5.9.3 Hoover compare segmentation

Compare two segmentations with Hoover metrics

Detailed description

This application compares a machine segmentation (MS) with a partial ground truth segmentation (GT). The Hoover metrics are used to estimate scores for correct detection, over-segmentation, under-segmentation and missed detection.
The application can output the overall Hoover scores along with coloredimages of the MS and GT segmentation showing the state of each region (correct detection, over-segmentation, under-segmentation, missed)
The Hoover metrics are described in : Hoover et al., ”An experimental comparison of range image segmentation algorithms”, IEEE PAMI vol. 18, no. 7, July 1996.

Parameters

This section describes in details the parameters available for this application. Table 5.65, page 681 presents a summary of these parameters and the parameters keys to be used in command-line and programming languages. Application key is HooverCompareSegmentation.




Parameter key

Parameter type

Parameter description




ingt

Input image

Input ground truth

inms

Input image

Input machine segmentation

bg

Int

Background label

th

Float

Overlapping threshold

outgt

Output image

Colored ground truth output

outms

Output image

Colored machine segmentation output

rc

Float

Correct detection score

rf

Float

Over-segmentation score

ra

Float

Under-segmentation score

rm

Float

Missed detection score

inxml

XML input parameters file

Load otb application from xml file

outxml

XML output parameters file

Save otb application to xml file








Figure 5.65: Parameters table for Hoover compare segmentation.

Example

To run this example in command-line, use the following:

otbcli_HooverCompareSegmentation -ingt maur_GT.tif -inms maur_labelled.tif -outgt maur_colored_GT.tif uint8

To run this example from Python, use the following code snippet:

#!/usr/bin/python 
 
# Import the otb applications package 
import otbApplication 
 
# The following line creates an instance of the HooverCompareSegmentation application 
HooverCompareSegmentation = otbApplication.Registry.CreateApplication("HooverCompareSegmentation") 
 
# The following lines set all the application parameters: 
HooverCompareSegmentation.SetParameterString("ingt", "maur_GT.tif") 
 
HooverCompareSegmentation.SetParameterString("inms", "maur_labelled.tif") 
 
HooverCompareSegmentation.SetParameterString("outgt", "maur_colored_GT.tif") 
HooverCompareSegmentation.SetParameterOutputImagePixelType("outgt", 1) 
 
# The following line execute the application 
HooverCompareSegmentation.ExecuteAndWriteOutput()

Limitations

None

Authors

This application has been written by OTB-Team.

See also

These additional ressources can be useful for further information: