Train Images Classifier and Image Classifier Algorithm

OTB Usage
1

Hello All,
I am new to OTB. I was able to run the algorithm ‘ComputeImagesStatistics’ but generated error when the statistic.xml is uploaded to run in the algorithm ‘TrainImagesClassifier’. The error from the report is (000001D7692A0320): is a wrong tension FileName : Expected .xml. I was able to run the algorithm without the statistics.xml file.

Also, the ImageClassifier failed to output the confidence map and classification map
The full report is copied below for assistance.
QGIS version: 3.6.3-Noosa
QGIS code revision: 0c5774c068
Qt version: 5.11.2
GDAL version: 2.4.1
GEOS version: 3.7.2-CAPI-1.11.0 b55d2125
PROJ version: 520
Processing algorithm…
Algorithm ‘ImageClassifier’ starting…
Input parameters:
{ ‘in’ : ‘C:/Users/ofala/AppData/Local/Temp/semiautomaticclassification/20190611_120354086141/20190611_121339248488Virtual Band Set 1.vrt’, ‘mask’ : None, ‘model’ : ‘C:\QGIS Processsing Sentinel\Sentinel 2\Oluwa Forest Reserve\2016\L1C_T31NFH_A002836_20160107T101236_2016-01-07\Stats\Model.txt’, ‘imstat’ : ‘C:\QGIS Processsing Sentinel\Sentinel 2\Oluwa Forest Reserve\2016\L1C_T31NFH_A002836_20160107T101236_2016-01-07\Stats\Statistics1.xml’, ‘nodatalabel’ : 0, ‘out’ : ‘C:/QGIS Processsing Sentinel/Sentinel 2/Oluwa Forest Reserve/2016/L1C_T31NFH_A002836_20160107T101236_2016-01-07/Stats/Output_Classification_Map.tif’, ‘confmap’ : ‘C:/QGIS Processsing Sentinel/Sentinel 2/Oluwa Forest Reserve/2016/L1C_T31NFH_A002836_20160107T101236_2016-01-07/Stats/Confidence_Map.tif’, ‘outputpixeltype’ : 5 }

2019-06-11 13:52:00 (INFO): Default RAM limit for OTB is 128 MB
2019-06-11 13:52:00 (INFO): GDAL maximum cache size is 405 MB
2019-06-11 13:52:00 (INFO): OTB will use at most 8 threads
2019-06-11 13:52:00 (INFO): No kwl metadata found in file C:/Users/ofala/AppData/Local/Temp/semiautomaticclassification/20190611_120354086141/20190611_121339248488Virtual Band Set 1.vrt
2019-06-11 13:52:00 (INFO): Loading model
Could not read file C:\QGIS
2019-06-11 13:52:00 (INFO): Model loaded
2019-06-11 13:52:00 (INFO): Input image normalization activated.
2019-06-11 13:52:00 (FATAL): itk::ERROR: StatisticsXMLFileReader(000001B7D7F89700): is a wrong Extension FileName : Expected .xml
Execution completed in 0.32 seconds
Results:
{‘confmap’: 'C:/QGIS Processsing Sentinel/Sentinel 2/Oluwa Forest ’
‘Reserve/2016/L1C_T31NFH_A002836_20160107T101236_2016-01-07/Stats/Confidence_Map.tif’,
‘out’: 'C:/QGIS Processsing Sentinel/Sentinel 2/Oluwa Forest ’
‘Reserve/2016/L1C_T31NFH_A002836_20160107T101236_2016-01-07/Stats/Output_Classification_Map.tif’}

Loading resulting layers
The following layers were not correctly generated.

