Dear OpenCV users,
I'm playing around with image stitching pipeline and panorama creation using OpenCV3.2. I'm using Kinect RGB camera as image source, additionaly I retrieve depth values from Kinect's sensor. My code is very similar to the example code that can be found in OpenCV documentation. I convert RGB images captured from Kinect to matrix with BGR format and I'm able to create the panorama from a set of BGR images easily.
Howewer, my goal is to create panoramas from four-channels image (BGR and one extra channel, which I want to use for storing depth values for each pixel) - panorama should be created using BGR values and in fourth channel I'd like to store depth values that would come from source images. Unfortunately, OpenCV does not allow me to use four-channel images. Is there any way to bypass this limitation? If not, I would be glad to know how to determine, for each panorama pixel which pixel from which image was used during panorama creation>
Thank you!