Detailled semantic labeling (2D) result


Name K. Nogueira et al.
Affiliation Universidade Federal de Minas Gerais, Brazil
Abbreviation UFMG_5
Strategy (u)nsupervised, (s)upervised, (h)ybrid s


Overall statistics, reference set: full_reference


Number of non processed tiles by this participant: 0
↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.914
0.030
0.039
0.012
0.004
0.000
building
0.048
0.922
0.022
0.007
0.000
0.000
low_veg
0.070
0.022
0.777
0.131
0.000
0.000
tree
0.027
0.007
0.101
0.865
0.000
0.000
car
0.266
0.043
0.009
0.004
0.678
0.000
clutter
0.723
0.200
0.037
0.010
0.031
0.000
Precision/Correctness
0.853
0.934
0.808
0.853
0.850
-nan
Recall/Completeness
0.914
0.922
0.777
0.865
0.678
0.000
F1
0.883
0.928
0.792
0.859
0.754
-nan

Overall accuracy 0.864

Overall statistics, reference set: no_boundary


Number of non processed tiles by this participant: 0
↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.937
0.023
0.032
0.006
0.002
0.000
building
0.040
0.940
0.014
0.005
0.000
0.000
low_veg
0.056
0.014
0.813
0.117
0.000
0.000
tree
0.013
0.003
0.085
0.898
0.000
0.000
car
0.170
0.050
0.005
0.002
0.773
0.000
clutter
0.721
0.207
0.036
0.004
0.032
0.000
Precision/Correctness
0.885
0.953
0.842
0.880
0.885
-nan
Recall/Completeness
0.937
0.940
0.813
0.898
0.773
0.000
F1
0.910
0.946
0.827
0.889
0.825
-nan

Overall accuracy 0.893
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9589
0.0087
0.0204
0.0078
0.0042
0.0000
building
0.0354
0.9323
0.0303
0.0020
0.0000
0.0000
low_veg
0.0927
0.0159
0.7364
0.1549
0.0002
0.0000
tree
0.0390
0.0051
0.1096
0.8461
0.0001
0.0000
car
0.3113
0.0033
0.0010
0.0009
0.6836
0.0000
clutter
0.8770
0.0118
0.0777
0.0335
0.0000
0.0000
Precision/Correctness
0.796
0.966
0.816
0.836
0.903
-nan
Recall/Completeness
0.959
0.932
0.736
0.846
0.684
0.000
F1
0.870
0.949
0.774
0.841
0.778
-nan

Overall accuracy 0.849

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9769
0.0053
0.0132
0.0017
0.0030
0.0000
building
0.0267
0.9545
0.0185
0.0003
0.0000
0.0000
low_veg
0.0730
0.0094
0.7666
0.1508
0.0002
0.0000
tree
0.0207
0.0032
0.0944
0.8817
0.0000
0.0000
car
0.1806
0.0025
0.0000
0.0002
0.8167
0.0000
clutter
0.8948
0.0111
0.0802
0.0139
0.0000
0.0000
Precision/Correctness
0.832
0.980
0.849
0.856
0.925
-nan
Recall/Completeness
0.977
0.955
0.767
0.882
0.817
0.000
F1
0.898
0.967
0.806
0.869
0.867
-nan

Overall accuracy 0.877

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


=============================================================

Tile top_mosaic_09cm_area4_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9122
0.0719
0.0099
0.0025
0.0035
0.0000
building
0.0499
0.9423
0.0062
0.0015
0.0001
0.0000
low_veg
0.1921
0.0552
0.5264
0.2257
0.0007
0.0000
tree
0.0608
0.0207
0.0957
0.8225
0.0002
0.0000
car
0.3629
0.0253
0.0022
0.0006
0.6089
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.856
0.955
0.681
0.772
0.889
--
Recall/Completeness
0.912
0.942
0.526
0.823
0.609
--
F1
0.883
0.949
0.594
0.797
0.723
--

Overall accuracy 0.903

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


=============================================================

Tile top_mosaic_09cm_area4_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9353
0.0544
0.0077
0.0006
0.0021
0.0000
building
0.0359
0.9582
0.0050
0.0009
0.0000
0.0000
low_veg
0.1495
0.0268
0.5727
0.2506
0.0004
0.0000
tree
0.0283
0.0086
0.0907
0.8724
0.0000
0.0000
car
0.2620
0.0231
0.0013
0.0000
0.7137
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.895
0.970
0.710
0.792
0.926
--
Recall/Completeness
0.935
0.958
0.573
0.872
0.714
--
F1
0.915
0.964
0.634
0.830
0.806
--

