Detailled semantic labeling (2D) result


Name W. Sun
Affiliation Univ. of Calgary, Canada
Abbreviation UCal7
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
0.888
0.053
0.037
0.017
0.005
0.000
building
0.063
0.905
0.026
0.005
0.001
0.000
low_veg
0.067
0.032
0.728
0.172
0.001
0.000
tree
0.025
0.006
0.103
0.866
0.000
0.000
car
0.376
0.060
0.013
0.006
0.545
0.000
clutter
0.373
0.316
0.012
0.008
0.043
0.247
Precision/Correctness
0.846
0.899
0.795
0.819
0.764
0.963
Recall/Completeness
0.888
0.905
0.728
0.866
0.545
0.247
F1
0.867
0.902
0.760
0.842
0.636
0.394

Overall accuracy 0.843

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
0.912
0.046
0.029
0.008
0.003
0.000
building
0.055
0.923
0.020
0.002
0.001
0.000
low_veg
0.053
0.023
0.762
0.161
0.000
0.000
tree
0.013
0.002
0.085
0.899
0.000
0.000
car
0.283
0.065
0.010
0.004
0.638
0.000
clutter
0.334
0.336
0.009
0.003
0.044
0.274
Precision/Correctness
0.880
0.919
0.831
0.845
0.795
0.976
Recall/Completeness
0.912
0.923
0.762
0.899
0.638
0.274
F1
0.896
0.921
0.795
0.871
0.708
0.428

Overall accuracy 0.872
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9453
0.0177
0.0167
0.0132
0.0072
0.0000
building
0.0484
0.9242
0.0234
0.0033
0.0005
0.0001
low_veg
0.1044
0.0240
0.6765
0.1944
0.0007
0.0000
tree
0.0368
0.0043
0.0836
0.8742
0.0002
0.0009
car
0.3866
0.0158
0.0006
0.0027
0.5930
0.0014
clutter
0.0113
0.0000
0.0000
0.0190
0.0000
0.9697
Precision/Correctness
0.820
0.948
0.846
0.806
0.812
0.985
Recall/Completeness
0.945
0.924
0.677
0.874
0.593
0.970
F1
0.878
0.936
0.752
0.839
0.685
0.977

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_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9681
0.0135
0.0085
0.0044
0.0056
0.0000
building
0.0393
0.9449
0.0144
0.0009
0.0005
0.0000
low_veg
0.0868
0.0136
0.7106
0.1885
0.0005
0.0000
tree
0.0196
0.0015
0.0718
0.9067
0.0001
0.0003
car
0.2695
0.0146
0.0000
0.0013
0.7138
0.0008
clutter
0.0093
0.0000
0.0000
0.0052
0.0000
0.9855
Precision/Correctness
0.861
0.969
0.879
0.829
0.840
0.994
Recall/Completeness
0.968
0.945
0.711
0.907
0.714
0.986
F1
0.912
0.957
0.786
0.866
0.772
0.990

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_area4_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9095
0.0743
0.0082
0.0034
0.0046
0.0000
building
0.0720
0.9187
0.0066
0.0020
0.0007
0.0000
low_veg
0.1823
0.0717
0.4776
0.2667
0.0018
0.0000
tree
0.0605
0.0159
0.0935
0.8296
0.0004
0.0000
car
0.4613
0.0321
0.0003
0.0012
0.5051
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.820
0.952
0.668
0.740
0.799
--
Recall/Completeness
0.910
0.919
0.478
0.830
0.505
--
F1
0.863
0.935
0.557
0.782
0.619
--

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_area4_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9335
0.0567
0.0056
0.0010
0.0031
0.0000
building
0.0577
0.9351
0.0054
0.0010
0.0007
0.0000
low_veg
0.1500
0.0352
0.5138
0.2997
0.0014
0.0000
tree
0.0308
0.0069
0.0882
0.8738
0.0003
0.0000
car
0.3695
0.0239
0.0000
0.0001
0.6065
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.854
0.968
0.698
0.761
0.830
--
Recall/Completeness
0.934
0.935
0.514
0.874
0.607
--
F1
0.892
0.951
0.592
0.813
0.701
--

