2021.4_6shave.blob ~/GoPi5Go/models/depthai