Hi, we are using Raspberry pi HQ camera (the official one). With auto whitebalance the retrieved image is too blue:

If I play with manual whitebalance then it is too blue or too yellow. The best image I can get from OAK is (it yellowish and also blueish, no perfect white):

I tested the camera whitebalance with same light conditions all the time. I cannot find settings which would produce ideally white white.

Is there a possibility to add such funcionality so we can set white balance individually for each color channel? Such functionality is already for example in Basler cameras (https://docs.baslerweb.com/balance-white). Such settings would enable much better images and then potentially better image recognition results. Or is there another option which I can use that is already implemented to archive better images?

Thanks for help.

I am forwarding the images from camera to H.264 encoder so I need to be able to do some compensations inside OAK device

Hi, @erik
Yes I tried (first photo is with auto whitebalance and second with manual whitebalance - about 6500K, the best result I can get). But I need to set compensation for each color channel individually (RGB). That option can drastically help to improve image quality. I tried that on Basler camera (mentioned above). And simple whitebalance is just not helping. I need to set balance ratio for each channel. Then white is perfect white on image.

    Hi oto313 ,
    Let me ask the firmware team if there is any quick way for us to implement it. I assume you could also do this on your end using a custom CV node (kornia might have a function for that already), but it's not as simple.
    Thanks, Erik

      Thanks for help. I really appreciate it. It would really help us

      Looks doable. Investigating how hard.