Overall accuracy 0.929

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


=============================================================

Tile top_mosaic_09cm_area6_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9056
0.0571
0.0290
0.0044
0.0039
0.0000
building
0.0362
0.9380
0.0237
0.0019
0.0002
0.0000
low_veg
0.0968
0.0475
0.6942
0.1610
0.0005
0.0000
tree
0.0210
0.0063
0.0641
0.9085
0.0001
0.0000
car
0.3369
0.0229
0.0021
0.0008
0.6373
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.872
0.934
0.687
0.932
0.901
--
Recall/Completeness
0.906
0.938
0.694
0.909
0.637
--
F1
0.888
0.936
0.691
0.920
0.747
--

Overall accuracy 0.890

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


=============================================================

Tile top_mosaic_09cm_area6_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9329
0.0431
0.0213
0.0009
0.0018
0.0000
building
0.0269
0.9533
0.0192
0.0006
0.0000
0.0000
low_veg
0.0774
0.0346
0.7422
0.1458
0.0000
0.0000
tree
0.0077
0.0021
0.0514
0.9388
0.0000
0.0000
car
0.2396
0.0194
0.0016
0.0000
0.7393
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.914
0.956
0.726
0.950
0.951
--
Recall/Completeness
0.933
0.953
0.742
0.939
0.739
--
F1
0.923
0.955
0.734
0.944
0.832
--

Overall accuracy 0.921

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


=============================================================

Tile top_mosaic_09cm_area8_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8992
0.0280
0.0657
0.0043
0.0027
0.0000
building
0.0234
0.9585
0.0161
0.0018
0.0001
0.0000
low_veg
0.0620
0.0177
0.8738
0.0462
0.0004
0.0000
tree
0.0319
0.0088
0.0991
0.8602
0.0000
0.0000
car
0.3002
0.0103
0.0173
0.0035
0.6687
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.903
0.938
0.780
0.950
0.921
--
Recall/Completeness
0.899
0.959
0.874
0.860
0.669
--
F1
0.901
0.948
0.825
0.903
0.775
--

Overall accuracy 0.895

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


=============================================================

Tile top_mosaic_09cm_area8_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9206
0.0209
0.0565
0.0008
0.0012
0.0000
building
0.0141
0.9778
0.0075
0.0005
0.0001
0.0000
low_veg
0.0429
0.0101
0.9106
0.0364
0.0000
0.0000
tree
0.0134
0.0042
0.0777
0.9047
0.0000
0.0000
car
0.1968
0.0101
0.0111
0.0023
0.7798
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.943
0.960
0.822
0.967
0.961
--
Recall/Completeness
0.921
0.978
0.911
0.905
0.780
--
F1
0.932
0.969
0.864
0.935
0.861
--

Overall accuracy 0.927

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


=============================================================

Tile top_mosaic_09cm_area10_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8694
0.0636
0.0477
0.0159
0.0033
0.0000
building
0.0155
0.9504
0.0219
0.0110
0.0012
0.0000
low_veg
0.0872
0.0291
0.7396
0.1439
0.0002
0.0000
tree
0.0178
0.0101
0.0732
0.8989
0.0000
0.0000
car
0.2516
0.0334
0.0061
0.0025
0.7063
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.930
0.878
0.773
0.845
0.762
--
Recall/Completeness
0.869
0.950
0.740
0.899
0.706
--
F1
0.899
0.913
0.756
0.871
0.733
--

Overall accuracy 0.871

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


=============================================================

Tile top_mosaic_09cm_area10_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9002
0.0512
0.0403
0.0062
0.0022
0.0000
building
0.0107
0.9623
0.0178
0.0082
0.0010
0.0000
low_veg
0.0820
0.0164
0.7866
0.1147
0.0002
0.0000
tree
0.0078
0.0046
0.0572
0.9304
0.0000
0.0000
car
0.1592
0.0405
0.0059
0.0007
0.7938
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.948
0.908
0.810
0.887
0.790
--
Recall/Completeness
0.900
0.962
0.787
0.930
0.794
--
F1
0.924
0.934
0.798
0.908
0.792
--