Overall accuracy 0.911

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
0.8938
0.0516
0.0378
0.0102
0.0065
0.0000
building
0.0873
0.8877
0.0216
0.0029
0.0005
0.0000
low_veg
0.0929
0.0245
0.6895
0.1925
0.0006
0.0000
tree
0.0216
0.0037
0.0759
0.8987
0.0001
0.0000
car
0.5510
0.0243
0.0018
0.0006
0.4224
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.808
0.945
0.655
0.915
0.784
--
Recall/Completeness
0.894
0.888
0.689
0.899
0.422
--
F1
0.849
0.915
0.672
0.907
0.549
--

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_area6_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9277
0.0360
0.0285
0.0032
0.0046
0.0000
building
0.0772
0.9058
0.0155
0.0011
0.0003
0.0000
low_veg
0.0700
0.0126
0.7362
0.1808
0.0005
0.0000
tree
0.0093
0.0012
0.0635
0.9260
0.0000
0.0000
car
0.4770
0.0200
0.0010
0.0000
0.5020
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.846
0.966
0.696
0.936
0.827
--
Recall/Completeness
0.928
0.906
0.736
0.926
0.502
--
F1
0.885
0.935
0.715
0.931
0.625
--

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_area8_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8944
0.0326
0.0550
0.0137
0.0043
0.0000
building
0.0525
0.9230
0.0204
0.0035
0.0006
0.0000
low_veg
0.0679
0.0133
0.7981
0.1200
0.0007
0.0000
tree
0.0289
0.0078
0.0764
0.8868
0.0001
0.0000
car
0.3786
0.0141
0.0239
0.0050
0.5784
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.879
0.934
0.794
0.881
0.855
--
Recall/Completeness
0.894
0.923
0.798
0.887
0.578
--
F1
0.886
0.929
0.796
0.884
0.690
--

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_area8_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9234
0.0241
0.0445
0.0056
0.0025
0.0000
building
0.0425
0.9425
0.0131
0.0014
0.0005
0.0000
low_veg
0.0495
0.0058
0.8348
0.1095
0.0004
0.0000
tree
0.0134
0.0042
0.0576
0.9248
0.0001
0.0000
car
0.2756
0.0115
0.0173
0.0040
0.6915
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.916
0.958
0.839
0.905
0.901
--
Recall/Completeness
0.923
0.943
0.835
0.925
0.692
--
F1
0.920
0.950
0.837
0.915
0.782
--

Overall accuracy 0.908

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
0.8061
0.1237
0.0445
0.0207
0.0050
0.0000
building
0.0596
0.9083
0.0201
0.0106
0.0007
0.0006
low_veg
0.0795
0.0481
0.6920
0.1804
0.0000
0.0000
tree
0.0199
0.0073
0.0905
0.8823
0.0000
0.0000
car
0.3310
0.0386
0.0022
0.0021
0.6261
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.898
0.791
0.752
0.812
0.682
--
Recall/Completeness
0.806
0.908
0.692
0.882
0.626
--
F1
0.849
0.846
0.721
0.846
0.653
--

Overall accuracy 0.825

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
0.8321
0.1173
0.0370
0.0096
0.0040
0.0000
building
0.0517
0.9256
0.0141
0.0074
0.0006
0.0007
low_veg
0.0734
0.0380
0.7306
0.1579
0.0000
0.0000
tree
0.0089
0.0032
0.0720
0.9159
0.0000
0.0000
car
0.2386
0.0429
0.0007
0.0005
0.7173
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.920
0.810
0.794
0.851
0.692
--
Recall/Completeness
0.832
0.926
0.731
0.916
0.717
--
F1
0.874
0.864
0.761
0.882
0.705
--

