Performs local Rx score computation on an hyperspectral image.


Performs local Rx score computation on an input hyperspectral image. For each hyperspectral pixel, the Rx score is computed using statistics computed on a dual neighborhood. The dual neighborhood is composed of all pixel that are in between two radiuses around the center pixel. This score can then be used to detect anomalies in the image, this can be done for example by thresholding the result of this application with the BandMath application.


Input Image -in image Mandatory
Input hyperspectral data cube

Output Image -out image [dtype]
Output Rx score image

Internal radius -ir int Default value: 1
Internal radius in pixel

External radius -er int Default value: 5
External radius in pixel

Available RAM (MB) -ram int Default value: 256
Available memory for processing (in MB).


From the command-line:

otbcli_LocalRxDetection -in cupriteSubHsi.tif -out LocalRxScore.tif -ir 1 -er 5

From Python:

import otbApplication

app = otbApplication.Registry.CreateApplication("LocalRxDetection")

app.SetParameterString("in", "cupriteSubHsi.tif")
app.SetParameterString("out", "LocalRxScore.tif")
app.SetParameterInt("ir", 1)
app.SetParameterInt("er", 5)


See also