Overall accuracy 0.901

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


=============================================================

Tile top_mosaic_09cm_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8680
0.0375
0.0636
0.0280
0.0030
0.0000
building
0.1722
0.8072
0.0159
0.0039
0.0009
0.0000
low_veg
0.0483
0.0242
0.7532
0.1736
0.0007
0.0000
tree
0.0108
0.0084
0.1197
0.8610
0.0001
0.0000
car
0.1846
0.0000
0.0074
0.0075
0.8005
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.704
0.909
0.795
0.853
0.830
--
Recall/Completeness
0.868
0.807
0.753
0.861
0.801
--
F1
0.777
0.855
0.773
0.857
0.815
--

Overall accuracy 0.820

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


=============================================================

Tile top_mosaic_09cm_area12_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8965
0.0343
0.0532
0.0156
0.0004
0.0000
building
0.1809
0.8108
0.0063
0.0010
0.0009
0.0000
low_veg
0.0460
0.0174
0.7835
0.1524
0.0007
0.0000
tree
0.0055
0.0039
0.1030
0.8875
0.0000
0.0000
car
0.0883
0.0000
0.0047
0.0058
0.9012
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.717
0.933
0.825
0.878
0.878
--
Recall/Completeness
0.896
0.811
0.783
0.888
0.901
--
F1
0.797
0.868
0.804
0.883
0.889
--

Overall accuracy 0.844

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


=============================================================

Tile top_mosaic_09cm_area14_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8619
0.0356
0.0696
0.0281
0.0049
0.0000
building
0.0175
0.9612
0.0174
0.0037
0.0001
0.0000
low_veg
0.0980
0.0553
0.7003
0.1458
0.0006
0.0000
tree
0.0346
0.0132
0.1205
0.8317
0.0000
0.0000
car
0.1310
0.0000
0.0000
0.0046
0.8644
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.832
0.864
0.750
0.863
0.635
--
Recall/Completeness
0.862
0.961
0.700
0.832
0.864
--
F1
0.847
0.910
0.724
0.847
0.732
--

Overall accuracy 0.828

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


=============================================================

Tile top_mosaic_09cm_area14_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8801
0.0314
0.0654
0.0189
0.0042
0.0000
building
0.0121
0.9780
0.0088
0.0010
0.0001
0.0000
low_veg
0.0927
0.0405
0.7318
0.1344
0.0006
0.0000
tree
0.0258
0.0062
0.1089
0.8591
0.0000
0.0000
car
0.0370
0.0000
0.0000
0.0007
0.9623
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.858
0.897
0.772
0.884
0.625
--
Recall/Completeness
0.880
0.978
0.732
0.859
0.962
--
F1
0.869
0.936
0.752
0.872
0.758
--

Overall accuracy 0.853

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


=============================================================

Tile top_mosaic_09cm_area16_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8050
0.0314
0.1170
0.0439
0.0026
0.0000
building
0.0365
0.9235
0.0296
0.0103
0.0001
0.0000
low_veg
0.0217
0.0119
0.8493
0.1171
0.0000
0.0000
tree
0.0214
0.0059
0.1406
0.8321
0.0000
0.0000
car
0.1777
0.0000
0.0145
0.0083
0.7994
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.855
0.940
0.771
0.876
0.808
--
Recall/Completeness
0.805
0.924
0.849
0.832
0.799
--
F1
0.829
0.932
0.808
0.853
0.804
--

Overall accuracy 0.849

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


=============================================================

Tile top_mosaic_09cm_area16_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8366
0.0278
0.1084
0.0263
0.0009
0.0000
building
0.0328
0.9469
0.0163
0.0039
0.0001
0.0000
low_veg
0.0173
0.0068
0.8731
0.1028
0.0000
0.0000
tree
0.0139
0.0026
0.1260
0.8576
0.0000
0.0000
car
0.1073
0.0000
0.0090
0.0030
0.8807
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.886
0.959
0.798
0.900
0.900
--
Recall/Completeness
0.837
0.947
0.873
0.858
0.881
--
F1
0.860
0.953
0.834
0.878
0.890
--

Overall accuracy 0.875

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


=============================================================

Tile top_mosaic_09cm_area20_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8646
0.0197
0.0796
0.0318
0.0043
0.0000
building
0.0140
0.9415
0.0390
0.0055
0.0000
0.0000
low_veg
0.0705
0.0177
0.7719
0.1396
0.0002
0.0000
tree
0.0098
0.0013
0.0610
0.9279
0.0000
0.0000
car
0.1817
0.0089
0.0314
0.0164
0.7616
0.0000
clutter
0.9029
0.0362
0.0605
0.0004
0.0000
0.0000
Precision/Correctness
0.794
0.945
0.752
0.917
0.775
-nan
Recall/Completeness
0.865
0.941
0.772
0.928
0.762
0.000
F1
0.828
0.943
0.762
0.923
0.768
-nan