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_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8807
0.0416
0.0439
0.0298
0.0033
0.0007
building
0.0368
0.9271
0.0302
0.0055
0.0004
0.0000
low_veg
0.0389
0.0295
0.7462
0.1852
0.0003
0.0000
tree
0.0114
0.0073
0.1233
0.8580
0.0000
0.0000
car
0.2278
0.0047
0.0245
0.0044
0.7387
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.841
0.912
0.789
0.843
0.855
--
Recall/Completeness
0.881
0.927
0.746
0.858
0.739
--
F1
0.860
0.919
0.767
0.851
0.793
--

Overall accuracy 0.841

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
0.9058
0.0394
0.0367
0.0161
0.0012
0.0007
building
0.0343
0.9416
0.0220
0.0017
0.0004
0.0000
low_veg
0.0348
0.0197
0.7796
0.1657
0.0002
0.0000
tree
0.0054
0.0023
0.1063
0.8860
0.0000
0.0000
car
0.1180
0.0035
0.0211
0.0001
0.8573
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.872
0.938
0.818
0.869
0.913
--
Recall/Completeness
0.906
0.942
0.780
0.886
0.857
--
F1
0.889
0.940
0.798
0.877
0.884
--

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_area14_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8132
0.0631
0.0822
0.0370
0.0045
0.0000
building
0.0255
0.9420
0.0268
0.0051
0.0000
0.0006
low_veg
0.0690
0.0502
0.6979
0.1827
0.0001
0.0000
tree
0.0245
0.0133
0.1195
0.8427
0.0000
0.0000
car
0.1979
0.0000
0.0008
0.0030
0.7983
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.858
0.839
0.736
0.835
0.659
--
Recall/Completeness
0.813
0.942
0.698
0.843
0.798
--
F1
0.835
0.888
0.717
0.839
0.722
--

Overall accuracy 0.816

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
0.8325
0.0609
0.0771
0.0258
0.0037
0.0000
building
0.0202
0.9617
0.0156
0.0019
0.0001
0.0006
low_veg
0.0632
0.0358
0.7263
0.1745
0.0001
0.0000
tree
0.0168
0.0071
0.1055
0.8705
0.0000
0.0000
car
0.0827
0.0000
0.0000
0.0000
0.9173
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.886
0.868
0.762
0.856
0.669
--
Recall/Completeness
0.833
0.962
0.726
0.871
0.917
--
F1
0.858
0.912
0.744
0.863
0.774
--

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_area16_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8128
0.0347
0.0994
0.0502
0.0028
0.0000
building
0.0562
0.8975
0.0355
0.0108
0.0000
0.0000
low_veg
0.0211
0.0204
0.8104
0.1475
0.0006
0.0000
tree
0.0245
0.0049
0.1249
0.8455
0.0002
0.0000
car
0.3411
0.0030
0.0370
0.0063
0.6126
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.829
0.924
0.781
0.853
0.673
--
Recall/Completeness
0.813
0.897
0.810
0.846
0.613
--
F1
0.821
0.910
0.795
0.849
0.641
--

Overall accuracy 0.839

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
0.8453
0.0306
0.0909
0.0319
0.0014
0.0000
building
0.0517
0.9210
0.0227
0.0045
0.0000
0.0000
low_veg
0.0162
0.0153
0.8356
0.1322
0.0006
0.0000
tree
0.0161
0.0020
0.1112
0.8705
0.0001
0.0000
car
0.2791
0.0001
0.0274
0.0006
0.6928
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.862
0.943
0.809
0.877
0.710
--
Recall/Completeness
0.845
0.921
0.836
0.871
0.693
--
F1
0.854
0.932
0.822
0.874
0.701
--

