Detailled semantic labeling (2D) result


Name K. Takahashi
Affiliation Waseda University, Japan
Abbreviation WAS2
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
0.909
0.036
0.036
0.014
0.006
0.000
building
0.079
0.888
0.025
0.005
0.001
0.002
low_veg
0.064
0.023
0.764
0.149
0.000
0.000
tree
0.029
0.005
0.097
0.869
0.000
0.000
car
0.325
0.023
0.005
0.003
0.643
0.000
clutter
0.456
0.276
0.016
0.010
0.080
0.163
Precision/Correctness
0.837
0.925
0.810
0.840
0.755
0.763
Recall/Completeness
0.909
0.888
0.764
0.869
0.643
0.163
F1
0.871
0.906
0.786
0.854
0.695
0.268

Overall accuracy 0.853

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
0.929
0.031
0.029
0.007
0.003
0.000
building
0.069
0.908
0.018
0.002
0.001
0.002
low_veg
0.049
0.016
0.799
0.136
0.000
0.000
tree
0.014
0.002
0.080
0.903
0.000
0.000
car
0.223
0.026
0.004
0.002
0.745
0.000
clutter
0.420
0.295
0.012
0.009
0.083
0.181
Precision/Correctness
0.872
0.941
0.844
0.866
0.783
0.767
Recall/Completeness
0.929
0.908
0.799
0.903
0.745
0.181
F1
0.900
0.924
0.821
0.884
0.764
0.293

Overall accuracy 0.882
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9545
0.0130
0.0163
0.0098
0.0065
0.0000
building
0.0845
0.8874
0.0217
0.0045
0.0019
0.0000
low_veg
0.0648
0.0138
0.7293
0.1920
0.0001
0.0000
tree
0.0353
0.0027
0.0755
0.8840
0.0003
0.0021
car
0.3388
0.0007
0.0001
0.0003
0.6600
0.0000
clutter
0.0127
0.0000
0.0000
0.0052
0.0000
0.9822
Precision/Correctness
0.828
0.965
0.866
0.812
0.825
0.972
Recall/Completeness
0.955
0.887
0.729
0.884
0.660
0.982
F1
0.887
0.925
0.792
0.846
0.733
0.977

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_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9746
0.0103
0.0086
0.0024
0.0040
0.0000
building
0.0745
0.9112
0.0110
0.0013
0.0020
0.0000
low_veg
0.0441
0.0070
0.7629
0.1860
0.0000
0.0000
tree
0.0176
0.0007
0.0622
0.9183
0.0002
0.0010
car
0.2259
0.0000
0.0000
0.0000
0.7741
0.0000
clutter
0.0117
0.0000
0.0000
0.0003
0.0000
0.9880
Precision/Correctness
0.871
0.980
0.900
0.834
0.859
0.987
Recall/Completeness
0.975
0.911
0.763
0.918
0.774
0.988
F1
0.920
0.944
0.826
0.874
0.814
0.987

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: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9267
0.0508
0.0110
0.0039
0.0076
0.0000
building
0.0948
0.8818
0.0079
0.0022
0.0008
0.0125
low_veg
0.1815
0.0390
0.4705
0.3090
0.0001
0.0000
tree
0.0573
0.0110
0.0657
0.8657
0.0003
0.0000
car
0.3959
0.0356
0.0000
0.0025
0.5660
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.795
0.966
0.660
0.720
0.756
--
Recall/Completeness
0.927
0.882
0.470
0.866
0.566
--
F1
0.856
0.922
0.549
0.786
0.647
--

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_area4_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9465
0.0371
0.0085
0.0020
0.0060
0.0000
building
0.0782
0.9003
0.0064
0.0012
0.0007
0.0131
low_veg
0.1337
0.0144
0.5082
0.3437
0.0000
0.0000
tree
0.0226
0.0044
0.0596
0.9133
0.0001
0.0000
car
0.2948
0.0312
0.0000
0.0013
0.6726
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.829
0.978
0.694
0.740
0.777
--
Recall/Completeness
0.947
0.900
0.508
0.913
0.673
--
F1
0.884
0.938
0.587
0.818
0.721
--