Overall accuracy 0.861

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


=============================================================

Tile top_mosaic_09cm_area20_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8932
0.0142
0.0725
0.0172
0.0028
0.0000
building
0.0109
0.9553
0.0320
0.0018
0.0000
0.0000
low_veg
0.0637
0.0083
0.8163
0.1115
0.0002
0.0000
tree
0.0042
0.0002
0.0476
0.9480
0.0000
0.0000
car
0.1144
0.0087
0.0246
0.0091
0.8432
0.0000
clutter
0.9164
0.0329
0.0506
0.0000
0.0000
0.0000
Precision/Correctness
0.812
0.967
0.785
0.942
0.804
-nan
Recall/Completeness
0.893
0.955
0.816
0.948
0.843
0.000
F1
0.851
0.961
0.800
0.945
0.823
-nan

Overall accuracy 0.887

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


=============================================================

Tile top_mosaic_09cm_area22_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9061
0.0247
0.0411
0.0228
0.0053
0.0000
building
0.0333
0.9465
0.0157
0.0043
0.0004
0.0000
low_veg
0.1266
0.0326
0.7088
0.1319
0.0001
0.0000
tree
0.0268
0.0040
0.0693
0.8997
0.0002
0.0000
car
0.3094
0.0043
0.0108
0.0101
0.6654
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.872
0.915
0.799
0.882
0.800
--
Recall/Completeness
0.906
0.946
0.709
0.900
0.665
--
F1
0.889
0.930
0.751
0.891
0.727
--

Overall accuracy 0.869

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


=============================================================

Tile top_mosaic_09cm_area22_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9340
0.0189
0.0339
0.0098
0.0033
0.0000
building
0.0260
0.9644
0.0080
0.0014
0.0002
0.0000
low_veg
0.1232
0.0212
0.7501
0.1055
0.0000
0.0000
tree
0.0117
0.0012
0.0525
0.9346
0.0000
0.0000
car
0.2277
0.0065
0.0081
0.0027
0.7550
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.899
0.943
0.841
0.918
0.844
--
Recall/Completeness
0.934
0.964
0.750
0.935
0.755
--
F1
0.916
0.953
0.793
0.926
0.797
--

Overall accuracy 0.902

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


=============================================================

Tile top_mosaic_09cm_area24_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8382
0.0349
0.0894
0.0317
0.0058
0.0000
building
0.0664
0.8776
0.0368
0.0192
0.0000
0.0000
low_veg
0.0355
0.0189
0.8723
0.0729
0.0003
0.0000
tree
0.0209
0.0083
0.1530
0.8178
0.0001
0.0000
car
0.1678
0.0001
0.0053
0.0013
0.8256
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.787
0.917
0.859
0.845
0.757
--
Recall/Completeness
0.838
0.878
0.872
0.818
0.826
--
F1
0.812
0.897
0.866
0.831
0.790
--

Overall accuracy 0.854

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


=============================================================

Tile top_mosaic_09cm_area24_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8662
0.0264
0.0811
0.0222
0.0041
0.0000
building
0.0631
0.8908
0.0295
0.0166
0.0000
0.0000
low_veg
0.0317
0.0145
0.8920
0.0614
0.0003
0.0000
tree
0.0137
0.0047
0.1328
0.8488
0.0000
0.0000
car
0.0666
0.0001
0.0019
0.0000
0.9314
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.811
0.939
0.881
0.869
0.774
--
Recall/Completeness
0.866
0.891
0.892
0.849
0.931
--
F1
0.838
0.914
0.886
0.859
0.845
--

Overall accuracy 0.877

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


=============================================================

Tile top_mosaic_09cm_area27_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9432
0.0270
0.0192
0.0048
0.0058
0.0000
building
0.0602
0.9191
0.0162
0.0042
0.0003
0.0000
low_veg
0.1023
0.0286
0.6736
0.1953
0.0003
0.0000
tree
0.0199
0.0076
0.0461
0.9263
0.0001
0.0000
car
0.2838
0.0053
0.0088
0.0043
0.6977
0.0000
clutter
0.7110
0.1015
0.1214
0.0162
0.0498
0.0000
Precision/Correctness
0.848
0.954
0.886
0.692
0.914
-nan
Recall/Completeness
0.943
0.919
0.674
0.926
0.698
0.000
F1
0.893
0.936
0.765
0.792
0.791
-nan