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_area20_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8617
0.0444
0.0408
0.0487
0.0044
0.0000
building
0.0179
0.9454
0.0296
0.0070
0.0000
0.0000
low_veg
0.0465
0.0300
0.7068
0.2157
0.0010
0.0000
tree
0.0105
0.0018
0.0562
0.9314
0.0000
0.0000
car
0.2939
0.0174
0.0368
0.0217
0.6301
0.0000
clutter
0.0116
0.9751
0.0114
0.0019
0.0000
0.0000
Precision/Correctness
0.907
0.787
0.789
0.879
0.708
-nan
Recall/Completeness
0.862
0.945
0.707
0.931
0.630
0.000
F1
0.884
0.859
0.746
0.904
0.667
-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_area20_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8919
0.0378
0.0375
0.0296
0.0032
0.0000
building
0.0145
0.9616
0.0218
0.0022
0.0000
0.0000
low_veg
0.0396
0.0209
0.7464
0.1920
0.0011
0.0000
tree
0.0047
0.0003
0.0440
0.9510
0.0000
0.0000
car
0.2049
0.0187
0.0309
0.0141
0.7314
0.0000
clutter
0.0056
0.9873
0.0071
0.0000
0.0000
0.0000
Precision/Correctness
0.935
0.802
0.822
0.905
0.719
-nan
Recall/Completeness
0.892
0.962
0.746
0.951
0.731
0.000
F1
0.913
0.875
0.782
0.927
0.725
-nan

Overall accuracy 0.876

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
0.8858
0.0375
0.0393
0.0327
0.0048
0.0000
building
0.0375
0.9340
0.0195
0.0088
0.0002
0.0001
low_veg
0.0806
0.0410
0.7043
0.1741
0.0000
0.0000
tree
0.0254
0.0033
0.0684
0.9029
0.0000
0.0000
car
0.3661
0.0032
0.0258
0.0293
0.5756
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.892
0.887
0.798
0.846
0.801
--
Recall/Completeness
0.886
0.934
0.704
0.903
0.576
--
F1
0.889
0.910
0.748
0.873
0.670
--

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
0.9165
0.0305
0.0326
0.0176
0.0028
0.0000
building
0.0305
0.9541
0.0103
0.0048
0.0002
0.0000
low_veg
0.0743
0.0298
0.7484
0.1475
0.0000
0.0000
tree
0.0115
0.0009
0.0520
0.9356
0.0000
0.0000
car
0.2875
0.0023
0.0236
0.0203
0.6662
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.920
0.916
0.841
0.883
0.851
--
Recall/Completeness
0.916
0.954
0.748
0.936
0.666
--
F1
0.918
0.934
0.792
0.909
0.747
--

Overall accuracy 0.894

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
0.8019
0.0631
0.0944
0.0349
0.0057
0.0000
building
0.0725
0.8640
0.0555
0.0079
0.0000
0.0000
low_veg
0.0432
0.0161
0.8464
0.0939
0.0004
0.0000
tree
0.0296
0.0054
0.1526
0.8123
0.0000
0.0000
car
0.3324
0.0149
0.0037
0.0187
0.6303
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.744
0.904
0.847
0.820
0.711
--
Recall/Completeness
0.802
0.864
0.846
0.812
0.630
--
F1
0.772
0.884
0.847
0.816
0.668
--

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
0.8311
0.0567
0.0831
0.0251
0.0040
0.0000
building
0.0656
0.8807
0.0480
0.0056
0.0000
0.0000
low_veg
0.0386
0.0120
0.8652
0.0838
0.0003
0.0000
tree
0.0226
0.0023
0.1303
0.8448
0.0000
0.0000
car
0.2378
0.0167
0.0012
0.0148
0.7295
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.773
0.924
0.871
0.841
0.734
--
Recall/Completeness
0.831
0.881
0.865
0.845
0.729
--
F1
0.801
0.902
0.868
0.843
0.732
--

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_area27_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9252
0.0391
0.0199
0.0062
0.0095
0.0000
building
0.0943
0.8806
0.0214
0.0030
0.0008
0.0000
low_veg
0.1052
0.0336
0.6507
0.2096
0.0009
0.0000
tree
0.0174
0.0046
0.0783
0.8997
0.0001
0.0000
car
0.4067
0.0199
0.0090
0.0068
0.5567
0.0009
clutter
0.3731
0.4506
0.0960
0.0029
0.0775
0.0000
Precision/Correctness
0.810
0.935
0.852
0.671
0.831
0.000
Recall/Completeness
0.925
0.881
0.651
0.900
0.557
0.000
F1
0.864
0.907
0.738
0.769
0.667
-nan

