Detailled semantic labeling (2D) result


Name K. Takahashi
Affiliation Waseda University, Japan
Abbreviation WAS6
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
0.900
0.042
0.040
0.014
0.005
0.000
building
0.052
0.923
0.022
0.003
0.001
0.000
low_veg
0.054
0.045
0.774
0.126
0.000
0.000
tree
0.025
0.009
0.119
0.847
0.000
0.000
car
0.306
0.037
0.009
0.003
0.644
0.001
clutter
0.377
0.409
0.014
0.004
0.040
0.156
Precision/Correctness
0.867
0.897
0.793
0.858
0.810
0.942
Recall/Completeness
0.900
0.923
0.774
0.847
0.644
0.156
F1
0.883
0.909
0.783
0.852
0.717
0.267

Overall accuracy 0.857

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
0.924
0.034
0.032
0.007
0.003
0.000
building
0.044
0.938
0.016
0.001
0.001
0.000
low_veg
0.042
0.035
0.808
0.114
0.000
0.000
tree
0.012
0.004
0.102
0.883
0.000
0.000
car
0.194
0.041
0.006
0.001
0.757
0.001
clutter
0.342
0.431
0.011
0.001
0.042
0.173
Precision/Correctness
0.901
0.920
0.825
0.883
0.846
0.963
Recall/Completeness
0.924
0.938
0.808
0.883
0.757
0.173
F1
0.912
0.929
0.817
0.883
0.799
0.293

Overall accuracy 0.886
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9400
0.0232
0.0193
0.0114
0.0061
0.0000
building
0.0609
0.9212
0.0155
0.0023
0.0000
0.0001
low_veg
0.0587
0.0332
0.7125
0.1957
0.0000
0.0000
tree
0.0294
0.0081
0.0857
0.8750
0.0002
0.0015
car
0.3164
0.0013
0.0000
0.0007
0.6816
0.0000
clutter
0.0000
0.0000
0.0000
0.0096
0.0000
0.9904
Precision/Correctness
0.853
0.930
0.855
0.808
0.869
0.979
Recall/Completeness
0.940
0.921
0.712
0.875
0.682
0.990
F1
0.894
0.926
0.777
0.840
0.764
0.985

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_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9634
0.0187
0.0104
0.0031
0.0043
0.0000
building
0.0544
0.9377
0.0075
0.0004
0.0000
0.0000
low_veg
0.0411
0.0225
0.7448
0.1915
0.0000
0.0000
tree
0.0130
0.0032
0.0724
0.9106
0.0002
0.0006
car
0.1810
0.0004
0.0000
0.0001
0.8185
0.0000
clutter
0.0000
0.0000
0.0000
0.0016
0.0000
0.9984
Precision/Correctness
0.894
0.954
0.888
0.829
0.898
0.992
Recall/Completeness
0.963
0.938
0.745
0.911
0.819
0.998
F1
0.927
0.946
0.810
0.868
0.856
0.995

Overall accuracy 0.891

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
0.9040
0.0661
0.0213
0.0040
0.0046
0.0000
building
0.0619
0.9267
0.0091
0.0011
0.0011
0.0000
low_veg
0.1150
0.0593
0.5155
0.3093
0.0008
0.0000
tree
0.0490
0.0255
0.0539
0.8716
0.0001
0.0000
car
0.3815
0.0361
0.0043
0.0019
0.5762
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.847
0.956
0.621
0.728
0.805
--
Recall/Completeness
0.904
0.927
0.516
0.872
0.576
--
F1
0.874
0.941
0.564
0.793
0.672
--

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_area4_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9294
0.0475
0.0188
0.0015
0.0028
0.0000
building
0.0471
0.9435
0.0078
0.0004
0.0012
0.0000
low_veg
0.0728
0.0241
0.5584
0.3445
0.0002
0.0001
tree
0.0188
0.0103
0.0469
0.9240
0.0000
0.0000
car
0.2731
0.0325
0.0029
0.0007
0.6908
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.885
0.973
0.647
0.750
0.836
--
Recall/Completeness
0.929
0.943
0.558
0.924
0.691
--
F1
0.907
0.958
0.599
0.828
0.757
--