Overall accuracy 0.896

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
0.9220
0.0351
0.0284
0.0058
0.0087
0.0000
building
0.0653
0.9131
0.0187
0.0026
0.0002
0.0000
low_veg
0.1404
0.0144
0.6691
0.1758
0.0004
0.0000
tree
0.0265
0.0034
0.0640
0.9058
0.0003
0.0000
car
0.4066
0.0122
0.0077
0.0001
0.5734
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.822
0.963
0.690
0.925
0.796
--
Recall/Completeness
0.922
0.913
0.669
0.906
0.573
--
F1
0.869
0.937
0.680
0.915
0.667
--

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_area6_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9472
0.0245
0.0210
0.0015
0.0057
0.0000
building
0.0505
0.9341
0.0148
0.0005
0.0002
0.0000
low_veg
0.1149
0.0056
0.7153
0.1643
0.0000
0.0000
tree
0.0118
0.0009
0.0524
0.9348
0.0001
0.0000
car
0.3112
0.0115
0.0071
0.0000
0.6702
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.868
0.978
0.728
0.944
0.847
--
Recall/Completeness
0.947
0.934
0.715
0.935
0.670
--
F1
0.906
0.956
0.722
0.939
0.748
--

Overall accuracy 0.913

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
0.8815
0.0359
0.0720
0.0066
0.0038
0.0002
building
0.0397
0.9320
0.0250
0.0029
0.0004
0.0000
low_veg
0.0608
0.0097
0.8444
0.0847
0.0004
0.0000
tree
0.0323
0.0064
0.0758
0.8853
0.0001
0.0001
car
0.3795
0.0014
0.0044
0.0017
0.6130
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.887
0.936
0.781
0.916
0.880
--
Recall/Completeness
0.882
0.932
0.844
0.885
0.613
--
F1
0.884
0.934
0.811
0.900
0.723
--

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_area8_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9006
0.0322
0.0631
0.0018
0.0022
0.0002
building
0.0274
0.9557
0.0158
0.0006
0.0004
0.0000
low_veg
0.0419
0.0040
0.8776
0.0764
0.0001
0.0000
tree
0.0132
0.0032
0.0556
0.9280
0.0000
0.0000
car
0.2723
0.0007
0.0015
0.0010
0.7245
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.930
0.952
0.822
0.935
0.919
--
Recall/Completeness
0.901
0.956
0.878
0.928
0.725
--
F1
0.915
0.954
0.849
0.931
0.810
--

Overall accuracy 0.914

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
0.8230
0.1104
0.0453
0.0171
0.0043
0.0000
building
0.0766
0.8844
0.0239
0.0128
0.0023
0.0000
low_veg
0.0696
0.0473
0.6874
0.1954
0.0003
0.0000
tree
0.0187
0.0080
0.0758
0.8974
0.0000
0.0000
car
0.2682
0.0278
0.0035
0.0012
0.6994
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.895
0.802
0.760
0.808
0.690
--
Recall/Completeness
0.823
0.884
0.687
0.897
0.699
--
F1
0.858
0.841
0.722
0.850
0.694
--

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_area10_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8450
0.1065
0.0385
0.0072
0.0028
0.0000
building
0.0680
0.9001
0.0203
0.0095
0.0021
0.0000
low_veg
0.0626
0.0364
0.7279
0.1728
0.0004
0.0000
tree
0.0079
0.0040
0.0586
0.9295
0.0000
0.0000
car
0.1803
0.0328
0.0024
0.0000
0.7846
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.917
0.819
0.797
0.844
0.716
--
Recall/Completeness
0.845
0.900
0.728
0.929
0.785
--
F1
0.879
0.858
0.761
0.885
0.749
--