Overall accuracy 0.870

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


=============================================================

Tile top_mosaic_09cm_area27_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9654
0.0179
0.0140
0.0014
0.0012
0.0000
building
0.0486
0.9385
0.0106
0.0022
0.0001
0.0000
low_veg
0.0807
0.0163
0.7170
0.1858
0.0001
0.0000
tree
0.0101
0.0031
0.0312
0.9556
0.0000
0.0000
car
0.1836
0.0049
0.0073
0.0029
0.8012
0.0000
clutter
0.7225
0.0829
0.1254
0.0117
0.0575
0.0000
Precision/Correctness
0.885
0.973
0.920
0.719
0.971
-nan
Recall/Completeness
0.965
0.939
0.717
0.956
0.801
0.000
F1
0.923
0.956
0.806
0.820
0.878
-nan

Overall accuracy 0.901

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


=============================================================

Tile top_mosaic_09cm_area29_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9427
0.0161
0.0251
0.0111
0.0050
0.0000
building
0.0396
0.9421
0.0126
0.0052
0.0005
0.0000
low_veg
0.0771
0.0258
0.6211
0.2757
0.0004
0.0000
tree
0.0064
0.0058
0.0315
0.9563
0.0000
0.0000
car
0.2597
0.0032
0.0014
0.0093
0.7263
0.0000
clutter
0.6256
0.2794
0.0181
0.0097
0.0672
0.0000
Precision/Correctness
0.899
0.929
0.836
0.689
0.694
-nan
Recall/Completeness
0.943
0.942
0.621
0.956
0.726
0.000
F1
0.920
0.935
0.713
0.801
0.710
-nan

Overall accuracy 0.865

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


=============================================================

Tile top_mosaic_09cm_area29_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9632
0.0098
0.0185
0.0048
0.0037
0.0000
building
0.0347
0.9554
0.0072
0.0023
0.0004
0.0000
low_veg
0.0532
0.0130
0.6675
0.2660
0.0003
0.0000
tree
0.0013
0.0034
0.0249
0.9705
0.0000
0.0000
car
0.1750
0.0002
0.0014
0.0059
0.8175
0.0000
clutter
0.6228
0.2867
0.0158
0.0032
0.0716
0.0000
Precision/Correctness
0.921
0.950
0.875
0.724
0.695
-nan
Recall/Completeness
0.963
0.955
0.668
0.970
0.817
0.000
F1
0.942
0.953
0.757
0.830
0.751
-nan

Overall accuracy 0.893

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


=============================================================

Tile top_mosaic_09cm_area31_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9736
0.0084
0.0100
0.0031
0.0049
0.0000
building
0.0800
0.9044
0.0121
0.0019
0.0016
0.0000
low_veg
0.0517
0.0020
0.9129
0.0332
0.0002
0.0000
tree
0.0508
0.0031
0.0782
0.8674
0.0005
0.0000
car
0.1696
0.2040
0.0097
0.0055
0.6113
0.0000
clutter
0.5061
0.4221
0.0429
0.0086
0.0203
0.0000
Precision/Correctness
0.866
0.908
0.884
0.932
0.876
-nan
Recall/Completeness
0.974
0.904
0.913
0.867
0.611
0.000
F1
0.916
0.906
0.898
0.899
0.720
-nan

Overall accuracy 0.887

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


=============================================================

Tile top_mosaic_09cm_area31_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9853
0.0050
0.0073
0.0007
0.0018
0.0000
building
0.0684
0.9238
0.0063
0.0003
0.0012
0.0000
low_veg
0.0294
0.0006
0.9440
0.0260
0.0000
0.0000
tree
0.0199
0.0002
0.0617
0.9181
0.0001
0.0000
car
0.1008
0.2310
0.0042
0.0015
0.6625
0.0000
clutter
0.4484
0.4841
0.0442
0.0022
0.0212
0.0000
Precision/Correctness
0.900
0.920
0.917
0.958
0.918
-nan
Recall/Completeness
0.985
0.924
0.944
0.918
0.663
0.000
F1
0.940
0.922
0.930
0.938
0.770
-nan