Overall accuracy 0.920

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
0.9110
0.0407
0.0365
0.0069
0.0048
0.0002
building
0.0475
0.9415
0.0099
0.0011
0.0001
0.0000
low_veg
0.0752
0.0432
0.7568
0.1247
0.0001
0.0000
tree
0.0206
0.0082
0.1090
0.8621
0.0001
0.0000
car
0.4038
0.0337
0.0032
0.0010
0.5582
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.865
0.946
0.647
0.942
0.878
--
Recall/Completeness
0.911
0.942
0.757
0.862
0.558
--
F1
0.887
0.944
0.698
0.900
0.683
--

Overall accuracy 0.885

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
0.9391
0.0281
0.0281
0.0019
0.0027
0.0002
building
0.0345
0.9595
0.0058
0.0002
0.0000
0.0000
low_veg
0.0591
0.0259
0.8014
0.1135
0.0000
0.0000
tree
0.0090
0.0029
0.0944
0.8936
0.0000
0.0000
car
0.2962
0.0298
0.0017
0.0002
0.6722
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.907
0.968
0.678
0.958
0.924
--
Recall/Completeness
0.939
0.960
0.801
0.894
0.672
--
F1
0.923
0.964
0.734
0.925
0.778
--

Overall accuracy 0.916

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
0.8711
0.0405
0.0806
0.0045
0.0032
0.0001
building
0.0401
0.9379
0.0199
0.0017
0.0004
0.0000
low_veg
0.0498
0.0141
0.8895
0.0464
0.0003
0.0000
tree
0.0278
0.0087
0.0922
0.8713
0.0000
0.0001
car
0.3506
0.0138
0.0278
0.0007
0.6047
0.0025
clutter
--
--
--
--
--
--
Precision/Correctness
0.896
0.924
0.770
0.950
0.899
--
Recall/Completeness
0.871
0.938
0.889
0.871
0.605
--
F1
0.884
0.931
0.825
0.909
0.723
--

Overall accuracy 0.886

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
0.8942
0.0347
0.0685
0.0007
0.0018
0.0001
building
0.0296
0.9573
0.0125
0.0003
0.0004
0.0000
low_veg
0.0339
0.0062
0.9224
0.0375
0.0001
0.0000
tree
0.0109
0.0037
0.0687
0.9167
0.0000
0.0000
car
0.2358
0.0121
0.0199
0.0001
0.7299
0.0023
clutter
--
--
--
--
--
--
Precision/Correctness
0.935
0.946
0.813
0.967
0.933
--
Recall/Completeness
0.894
0.957
0.922
0.917
0.730
--
F1
0.914
0.952
0.864
0.941
0.819
--

Overall accuracy 0.918

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
0.8473
0.0836
0.0470
0.0165
0.0053
0.0002
building
0.0442
0.9276
0.0182
0.0078
0.0022
0.0000
low_veg
0.0725
0.0792
0.6811
0.1665
0.0006
0.0000
tree
0.0173
0.0125
0.0917
0.8785
0.0000
0.0000
car
0.2841
0.0610
0.0032
0.0005
0.6496
0.0017
clutter
--
--
--
--
--
--
Precision/Correctness
0.917
0.819
0.746
0.829
0.636
--
Recall/Completeness
0.847
0.928
0.681
0.879
0.650
--
F1
0.881
0.870
0.712
0.853
0.643
--

Overall accuracy 0.842

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
0.8768
0.0716
0.0393
0.0079
0.0042
0.0002
building
0.0381
0.9399
0.0145
0.0057
0.0018
0.0000
low_veg
0.0709
0.0637
0.7197
0.1450
0.0007
0.0000
tree
0.0071
0.0061
0.0698
0.9170
0.0000
0.0000
car
0.1869
0.0677
0.0019
0.0000
0.7429
0.0007
clutter
--
--
--
--
--
--
Precision/Correctness
0.935
0.850
0.789
0.864
0.643
--
Recall/Completeness
0.877
0.940
0.720
0.917
0.743
--
F1
0.905
0.893
0.753
0.890
0.689
--