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_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8951
0.0426
0.0350
0.0234
0.0039
0.0000
building
0.0872
0.8957
0.0106
0.0059
0.0006
0.0000
low_veg
0.0774
0.0287
0.7373
0.1563
0.0002
0.0000
tree
0.0175
0.0083
0.1084
0.8658
0.0000
0.0000
car
0.1878
0.0101
0.0000
0.0006
0.8015
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.732
0.907
0.819
0.866
0.843
--
Recall/Completeness
0.895
0.896
0.737
0.866
0.801
--
F1
0.805
0.901
0.776
0.866
0.822
--

Overall accuracy 0.838

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
0.9197
0.0398
0.0273
0.0118
0.0015
0.0000
building
0.0859
0.9072
0.0044
0.0020
0.0006
0.0000
low_veg
0.0734
0.0201
0.7729
0.1333
0.0002
0.0000
tree
0.0097
0.0038
0.0931
0.8934
0.0000
0.0000
car
0.0732
0.0090
0.0000
0.0000
0.9177
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.760
0.932
0.848
0.893
0.894
--
Recall/Completeness
0.920
0.907
0.773
0.893
0.918
--
F1
0.833
0.920
0.809
0.893
0.906
--

Overall accuracy 0.866

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
0.8201
0.0561
0.0875
0.0316
0.0047
0.0000
building
0.0297
0.9492
0.0143
0.0068
0.0000
0.0000
low_veg
0.1088
0.0414
0.6543
0.1943
0.0012
0.0000
tree
0.0329
0.0120
0.1012
0.8539
0.0001
0.0000
car
0.1676
0.0000
0.0000
0.0070
0.8254
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.809
0.859
0.746
0.832
0.609
--
Recall/Completeness
0.820
0.949
0.654
0.854
0.825
--
F1
0.815
0.902
0.697
0.843
0.701
--

Overall accuracy 0.812

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
0.8359
0.0543
0.0841
0.0217
0.0040
0.0000
building
0.0205
0.9691
0.0077
0.0027
0.0000
0.0000
low_veg
0.1027
0.0277
0.6822
0.1861
0.0012
0.0000
tree
0.0231
0.0061
0.0896
0.8812
0.0000
0.0000
car
0.0572
0.0000
0.0000
0.0025
0.9403
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.840
0.887
0.768
0.852
0.599
--
Recall/Completeness
0.836
0.969
0.682
0.881
0.940
--
F1
0.838
0.926
0.723
0.866
0.732
--

Overall accuracy 0.836

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
0.8615
0.0251
0.0730
0.0385
0.0020
0.0000
building
0.1089
0.8646
0.0174
0.0082
0.0009
0.0000
low_veg
0.0262
0.0112
0.8501
0.1119
0.0001
0.0006
tree
0.0345
0.0056
0.1284
0.8315
0.0000
0.0000
car
0.2947
0.0046
0.0000
0.0001
0.7006
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.767
0.943
0.804
0.883
0.754
--
Recall/Completeness
0.861
0.865
0.850
0.831
0.701
--
F1
0.812
0.902
0.826
0.856
0.726
--

Overall accuracy 0.847

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
0.8906
0.0203
0.0652
0.0231
0.0008
0.0000
building
0.1039
0.8864
0.0065
0.0023
0.0010
0.0000
low_veg
0.0205
0.0063
0.8730
0.0996
0.0001
0.0006
tree
0.0246
0.0025
0.1138
0.8592
0.0000
0.0000
car
0.1984
0.0008
0.0000
0.0000
0.8008
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.798
0.965
0.831
0.904
0.800
--
Recall/Completeness
0.891
0.886
0.873
0.859
0.801
--
F1
0.842
0.924
0.851
0.881
0.800
--

