R

ryan

Thank you Brandon for following up so quickly and so thoroughly.

I did see the 4-points transform, which is why I kinda 'deep down in the cockles of my heart' knew that the functionality must be there somewhere and that there is a hole in my knowledge

I also did see setWarpTransformMatrix3x3 in the API and my thought was that it would/might/should do what I needed, based on my limited understanding of the algorithms doing the actual work behind the OpenCV fisheye functions that I currently use, but as I was at the limits of my knowledge I wanted to check before I invested serious learning time into an approach that might actually be a dead-end.

This is critically important to me, and so armed with the knowledge that there is a path there for me to pursue, I will follow it as best I can.

If you are able to get the output to 4K, this would be fantastic (I am already doing 1080 with the RPi4 and it really needs to be higher. I was on the verge of trying to solve this by trying to get 2K by stitching two frames or such)

To be honest, this will be challenging for me. I will appreciate anything that reduces the slope of my curve.

I will start on this today, though will disappear down a hole for a few days (hopefully!) while I work to get my head around it properly. I will re-emerge with either results, questions, or both I expect. When I do, would your Discord server be the more appropriate forum for this communication?

Thank you again. I very much appreaciate how good your support is. I am sure you guys must be very busy.
Ryan

Hello,

One critical requirement of my use case is the ability to create video of a large area (a football pitch) for coaches and players to later look at.

I can currently do this with RPi4, but not well! Encoding is limited to 1080, the CPU struggles badly to dewarp the fisheye, and so processing times are terrible.

I have purchased the BW1098FFC Body Kit and adapter, and am using an RPi4 and HQ camera with a 180 degree M12 fisheye lens from Arducam.

The 4K video encoding is awesome, and I can see that one of the key features of DepthAI is Warp/Dewarp.

Looking at the Python API, I was hoping to see something familiar and akin to the fisheye functions that I currently use with OpenCV, but I don’t see any.

It would seem to me that either I have a hole in my knowledge that I need to fill (very likely; I do not have expertise in this space), or DepthAI does not have this capability.

This is a critical element to the success of my project with this hardware, so I am hoping that DepthAI does support this capability, and I just need to be pointed in the right direction and get in some learning…

Thanks in advance,
Ryan

(P.S. I have also read through docs, forum, git examples code and discord and not found this information - so apologies upfront if this is already covered somewhere)

Jason. Apologies. I was mistaken. I take detailed notes, and should have checked them before responding. (I must have been thinking of something else that resulted in "Illegal instruction".)

My error message was:

(lux_only) pi@oak1b:~/depthai-python/examples $ python3 01_rgb_preview.py 
Traceback (most recent call last):
  File "01_rgb_preview.py", line 23, in <module>
    with dai.Device(pipeline) as device:
RuntimeError: Failed to find device (ma2480), error message: X_LINK_DEVICE_NOT_FOUND

Most likely due to trying to run Gen2 examples with Gen1 depthai, I would think.

My venv/bin is :

(lux_only) pi@oak1b:~/.virtualenvs/lux_only/bin $ ls -al | grep python
lrwxrwxrwx 1 pi pi   16 Apr  1 11:34 python -> /usr/bin/python3
lrwxrwxrwx 1 pi pi    6 Apr  1 11:34 python3 -> python
lrwxrwxrwx 1 pi pi    6 Apr  1 11:34 python3.7 -> python

And in the hope that it might be helpful, I will include my entire install notes below:

Downloaded 32 bit via Raspberry Pi Imager
Set time/loc/passwd/connected to WLAN/ran upddates / rebooted
Renamed host to 'oak1b'

>Preferences>Raspberry Pi Configuration
    Renamed to 'oak1b'
    Enabled camera, VNC, SSH
    Increased GPU to 128
    rebooted / checked settings

set static wifi ip / disabled IPv6 / rebooted

connected to vnc 
sudo rpi-eeprom-update checked
right click on Task Bar and Add/Remove Panel items.
    added CPU temp
    added CPU usage

sudo apt update
sudo apt full-upgrade
sudo apt install python3 python3-pip

sudo apt install build-essential cmake pkg-config
sudo apt install libatlas-base-dev gfortran
sudo apt install libhdf5-serial-dev hdf5-tools
mkdir python-envs && cd python-envs

pip3 install virtualenvwrapper

sudo nano ~/.bashrc

export WORKON_HOME=$HOME/.virtualenvs
export PROJECT_HOME=./python-envs
export VIRTUALENVWRAPPER_PYTHON=/usr/bin/python3
export VIRTUALENVWRAPPER_VIRTUALENV=~/.local/bin/virtualenv
source ~/.local/bin/virtualenvwrapper.sh
export VIRTUALENVWRAPPER_ENV_BIN_DIR=bin

exit

mkvirtualenv lux_only

[my notes are not clear at this point - but essentially - within the lux_only env, I followed the basic steps of dependencies.sh, install_reqs and then I wasn't sure which depth-ai to install, and ended up trying to install Gen1, and I think the snapshot (though maybe I am mistaken and am remembering a previous occasion...); 
but the end result was that I ended up running: pip uninstall depthai]

//then my notes start again...

python3 install_requirements.py
...Installing collected packages: depthai
Successfully installed depthai-2.1.0.0

After that I was successfully able to execute the scripts in the examples folder.

I hope this is helpful, and apologies for my initial incorrect response.

Hi Jason,

This might help... but I too had a problem when I tried to explicitly install the snapshot version (my install also reported 'Successfully installed depthai-2.1.0.0') and so I just went back to the default install instructions and the issue automagically went away...

(pip uninstall depthai)
sudo curl -fL http://docs.luxonis.com/_static/install_dependencies.sh | bash
python3 install_requirements.py
git clone https://github.com/luxonis/depthai-python.git

I have since been able to successfully run the example scripts.

I am running RPi4 using VNC (and also sometimes directly via bluetooth keyboard and HDMI). I too am using virtual environments.

FWIW - interestingly - VNC so far works perfectly... but I have experienced 'weird issues' when trying to do the same work using my bluetooth keyboard and HDMI.

Hope this is helpful.
Cheers

Hey Brandon,

Thank you for your prompt and very helpful reply.

I appreciate the heads-up regarding the newer version that is on the way. I will definitely be getting one (probably more ) of those.

However, as best I can tell, your current solution will fit my needs, and so I am happy with that, and will proceed with purchase.

Thank you also for telling me about the Arducam M12 IMX477 - I didn't know about these.

If someone told me in 2017 that by 2021, I could retail purchase hardware that could run object detection at 30pfs on a low power (fanless!) system with 3 high quality cameras at a total size not much bigger than a deck of cards (say with a Pi Zero), I would have wondered what they had been smoking!

Thanks again and best wishes for your ongoing success,
Ryan