Overall accuracy 0.873

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
0.8945
0.0451
0.0342
0.0229
0.0032
0.0000
building
0.0230
0.9682
0.0066
0.0023
0.0000
0.0000
low_veg
0.0682
0.0458
0.7639
0.1221
0.0000
0.0000
tree
0.0167
0.0118
0.1453
0.8262
0.0000
0.0000
car
0.2441
0.0174
0.0000
0.0018
0.7367
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.801
0.885
0.787
0.887
0.888
--
Recall/Completeness
0.895
0.968
0.764
0.826
0.737
--
F1
0.845
0.924
0.775
0.855
0.805
--

Overall accuracy 0.845

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
0.9186
0.0417
0.0270
0.0116
0.0012
0.0000
building
0.0202
0.9768
0.0026
0.0004
0.0000
0.0000
low_veg
0.0652
0.0312
0.8008
0.1028
0.0000
0.0000
tree
0.0101
0.0043
0.1285
0.8571
0.0000
0.0000
car
0.1104
0.0175
0.0000
0.0000
0.8721
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.832
0.920
0.813
0.912
0.951
--
Recall/Completeness
0.919
0.977
0.801
0.857
0.872
--
F1
0.873
0.948
0.807
0.884
0.910
--

Overall accuracy 0.873

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
0.7884
0.0617
0.1107
0.0330
0.0062
0.0000
building
0.0213
0.9646
0.0114
0.0026
0.0000
0.0000
low_veg
0.0896
0.0596
0.7012
0.1494
0.0003
0.0000
tree
0.0269
0.0189
0.1434
0.8108
0.0000
0.0000
car
0.1463
0.0000
0.0007
0.0006
0.8524
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.834
0.826
0.703
0.855
0.601
--
Recall/Completeness
0.788
0.965
0.701
0.811
0.852
--
F1
0.811
0.890
0.702
0.832
0.705
--

Overall accuracy 0.805

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
0.8048
0.0585
0.1076
0.0236
0.0055
0.0000
building
0.0161
0.9776
0.0054
0.0009
0.0000
0.0000
low_veg
0.0854
0.0411
0.7321
0.1412
0.0002
0.0000
tree
0.0183
0.0101
0.1319
0.8396
0.0000
0.0000
car
0.0421
0.0000
0.0000
0.0000
0.9579
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.861
0.862
0.720
0.874
0.584
--
Recall/Completeness
0.805
0.978
0.732
0.840
0.958
--
F1
0.832
0.916
0.726
0.857
0.726
--

Overall accuracy 0.829

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
0.8648
0.0380
0.0456
0.0493
0.0023
0.0000
building
0.0593
0.9242
0.0105
0.0059
0.0000
0.0000
low_veg
0.0311
0.0234
0.8649
0.0794
0.0000
0.0012
tree
0.0312
0.0093
0.1774
0.7822
0.0000
0.0000
car
0.2745
0.0041
0.0005
0.0002
0.7207
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.808
0.910
0.776
0.899
0.820
--
Recall/Completeness
0.865
0.924
0.865
0.782
0.721
--
F1
0.835
0.917
0.818
0.837
0.767
--

Overall accuracy 0.845

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
0.8949
0.0326
0.0388
0.0327
0.0010
0.0000
building
0.0555
0.9388
0.0044
0.0013
0.0000
0.0000
low_veg
0.0264
0.0152
0.8880
0.0691
0.0000
0.0013
tree
0.0221
0.0042
0.1637
0.8101
0.0000
0.0000
car
0.1883
0.0007
0.0000
0.0000
0.8110
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.837
0.939
0.798
0.921
0.895
--
Recall/Completeness
0.895
0.939
0.888
0.810
0.811
--
F1
0.865
0.939
0.841
0.862
0.851
--