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_area20_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8430
0.0679
0.0180
0.0653
0.0058
0.0000
building
0.0313
0.9333
0.0282
0.0073
0.0000
0.0000
low_veg
0.0445
0.0326
0.7041
0.2187
0.0000
0.0000
tree
0.0091
0.0019
0.0442
0.9447
0.0001
0.0000
car
0.1480
0.0571
0.0395
0.0072
0.7482
0.0000
clutter
0.0000
0.9996
0.0000
0.0004
0.0000
0.0000
Precision/Correctness
0.904
0.761
0.837
0.872
0.719
-nan
Recall/Completeness
0.843
0.933
0.704
0.945
0.748
0.000
F1
0.872
0.838
0.765
0.907
0.733
-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_area20_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8719
0.0602
0.0156
0.0483
0.0040
0.0000
building
0.0281
0.9459
0.0240
0.0020
0.0000
0.0000
low_veg
0.0372
0.0231
0.7493
0.1904
0.0000
0.0000
tree
0.0038
0.0005
0.0338
0.9619
0.0000
0.0000
car
0.0701
0.0522
0.0352
0.0022
0.8403
0.0000
clutter
0.0000
1.0000
0.0000
0.0000
0.0000
0.0000
Precision/Correctness
0.929
0.778
0.866
0.899
0.751
-nan
Recall/Completeness
0.872
0.946
0.749
0.962
0.840
0.000
F1
0.900
0.854
0.804
0.929
0.793
-nan

Overall accuracy 0.874

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
0.9142
0.0172
0.0345
0.0267
0.0074
0.0000
building
0.0720
0.9049
0.0166
0.0051
0.0014
0.0000
low_veg
0.1235
0.0325
0.6729
0.1707
0.0004
0.0000
tree
0.0281
0.0038
0.0589
0.9086
0.0007
0.0000
car
0.3360
0.0015
0.0013
0.0073
0.6539
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.855
0.925
0.814
0.856
0.713
--
Recall/Completeness
0.914
0.905
0.673
0.909
0.654
--
F1
0.884
0.915
0.737
0.882
0.682
--

Overall accuracy 0.859

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
0.9419
0.0107
0.0289
0.0133
0.0052
0.0000
building
0.0627
0.9246
0.0100
0.0013
0.0014
0.0000
low_veg
0.1203
0.0204
0.7146
0.1443
0.0004
0.0000
tree
0.0127
0.0012
0.0443
0.9413
0.0004
0.0000
car
0.2365
0.0014
0.0002
0.0031
0.7589
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.883
0.956
0.854
0.892
0.743
--
Recall/Completeness
0.942
0.925
0.715
0.941
0.759
--
F1
0.912
0.940
0.778
0.916
0.751
--

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_area24_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8132
0.0338
0.1197
0.0280
0.0053
0.0000
building
0.0555
0.8517
0.0822
0.0106
0.0001
0.0000
low_veg
0.0243
0.0195
0.8671
0.0888
0.0003
0.0000
tree
0.0179
0.0087
0.1696
0.8038
0.0001
0.0000
car
0.2583
0.0000
0.0003
0.0014
0.7400
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.820
0.914
0.824
0.827
0.753
--
Recall/Completeness
0.813
0.852
0.867
0.804
0.740
--
F1
0.817
0.882
0.845
0.815
0.747
--

Overall accuracy 0.840

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
0.8447
0.0244
0.1102
0.0177
0.0030
0.0000
building
0.0530
0.8614
0.0775
0.0080
0.0001
0.0000
low_veg
0.0215
0.0144
0.8860
0.0777
0.0003
0.0000
tree
0.0112
0.0043
0.1499
0.8346
0.0000
0.0000
car
0.1588
0.0000
0.0000
0.0000
0.8412
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.844
0.939
0.845
0.851
0.796
--
Recall/Completeness
0.845
0.861
0.886
0.835
0.841
--
F1
0.844
0.899
0.865
0.843
0.818
--

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_area27_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9407
0.0215
0.0210
0.0058
0.0111
0.0000
building
0.1032
0.8674
0.0239
0.0043
0.0011
0.0000
low_veg
0.0810
0.0152
0.6724
0.2308
0.0006
0.0000
tree
0.0151
0.0040
0.0584
0.9222
0.0003
0.0000
car
0.3140
0.0061
0.0050
0.0043
0.6706
0.0000
clutter
0.4894
0.3190
0.0709
0.0114
0.1094
0.0000
Precision/Correctness
0.822
0.964
0.861
0.655
0.834
0.000
Recall/Completeness
0.941
0.867
0.672
0.922
0.671
0.000
F1
0.878
0.913
0.755
0.766
0.744
-nan

