Is it possible to crop before depth estimation?

I would like to process depth maps of a central masked area that a ZED2 camera sees.

There are other lighting fixtures towards one of the edges which I fear might affect the overall depth quality.

I had a look at the documentation but I couldn’t figure out if it’s possible to crop the left and right images before they get used to compute the depth map (to avoid as much as possible light from the fixtures).

I assume I can manually crop and use OpenCV to compute the disparity map from the crop result ?
I would like to avoid reinventing the wheel if possible though.

Is it possble to crop left/right images and compute a depth map of the cropped images using ZED SDK ? (If so, can you please point me to the relevant documentation/example ?)

Thank you so much,
George

It’s not currently possible, but we are adding a similar feature in one of the next releases of the ZED SDK

1 Like

Thank you so much for the swift response.

Will keep an eye on updates.