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_area20_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8375
0.1010
0.0177
0.0399
0.0039
0.0000
building
0.0157
0.9513
0.0295
0.0035
0.0000
0.0000
low_veg
0.0464
0.0434
0.7594
0.1508
0.0000
0.0000
tree
0.0098
0.0046
0.0571
0.9284
0.0000
0.0000
car
0.1646
0.0035
0.0399
0.0055
0.7798
0.0067
clutter
0.0007
0.9989
0.0004
0.0000
0.0000
0.0000
Precision/Correctness
0.912
0.729
0.821
0.910
0.803
0.000
Recall/Completeness
0.838
0.951
0.759
0.928
0.780
0.000
F1
0.873
0.826
0.789
0.919
0.791
-nan

Overall accuracy 0.855

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
0.8662
0.0927
0.0144
0.0246
0.0021
0.0000
building
0.0131
0.9586
0.0276
0.0006
0.0000
0.0000
low_veg
0.0398
0.0299
0.8056
0.1247
0.0000
0.0000
tree
0.0041
0.0020
0.0441
0.9498
0.0000
0.0000
car
0.0592
0.0001
0.0358
0.0008
0.8978
0.0064
clutter
0.0000
0.9999
0.0001
0.0000
0.0000
0.0000
Precision/Correctness
0.938
0.750
0.851
0.934
0.864
0.000
Recall/Completeness
0.866
0.959
0.806
0.950
0.898
0.000
F1
0.901
0.842
0.828
0.942
0.880
-nan

Overall accuracy 0.881

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
0.8915
0.0345
0.0390
0.0292
0.0057
0.0000
building
0.0614
0.9261
0.0077
0.0048
0.0000
0.0000
low_veg
0.0765
0.0542
0.7263
0.1430
0.0000
0.0001
tree
0.0240
0.0064
0.0723
0.8972
0.0001
0.0000
car
0.3308
0.0075
0.0187
0.0072
0.6277
0.0081
clutter
--
--
--
--
--
--
Precision/Correctness
0.885
0.874
0.808
0.869
0.786
--
Recall/Completeness
0.892
0.926
0.726
0.897
0.628
--
F1
0.888
0.899
0.765
0.883
0.698
--

Overall accuracy 0.863

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
0.9220
0.0269
0.0318
0.0151
0.0042
0.0000
building
0.0549
0.9404
0.0022
0.0025
0.0000
0.0000
low_veg
0.0733
0.0375
0.7721
0.1171
0.0000
0.0000
tree
0.0103
0.0020
0.0549
0.9327
0.0000
0.0000
car
0.2115
0.0093
0.0153
0.0025
0.7545
0.0068
clutter
--
--
--
--
--
--
Precision/Correctness
0.912
0.911
0.850
0.905
0.818
--
Recall/Completeness
0.922
0.940
0.772
0.933
0.755
--
F1
0.917
0.925
0.809
0.918
0.785
--

Overall accuracy 0.898

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
0.7925
0.0546
0.1161
0.0305
0.0062
0.0000
building
0.0434
0.8665
0.0849
0.0052
0.0000
0.0000
low_veg
0.0252
0.0270
0.8702
0.0777
0.0000
0.0000
tree
0.0155
0.0108
0.1984
0.7752
0.0000
0.0000
car
0.2626
0.0000
0.0049
0.0005
0.7320
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.831
0.882
0.811
0.840
0.755
--
Recall/Completeness
0.793
0.867
0.870
0.775
0.732
--
F1
0.811
0.874
0.840
0.807
0.743
--

Overall accuracy 0.834

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
0.8238
0.0435
0.1098
0.0187
0.0042
0.0000
building
0.0409
0.8715
0.0842
0.0033
0.0000
0.0000
low_veg
0.0228
0.0199
0.8889
0.0684
0.0000
0.0000
tree
0.0086
0.0050
0.1794
0.8070
0.0000
0.0000
car
0.1644
0.0000
0.0023
0.0000
0.8333
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.855
0.913
0.829
0.863
0.790
--
Recall/Completeness
0.824
0.871
0.889
0.807
0.833
--
F1
0.839
0.892
0.858
0.834
0.811
--