Overall accuracy 0.915

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


=============================================================

Tile top_mosaic_09cm_area33_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9841
0.0069
0.0057
0.0015
0.0018
0.0000
building
0.0778
0.8339
0.0239
0.0626
0.0018
0.0000
low_veg
0.0876
0.0082
0.8586
0.0439
0.0016
0.0000
tree
0.0548
0.0090
0.1574
0.7788
0.0000
0.0000
car
0.2983
0.0008
0.0013
0.0026
0.6970
0.0000
clutter
0.7731
0.1763
0.0017
0.0009
0.0480
0.0000
Precision/Correctness
0.813
0.944
0.837
0.762
0.687
-nan
Recall/Completeness
0.984
0.834
0.859
0.779
0.697
0.000
F1
0.890
0.885
0.848
0.770
0.692
-nan

Overall accuracy 0.843

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


=============================================================

Tile top_mosaic_09cm_area33_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9921
0.0037
0.0031
0.0002
0.0009
0.0000
building
0.0715
0.8441
0.0193
0.0635
0.0015
0.0000
low_veg
0.0518
0.0054
0.8985
0.0429
0.0015
0.0000
tree
0.0267
0.0042
0.1482
0.8209
0.0000
0.0000
car
0.1918
0.0002
0.0000
0.0015
0.8065
0.0000
clutter
0.7615
0.1858
0.0005
0.0006
0.0516
0.0000
Precision/Correctness
0.841
0.955
0.860
0.766
0.689
-nan
Recall/Completeness
0.992
0.844
0.898
0.821
0.806
0.000
F1
0.910
0.896
0.879
0.792
0.743
-nan

Overall accuracy 0.864

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


=============================================================

Tile top_mosaic_09cm_area35_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9048
0.0295
0.0548
0.0101
0.0009
0.0000
building
0.0405
0.9313
0.0240
0.0038
0.0004
0.0000
low_veg
0.0742
0.0135
0.6972
0.2151
0.0000
0.0000
tree
0.0488
0.0085
0.1059
0.8367
0.0001
0.0000
car
0.2938
0.0389
0.0047
0.0049
0.6578
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.841
0.950
0.794
0.775
0.933
--
Recall/Completeness
0.905
0.931
0.697
0.837
0.658
--
F1
0.872
0.941
0.742
0.805
0.772
--

Overall accuracy 0.843

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


=============================================================

Tile top_mosaic_09cm_area35_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9341
0.0250
0.0389
0.0018
0.0001
0.0000
building
0.0291
0.9592
0.0108
0.0005
0.0004
0.0000
low_veg
0.0539
0.0072
0.7266
0.2123
0.0000
0.0000
tree
0.0194
0.0033
0.0841
0.8932
0.0000
0.0000
car
0.1896
0.0472
0.0031
0.0013
0.7588
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.895
0.968
0.848
0.795
0.972
--
Recall/Completeness
0.934
0.959
0.727
0.893
0.759
--
F1
0.914
0.964
0.783
0.841
0.852
--

Overall accuracy 0.880

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


=============================================================

Tile top_mosaic_09cm_area38_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9146
0.0314
0.0431
0.0086
0.0024
0.0000
building
0.0316
0.9238
0.0396
0.0045
0.0005
0.0000
low_veg
0.0535
0.0120
0.8513
0.0830
0.0001
0.0000
tree
0.0331
0.0076
0.1212
0.8380
0.0001
0.0000
car
0.2375
0.0357
0.0260
0.0059
0.6949
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.885
0.945
0.840
0.859
0.890
--
Recall/Completeness
0.915
0.924
0.851
0.838
0.695
--
F1
0.900
0.934
0.846
0.849
0.780
--

Overall accuracy 0.882

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


=============================================================

Tile top_mosaic_09cm_area38_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9363
0.0294
0.0311
0.0025
0.0008
0.0000
building
0.0233
0.9493
0.0257
0.0013
0.0004
0.0000
low_veg
0.0354
0.0071
0.8891
0.0683
0.0001
0.0000
tree
0.0144
0.0043
0.1004
0.8808
0.0001
0.0000
car
0.1394
0.0430
0.0153
0.0016
0.8006
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.927
0.958
0.878
0.894
0.941
--
Recall/Completeness
0.936
0.949
0.889
0.881
0.801
--
F1
0.932
0.954
0.883
0.887
0.865
--

Overall accuracy 0.915

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image