I want to do some custom pre-processing on the RGB images before they are used for getting the depth frames from them. This pre-processing includes cropping and some algorithm that is needed for my use case. I also want to do some post-processing on to get the desired result format. Now, can I do this pre and post processing on the internal VPU of the camera? How can I do this?

  • erik replied to this.

    Hi DhruvDarda ,
    You can do preprocessing with ImageManip node, just note that StereoDepth node might expect full-res images, but best to try out. You can also do postprocessing with ImageManip, or check here for custom processing:
    https://docs.luxonis.com/en/latest/pages/tutorials/on-device-programming/
    Such as depth->pointcloud conversion:
    https://docs.luxonis.com/en/latest/pages/tutorials/device-pointcloud/#on-device-pointcloud-nn-model
    Thoughts?