Overall accuracy 0.856

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
0.9267
0.0356
0.0214
0.0068
0.0094
0.0000
building
0.0658
0.9130
0.0186
0.0023
0.0003
0.0000
low_veg
0.0730
0.0281
0.6985
0.2003
0.0001
0.0000
tree
0.0142
0.0080
0.0787
0.8990
0.0001
0.0000
car
0.3036
0.0154
0.0043
0.0036
0.6727
0.0005
clutter
0.4547
0.3571
0.0814
0.0015
0.1053
0.0000
Precision/Correctness
0.856
0.944
0.864
0.681
0.865
0.000
Recall/Completeness
0.927
0.913
0.699
0.899
0.673
0.000
F1
0.890
0.928
0.772
0.775
0.757
-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_area27_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9540
0.0247
0.0148
0.0024
0.0040
0.0000
building
0.0550
0.9309
0.0132
0.0007
0.0002
0.0000
low_veg
0.0552
0.0132
0.7401
0.1916
0.0000
0.0000
tree
0.0058
0.0024
0.0612
0.9306
0.0000
0.0000
car
0.1891
0.0132
0.0026
0.0020
0.7928
0.0003
clutter
0.4439
0.3609
0.0772
0.0000
0.1180
0.0000
Precision/Correctness
0.892
0.967
0.899
0.709
0.925
0.000
Recall/Completeness
0.954
0.931
0.740
0.931
0.793
0.000
F1
0.922
0.949
0.812
0.805
0.854
-nan

Overall accuracy 0.897

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
0.9384
0.0235
0.0216
0.0116
0.0050
0.0000
building
0.0451
0.9383
0.0118
0.0048
0.0000
0.0000
low_veg
0.0596
0.0259
0.6012
0.3133
0.0000
0.0000
tree
0.0078
0.0032
0.0349
0.9541
0.0000
0.0000
car
0.3478
0.0032
0.0048
0.0113
0.6316
0.0013
clutter
0.3567
0.5674
0.0305
0.0037
0.0411
0.0006
Precision/Correctness
0.915
0.892
0.839
0.664
0.717
0.469
Recall/Completeness
0.938
0.938
0.601
0.954
0.632
0.001
F1
0.926
0.914
0.700
0.783
0.672
0.001

Overall accuracy 0.858

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
0.9587
0.0169
0.0155
0.0052
0.0037
0.0000
building
0.0388
0.9522
0.0070
0.0021
0.0000
0.0000
low_veg
0.0371
0.0115
0.6410
0.3103
0.0000
0.0000
tree
0.0022
0.0009
0.0261
0.9708
0.0000
0.0000
car
0.2442
0.0004
0.0023
0.0102
0.7412
0.0019
clutter
0.3264
0.6087
0.0207
0.0011
0.0426
0.0006
Precision/Correctness
0.938
0.913
0.880
0.695
0.732
0.409
Recall/Completeness
0.959
0.952
0.641
0.971
0.741
0.001
F1
0.948
0.932
0.742
0.810
0.737
0.001

Overall accuracy 0.886

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
0.9655
0.0111
0.0129
0.0028
0.0077
0.0000
building
0.1141
0.8781
0.0046
0.0021
0.0011
0.0000
low_veg
0.0492
0.0088
0.9102
0.0314
0.0004
0.0000
tree
0.0578
0.0055
0.0718
0.8645
0.0003
0.0002
car
0.2242
0.1340
0.0050
0.0015
0.6330
0.0023
clutter
0.5060
0.3604
0.0275
0.0076
0.0984
0.0000
Precision/Correctness
0.842
0.913
0.897
0.936
0.773
0.007
Recall/Completeness
0.966
0.878
0.910
0.864
0.633
0.000
F1
0.899
0.895
0.904
0.899
0.696
0.000

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_area31_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9789
0.0068
0.0102
0.0008
0.0033
0.0000
building
0.1042
0.8936
0.0012
0.0002
0.0008
0.0000
low_veg
0.0295
0.0044
0.9404
0.0256
0.0001
0.0000
tree
0.0235
0.0010
0.0552
0.9202
0.0000
0.0000
car
0.1295
0.1564
0.0009
0.0002
0.7117
0.0013
clutter
0.4595
0.3989
0.0277
0.0025
0.1113
0.0000
Precision/Correctness
0.874
0.928
0.926
0.959
0.807
0.021
Recall/Completeness
0.979
0.894
0.940
0.920
0.712
0.000
F1
0.924
0.911
0.933
0.939
0.756
0.000

