MatthewGale

MatthewGale · Feb 3, 2023

That is really helpful thank you.

MatthewGale · Feb 2, 2023

Yes, it's quite tricky to get the thresholding correct as I'm getting a lot of false detections due to noise in the depth data. I've got the pro oak d camera, and have set the dot projector output to 200mA, is that just automatically used to improve the depth information or do I need to signify elsewhere in the code to use the dot projector?

Thanks,

Mattie.

MatthewGale · Feb 1, 2023

Hi erik,

I'm looking to see whether change detection is more accurate when using a 3D camera. I'm using change detection to track a moving object.

Thanks,

Mattie.

MatthewGale · Feb 1, 2023

I have seen this really cool example. However, it only considers the RGB data from the camera. I've been trying to work out how to improve this using the depth data as well to mitigate lighting changes but I'm not sure where to start. I've seen this open issue that looks like it would do exactly what I want. I'm struggling to work out the logic required to know when to ignore anomalies in the depth data, and when to use depth data to discount lighting changes etc. Apologies if this is the wrong forum for this question.

MatthewGale · Jan 26, 2023

Hi erik,

Sorry I've realised my mistake. I forgot my code was running on a docker container so had a different version opencv and the depthai libraries. Even though i did install the requirements on my local machine. I have depthai 2.19.1.0 and opencv-contrib-python 4.6.0.66 on my docker container, and opencv-contrib-python 4.5.5.62, opencv-python 4.7.0.68, depthai-sdk 1.9.1.1, depthai 2.16.0.0 on my local machine.

Thanks for the help

MatthewGale · Jan 25, 2023

Hi erik ,

Sure, after cloning the depth-experiments I installed the requirements for the 'gen2-deeplabv3_depth' example, and ran the main.py script. This worked fine, and I was able to see the camera output, and the segmentation output via a seperate popup window that was created after running the script. I then tried to run the 'gen2-calc-spatials-on-host' example, but before doing that I realised the requirements.txt required a different version of the depthai module so I created a virtual environment to install the dependencies into. This made me notice my pip version was outdated so I updated that aswell using 'python3 -m pip install --upgrade pip'. After checking my history, I've noticed that I also ran 'python3 -m pip install --upgrade depthai' for some reason.

Since doing that I can no longer run the 'gen2-deeplabv3_depth' example, and the 'gen2-calc-spatials-on-host' doesn't work either. By not working, I mean that I can hear the camera click when I run the script which implies it can reach the camera, but no popup window with the camera feed is appearing, despite the terminal output being as expected:
'Use WASD keys to move ROI.
Use 'r' and 'f' to change ROI size.'
for 'gen2-calc-spatials-on-host'.

The strange thing is that I haven't modified the example code and my own basic code extracting the RGB and depth data from the camera is running fine.

MatthewGale · Jan 24, 2023

I have been running some of the experiments from https://github.com/luxonis/depthai-experiments including gen2-deeplab_depth and gen2-calc-spatials-on-host and they were running fine. Previously, the camera output was displayed in a new window that was created after running main.py, but this window isn't opening anymore for some reason. There is no error when I run the script, but I'm able to see the window with the camera feed. I've tried restarting my laptop. I'm not sure what's caused this as the only thing I changed since running the script initially was installing the requirements into a virtual environment and upgrading my pip version. I can't remember what version of pip I had before, but now I have 22.3.1.