Overall accuracy 0.850

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
0.9633
0.0146
0.0150
0.0021
0.0050
0.0000
building
0.0886
0.8915
0.0168
0.0021
0.0010
0.0000
low_veg
0.0578
0.0067
0.7115
0.2235
0.0005
0.0000
tree
0.0054
0.0012
0.0428
0.9505
0.0001
0.0000
car
0.2082
0.0045
0.0041
0.0035
0.7797
0.0000
clutter
0.4890
0.3311
0.0539
0.0050
0.1210
0.0000
Precision/Correctness
0.860
0.979
0.898
0.679
0.892
0.000
Recall/Completeness
0.963
0.892
0.711
0.951
0.780
0.000
F1
0.909
0.933
0.794
0.792
0.832
-nan

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_area29_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9474
0.0194
0.0181
0.0096
0.0054
0.0000
building
0.0568
0.9259
0.0118
0.0056
0.0000
0.0000
low_veg
0.0762
0.0196
0.6023
0.3017
0.0002
0.0000
tree
0.0096
0.0012
0.0433
0.9459
0.0000
0.0000
car
0.3375
0.0159
0.0000
0.0150
0.6315
0.0000
clutter
0.5896
0.2920
0.0295
0.0039
0.0828
0.0023
Precision/Correctness
0.890
0.926
0.844
0.672
0.639
1.000
Recall/Completeness
0.947
0.926
0.602
0.946
0.632
0.002
F1
0.918
0.926
0.703
0.786
0.635
0.005

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
0.9649
0.0142
0.0131
0.0037
0.0041
0.0000
building
0.0489
0.9415
0.0071
0.0025
0.0000
0.0000
low_veg
0.0496
0.0081
0.6471
0.2951
0.0001
0.0000
tree
0.0030
0.0001
0.0352
0.9617
0.0000
0.0000
car
0.2345
0.0206
0.0000
0.0137
0.7313
0.0000
clutter
0.5792
0.3093
0.0208
0.0007
0.0872
0.0027
Precision/Correctness
0.915
0.944
0.881
0.705
0.644
1.000
Recall/Completeness
0.965
0.941
0.647
0.962
0.731
0.003
F1
0.939
0.943
0.746
0.813
0.685
0.005

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
0.9636
0.0190
0.0085
0.0021
0.0067
0.0000
building
0.1172
0.8663
0.0092
0.0036
0.0036
0.0000
low_veg
0.0496
0.0031
0.9075
0.0395
0.0003
0.0000
tree
0.0678
0.0019
0.0702
0.8593
0.0008
0.0000
car
0.2870
0.0771
0.0054
0.0027
0.6278
0.0000
clutter
0.6259
0.1993
0.0398
0.0370
0.0980
0.0000
Precision/Correctness
0.826
0.932
0.898
0.915
0.762
-nan
Recall/Completeness
0.964
0.866
0.907
0.859
0.628
0.000
F1
0.890
0.898
0.903
0.886
0.689
-nan

Overall accuracy 0.872

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
0.9729
0.0174
0.0062
0.0005
0.0030
0.0000
building
0.1042
0.8874
0.0046
0.0008
0.0030
0.0000
low_veg
0.0287
0.0014
0.9348
0.0350
0.0001
0.0000
tree
0.0277
0.0003
0.0540
0.9179
0.0001
0.0000
car
0.1991
0.0915
0.0023
0.0008
0.7064
0.0000
clutter
0.5900
0.2239
0.0388
0.0408
0.1065
0.0000
Precision/Correctness
0.861
0.940
0.928
0.935
0.794
-nan
Recall/Completeness
0.973
0.887
0.935
0.918
0.706
0.000
F1
0.914
0.913
0.931
0.927
0.748
-nan