Overall accuracy 0.839

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
0.9506
0.0293
0.0128
0.0024
0.0049
0.0000
building
0.0826
0.8992
0.0165
0.0009
0.0008
0.0000
low_veg
0.0868
0.0191
0.6915
0.2017
0.0008
0.0000
tree
0.0078
0.0016
0.0627
0.9279
0.0000
0.0000
car
0.3130
0.0191
0.0071
0.0056
0.6543
0.0009
clutter
0.3486
0.4872
0.0700
0.0006
0.0935
0.0000
Precision/Correctness
0.845
0.958
0.888
0.697
0.881
0.000
Recall/Completeness
0.951
0.899
0.692
0.928
0.654
0.000
F1
0.894
0.928
0.778
0.796
0.751
-nan

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_area29_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8760
0.0826
0.0235
0.0119
0.0060
0.0000
building
0.0577
0.9249
0.0116
0.0055
0.0003
0.0000
low_veg
0.0860
0.0228
0.6120
0.2782
0.0010
0.0000
tree
0.0080
0.0015
0.0515
0.9390
0.0000
0.0000
car
0.3016
0.0359
0.0042
0.0086
0.6477
0.0020
clutter
0.4880
0.4141
0.0232
0.0141
0.0476
0.0130
Precision/Correctness
0.886
0.830
0.823
0.681
0.675
0.906
Recall/Completeness
0.876
0.925
0.612
0.939
0.648
0.013
F1
0.881
0.875
0.702
0.789
0.661
0.026

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_area29_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8937
0.0796
0.0170
0.0052
0.0044
0.0000
building
0.0515
0.9397
0.0060
0.0027
0.0003
0.0000
low_veg
0.0637
0.0106
0.6560
0.2688
0.0008
0.0000
tree
0.0028
0.0003
0.0403
0.9566
0.0000
0.0000
car
0.2083
0.0302
0.0024
0.0077
0.7495
0.0020
clutter
0.4677
0.4429
0.0186
0.0056
0.0497
0.0156
Precision/Correctness
0.910
0.846
0.866
0.718
0.690
0.938
Recall/Completeness
0.894
0.940
0.656
0.957
0.750
0.016
F1
0.902
0.890
0.747
0.820
0.719
0.031

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_area31_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9654
0.0174
0.0065
0.0039
0.0068
0.0000
building
0.0706
0.9150
0.0111
0.0013
0.0015
0.0004
low_veg
0.0592
0.0067
0.8992
0.0342
0.0007
0.0000
tree
0.0516
0.0041
0.1162
0.8272
0.0009
0.0000
car
0.2953
0.2451
0.0055
0.0025
0.4517
0.0000
clutter
0.5759
0.2701
0.0182
0.0075
0.1079
0.0205
Precision/Correctness
0.854
0.906
0.872
0.928
0.702
0.845
Recall/Completeness
0.965
0.915
0.899
0.827
0.452
0.020
F1
0.906
0.911
0.886
0.875
0.550
0.040

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_area31_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9765
0.0139
0.0046
0.0007
0.0043
0.0000
building
0.0577
0.9346
0.0056
0.0003
0.0012
0.0005
low_veg
0.0371
0.0037
0.9302
0.0286
0.0004
0.0000
tree
0.0241
0.0008
0.0959
0.8788
0.0004
0.0000
car
0.2132
0.2721
0.0018
0.0004
0.5125
0.0000
clutter
0.5394
0.3055
0.0138
0.0023
0.1152
0.0237
Precision/Correctness
0.889
0.922
0.906
0.953
0.725
0.842
Recall/Completeness
0.977
0.935
0.930
0.879
0.512
0.024
F1
0.931
0.928
0.918
0.914
0.600
0.046

