LSMSVectorization

Brief Description

Fourth step of the exact Large-Scale Mean-Shift segmentation workflow.

Long Description

This application performs the fourth step of the exact Large-Scale Mean-Shift segmentation workflow (LSMS). Given a segmentation result (label image), that may have been processed for small regions merging or not, it will convert it to a GIS vector file containing one polygon per segment. Each polygon contains additional fields: mean and variance of each channels from input image (in parameter), segmentation image label, number of pixels in the polygon. For large images one can use the nbtilesx and nbtilesy parameters for tile-wise processing, with the guarantees of identical results.

Parameters

[param] -in <string> The input image.. Mandatory: True. Default Value: ""
[param] -inseg <string> The segmented image input. Segmented image input is the segmentation of the input image.. Mandatory: True. Default Value: ""
[param] -out <string> The output GIS vector file, representing the vectorized version of the segmented image where the features of the polygons are the radiometric means and variances.. Mandatory: True. Default Value: ""
[param] -tilesizex <int32> Size of tiles along the X-axis.. Mandatory: True. Default Value: "500"
[param] -tilesizey <int32> Size of tiles along the Y-axis.. Mandatory: True. Default Value: "500"
[param] -inxml <string> Load otb application from xml file. Mandatory: False. Default Value: ""
[param] -outxml <string> Save otb application to xml file. Mandatory: False. Default Value: ""

Limitations

This application is part of the Large-Scale Mean-Shift segmentation workflow (LSMS) and may not be suited for any other purpose.

Authors

David Youssefi

Example of use

in: avions.tif
inseg: merged.tif
out: vector.shp
tilesizex: 256
tilesizey: 256