  • C:/QGIS Processsing Sentinel/Sentinel 2/Oluwa Forest Reserve/2016/L1C_T31NFH_A002836_20160107T101236_2016-01-07/Stats/Confidence_Map.tif
  • C:/QGIS Processsing Sentinel/Sentinel 2/Oluwa Forest Reserve/2016/L1C_T31NFH_A002836_20160107T101236_2016-01-07/Stats/Output_Classification_Map.tif
You can check the ‘Log Messages Panel’ in QGIS main window to find more information about the execution of the algorithm.
QGIS version: 3.6.3-Noosa
QGIS code revision: 0c5774c068
Qt version: 5.11.2
GDAL version: 2.4.1
GEOS version: 3.7.2-CAPI-1.11.0 b55d2125
PROJ version: 520
Processing algorithm…
Algorithm ‘ImageClassifier’ starting…
Input parameters:
{ ‘in’ : ‘C:/Users/ofala/AppData/Local/Temp/semiautomaticclassification/20190611_120354086141/20190611_121339248488Virtual Band Set 1.vrt’, ‘mask’ : None, ‘model’ : ‘C:\QGIS Processsing Sentinel\Sentinel 2\Oluwa Forest Reserve\2016\L1C_T31NFH_A002836_20160107T101236_2016-01-07\Stats\Model.txt’, ‘imstat’ : ‘’, ‘nodatalabel’ : 0, ‘out’ : ‘C:/QGIS Processsing Sentinel/Sentinel 2/Oluwa Forest Reserve/2016/L1C_T31NFH_A002836_20160107T101236_2016-01-07/Stats/Output_Classification_Map.tif’, ‘confmap’ : ‘C:/QGIS Processsing Sentinel/Sentinel 2/Oluwa Forest Reserve/2016/L1C_T31NFH_A002836_20160107T101236_2016-01-07/Stats/Confidence_Map.tif’, ‘outputpixeltype’ : 5 }

2019-06-11 13:52:20 (INFO): Default RAM limit for OTB is 128 MB
2019-06-11 13:52:20 (INFO): GDAL maximum cache size is 405 MB
2019-06-11 13:52:20 (INFO): OTB will use at most 8 threads
2019-06-11 13:52:20 (INFO): No kwl metadata found in file C:/Users/ofala/AppData/Local/Temp/semiautomaticclassification/20190611_120354086141/20190611_121339248488Virtual Band Set 1.vrt
2019-06-11 13:52:20 (INFO): Loading model
Could not read file C:\QGIS
2019-06-11 13:52:20 (INFO): Model loaded
2019-06-11 13:52:20 (INFO): Input image normalization deactivated.
2019-06-11 13:52:20 (INFO): Estimated memory for full processing: 91.7788MB (avail.: 128 MB), optimal image partitioning: 1 blocks
2019-06-11 13:52:20 (INFO): File C:/QGIS Processsing Sentinel/Sentinel 2/Oluwa Forest Reserve/2016/L1C_T31NFH_A002836_20160107T101236_2016-01-07/Stats/Output_Classification_Map.tif will be written in 1 blocks of 1976x902 pixels

Execution completed in 11.78 seconds
Results:
{‘confmap’: 'C:/QGIS Processsing Sentinel/Sentinel 2/Oluwa Forest ’
‘Reserve/2016/L1C_T31NFH_A002836_20160107T101236_2016-01-07/Stats/Confidence_Map.tif’,
‘out’: 'C:/QGIS Processsing Sentinel/Sentinel 2/Oluwa Forest ’
‘Reserve/2016/L1C_T31NFH_A002836_20160107T101236_2016-01-07/Stats/Output_Classification_Map.tif’}

Loading resulting layers
The following layers were not correctly generated.

  • C:/QGIS Processsing Sentinel/Sentinel 2/Oluwa Forest Reserve/2016/L1C_T31NFH_A002836_20160107T101236_2016-01-07/Stats/Confidence_Map.tif
  • C:/QGIS Processsing Sentinel/Sentinel 2/Oluwa Forest Reserve/2016/L1C_T31NFH_A002836_20160107T101236_2016-01-07/Stats/Output_Classification_Map.tif
You can check the ‘Log Messages Panel’ in QGIS main window to find more information about the execution of the algorithm.
2

sorry had the same problem posted here but no solution for me. so if please you figure out help me too

3

There seems to be problem with paths containing spaces… , need to investigate this.

4

the problem is with the folder name. if the folder name has spaces, the operation doesn’t work