I’m trying to use the LargeScaleMeanShift tool as this first step to carry out some benthic habitat mapping using WorldView 2 data.
This has worked successfully for me with previous analysis so I’m not sure what is happening now.
For some reason I’m getting a large polygon forming over the area of water so sub-surface features aren’t detected.
This is the image that I’m trying to classifiy
This is the result of the segmentation. You see the large polygon over the water area.
The data is fine. This is the result using a segmentation algorithm from GRASS.
I’m not sure why it’s not producing similar results with OTB.
As well as the LargeScaleMeanShift algorithm I’ve also tried with the LSMS workflow using MeanShiftSmoothing then LSMSSegmentation Then LSMSVectorization. This has given me the same results.
Here is a close up from Spatial Filtered Displacement.tif created using MeanShiftSmoothing. I should be able to detect the dredged channels that are clearly present here.