Overall accuracy 0.905

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
0.9732
0.0122
0.0099
0.0017
0.0030
0.0000
building
0.0819
0.8771
0.0371
0.0017
0.0023
0.0000
low_veg
0.0549
0.1757
0.7273
0.0422
0.0000
0.0000
tree
0.0576
0.0034
0.1552
0.7839
0.0000
0.0000
car
0.3514
0.0105
0.0044
0.0021
0.6284
0.0031
clutter
0.7009
0.2615
0.0038
0.0003
0.0334
0.0000
Precision/Correctness
0.823
0.846
0.783
0.914
0.690
0.000
Recall/Completeness
0.973
0.877
0.727
0.784
0.628
0.000
F1
0.892
0.861
0.754
0.844
0.658
-nan

Overall accuracy 0.831

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
0.9849
0.0083
0.0045
0.0005
0.0018
0.0000
building
0.0743
0.8893
0.0340
0.0004
0.0020
0.0000
low_veg
0.0278
0.1869
0.7472
0.0381
0.0000
0.0000
tree
0.0258
0.0007
0.1426
0.8309
0.0000
0.0000
car
0.2248
0.0119
0.0011
0.0006
0.7572
0.0044
clutter
0.6852
0.2753
0.0035
0.0000
0.0360
0.0000
Precision/Correctness
0.852
0.855
0.809
0.933
0.708
0.000
Recall/Completeness
0.985
0.889
0.747
0.831
0.757
0.000
F1
0.914
0.872
0.777
0.879
0.732
-nan

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_area35_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8450
0.0642
0.0776
0.0113
0.0018
0.0001
building
0.0242
0.9502
0.0227
0.0026
0.0003
0.0000
low_veg
0.0347
0.0184
0.7686
0.1781
0.0001
0.0001
tree
0.0351
0.0119
0.1445
0.8085
0.0000
0.0000
car
0.2785
0.0543
0.0010
0.0051
0.6611
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.893
0.914
0.763
0.799
0.899
--
Recall/Completeness
0.845
0.950
0.769
0.809
0.661
--
F1
0.868
0.932
0.766
0.804
0.762
--

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_area35_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8867
0.0564
0.0542
0.0021
0.0005
0.0001
building
0.0171
0.9697
0.0124
0.0005
0.0003
0.0000
low_veg
0.0222
0.0073
0.7950
0.1754
0.0001
0.0001
tree
0.0113
0.0051
0.1141
0.8695
0.0000
0.0000
car
0.1609
0.0561
0.0001
0.0003
0.7827
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.941
0.941
0.819
0.820
0.950
--
Recall/Completeness
0.887
0.970
0.795
0.870
0.783
--
F1
0.913
0.955
0.807
0.844
0.858
--

Overall accuracy 0.883

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
0.9179
0.0320
0.0406
0.0061
0.0034
0.0000
building
0.0373
0.9069
0.0530
0.0022
0.0006
0.0000
low_veg
0.0406
0.0747
0.8244
0.0602
0.0001
0.0000
tree
0.0297
0.0073
0.1580
0.8050
0.0000
0.0000
car
0.3120
0.0278
0.0315
0.0025
0.6262
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.893
0.880
0.806
0.892
0.847
--
Recall/Completeness
0.918
0.907
0.824
0.805
0.626
--
F1
0.905
0.893
0.815
0.846
0.720
--

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_area38_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9408
0.0283
0.0281
0.0011
0.0018
0.0000
building
0.0294
0.9278
0.0416
0.0007
0.0006
0.0000
low_veg
0.0237
0.0732
0.8554
0.0478
0.0000
0.0000
tree
0.0104
0.0026
0.1327
0.8543
0.0000
0.0000
car
0.1960
0.0321
0.0239
0.0001
0.7479
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.935
0.896
0.844
0.922
0.896
--
Recall/Completeness
0.941
0.928
0.855
0.854
0.748
--
F1
0.938
0.911
0.849
0.887
0.815
--

Overall accuracy 0.896

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image