Overall accuracy 0.899

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
0.9738
0.0123
0.0084
0.0024
0.0030
0.0000
building
0.0918
0.8530
0.0491
0.0028
0.0032
0.0000
low_veg
0.0584
0.0121
0.8653
0.0633
0.0009
0.0000
tree
0.0577
0.0012
0.1258
0.8153
0.0000
0.0000
car
0.3416
0.0326
0.0008
0.0014
0.6236
0.0000
clutter
0.7275
0.0908
0.0003
0.0014
0.1500
0.0298
Precision/Correctness
0.815
0.953
0.813
0.881
0.436
0.994
Recall/Completeness
0.974
0.853
0.865
0.815
0.624
0.030
F1
0.887
0.900
0.838
0.847
0.513
0.058

Overall accuracy 0.850

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
0.9830
0.0100
0.0047
0.0009
0.0014
0.0000
building
0.0818
0.8712
0.0435
0.0006
0.0029
0.0000
low_veg
0.0273
0.0092
0.9023
0.0603
0.0009
0.0000
tree
0.0262
0.0002
0.1141
0.8595
0.0000
0.0000
car
0.2339
0.0330
0.0000
0.0005
0.7325
0.0000
clutter
0.7001
0.0992
0.0000
0.0010
0.1655
0.0342
Precision/Correctness
0.846
0.961
0.837
0.901
0.425
1.000
Recall/Completeness
0.983
0.871
0.902
0.860
0.733
0.034
F1
0.909
0.914
0.868
0.880
0.538
0.066

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_area35_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8562
0.0600
0.0694
0.0117
0.0026
0.0000
building
0.0507
0.9118
0.0321
0.0052
0.0002
0.0000
low_veg
0.0449
0.0122
0.7318
0.2104
0.0008
0.0000
tree
0.0376
0.0049
0.1313
0.8258
0.0005
0.0000
car
0.3418
0.0142
0.0009
0.0040
0.6391
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.856
0.926
0.762
0.774
0.823
--
Recall/Completeness
0.856
0.912
0.732
0.826
0.639
--
F1
0.856
0.919
0.747
0.799
0.720
--

Overall accuracy 0.832

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
0.8897
0.0567
0.0488
0.0031
0.0017
0.0000
building
0.0393
0.9399
0.0196
0.0010
0.0003
0.0000
low_veg
0.0280
0.0058
0.7574
0.2079
0.0008
0.0000
tree
0.0120
0.0012
0.1015
0.8851
0.0002
0.0000
car
0.2369
0.0172
0.0000
0.0001
0.7458
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.909
0.944
0.820
0.796
0.854
--
Recall/Completeness
0.890
0.940
0.757
0.885
0.746
--
F1
0.899
0.942
0.787
0.838
0.796
--

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_area38_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9278
0.0248
0.0370
0.0064
0.0039
0.0000
building
0.0946
0.8520
0.0493
0.0033
0.0008
0.0000
low_veg
0.0454
0.0323
0.8551
0.0671
0.0002
0.0000
tree
0.0358
0.0026
0.1588
0.8026
0.0001
0.0000
car
0.3341
0.0179
0.0235
0.0022
0.6224
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.841
0.929
0.817
0.880
0.819
--
Recall/Completeness
0.928
0.852
0.855
0.803
0.622
--
F1
0.883
0.889
0.836
0.840
0.707
--

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_area38_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9472
0.0235
0.0255
0.0016
0.0023
0.0000
building
0.0848
0.8776
0.0360
0.0008
0.0008
0.0000
low_veg
0.0262
0.0301
0.8884
0.0553
0.0000
0.0000
tree
0.0144
0.0005
0.1346
0.8505
0.0000
0.0000
car
0.2264
0.0213
0.0182
0.0003
0.7339
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.882
0.940
0.854
0.910
0.865
--
Recall/Completeness
0.947
0.878
0.888
0.850
0.734
--
F1
0.913
0.908
0.871
0.879
0.794
--

Overall accuracy 0.893

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image