Overall accuracy 0.904

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
0.9186
0.0690
0.0056
0.0040
0.0015
0.0014
building
0.1041
0.7929
0.0980
0.0037
0.0013
0.0000
low_veg
0.1186
0.0212
0.4716
0.3877
0.0006
0.0002
tree
0.0446
0.0046
0.1336
0.8171
0.0000
0.0000
car
0.4307
0.1079
0.0038
0.0045
0.4512
0.0018
clutter
0.5360
0.1046
0.0016
0.0015
0.0356
0.3207
Precision/Correctness
0.802
0.860
0.619
0.578
0.662
0.968
Recall/Completeness
0.919
0.793
0.472
0.817
0.451
0.321
F1
0.856
0.825
0.535
0.677
0.537
0.482

Overall accuracy 0.764

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
0.9304
0.0642
0.0030
0.0011
0.0008
0.0005
building
0.0972
0.8021
0.0975
0.0021
0.0011
0.0000
low_veg
0.0808
0.0152
0.4862
0.4171
0.0005
0.0002
tree
0.0227
0.0009
0.1220
0.8543
0.0000
0.0000
car
0.3461
0.1045
0.0010
0.0023
0.5441
0.0020
clutter
0.4999
0.1020
0.0009
0.0010
0.0390
0.3572
Precision/Correctness
0.832
0.879
0.631
0.577
0.671
0.986
Recall/Completeness
0.930
0.802
0.486
0.854
0.544
0.357
F1
0.879
0.839
0.549
0.689
0.601
0.524

Overall accuracy 0.784

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
0.8608
0.0579
0.0629
0.0170
0.0014
0.0000
building
0.0646
0.9149
0.0141
0.0056
0.0008
0.0000
low_veg
0.0666
0.0179
0.6799
0.2355
0.0001
0.0000
tree
0.0371
0.0054
0.1225
0.8349
0.0001
0.0000
car
0.4586
0.0081
0.0043
0.0083
0.5207
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.825
0.923
0.778
0.753
0.869
--
Recall/Completeness
0.861
0.915
0.680
0.835
0.521
--
F1
0.842
0.919
0.725
0.792
0.651
--

Overall accuracy 0.822

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
0.9011
0.0519
0.0420
0.0044
0.0005
0.0000
building
0.0527
0.9393
0.0061
0.0012
0.0007
0.0000
low_veg
0.0490
0.0088
0.7108
0.2313
0.0001
0.0000
tree
0.0144
0.0014
0.0954
0.8888
0.0000
0.0000
car
0.3510
0.0061
0.0025
0.0031
0.6374
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.873
0.945
0.837
0.778
0.911
--
Recall/Completeness
0.901
0.939
0.711
0.889
0.637
--
F1
0.887
0.942
0.769
0.829
0.750
--

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: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8970
0.0381
0.0464
0.0130
0.0054
0.0000
building
0.0499
0.9034
0.0396
0.0054
0.0017
0.0000
low_veg
0.0511
0.0609
0.7655
0.1220
0.0005
0.0000
tree
0.0282
0.0035
0.1406
0.8276
0.0001
0.0000
car
0.3413
0.0286
0.0605
0.0040
0.5655
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.871
0.890
0.809
0.805
0.728
--
Recall/Completeness
0.897
0.903
0.765
0.828
0.566
--
F1
0.884
0.897
0.787
0.816
0.637
--

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_area38_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9244
0.0347
0.0324
0.0045
0.0039
0.0000
building
0.0428
0.9265
0.0266
0.0026
0.0015
0.0000
low_veg
0.0327
0.0592
0.7950
0.1127
0.0004
0.0000
tree
0.0132
0.0010
0.1139
0.8719
0.0000
0.0000
car
0.2459
0.0321
0.0525
0.0008
0.6688
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.910
0.904
0.853
0.833
0.758
--
Recall/Completeness
0.924
0.926
0.795
0.872
0.669
--
F1
0.917
0.915
0.823
0.852
0.711
--

Overall accuracy 0.878

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image