Detailled semantic labeling (2D) result


Name T. V. Duy
Affiliation Hanoi University of Science and Technology, Vietnam
Abbreviation BKHN_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
0.906
0.034
0.036
0.018
0.006
0.000
building
0.043
0.930
0.019
0.007
0.001
0.000
low_veg
0.070
0.026
0.759
0.144
0.000
0.000
tree
0.021
0.009
0.098
0.872
0.000
0.000
car
0.229
0.062
0.009
0.007
0.688
0.005
clutter
0.443
0.375
0.053
0.011
0.072
0.046
Precision/Correctness
0.868
0.920
0.812
0.838
0.777
0.721
Recall/Completeness
0.906
0.930
0.759
0.872
0.688
0.046
F1
0.887
0.925
0.785
0.855
0.729
0.086

Overall accuracy 0.862

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
0.933
0.026
0.029
0.009
0.003
0.000
building
0.036
0.946
0.013
0.004
0.001
0.000
low_veg
0.059
0.018
0.794
0.129
0.000
0.000
tree
0.010
0.005
0.083
0.901
0.000
0.000
car
0.151
0.071
0.006
0.004
0.763
0.006
clutter
0.417
0.402
0.053
0.005
0.074
0.049
Precision/Correctness
0.897
0.939
0.845
0.869
0.806
0.764
Recall/Completeness
0.933
0.946
0.794
0.901
0.763
0.049
F1
0.914
0.943
0.819
0.885
0.784
0.093

Overall accuracy 0.891
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9468
0.0130
0.0218
0.0111
0.0072
0.0000
building
0.0281
0.9496
0.0185
0.0038
0.0000
0.0000
low_veg
0.1079
0.0248
0.6913
0.1754
0.0006
0.0000
tree
0.0302
0.0107
0.1021
0.8563
0.0006
0.0002
car
0.2598
0.0154
0.0004
0.0045
0.7158
0.0041
clutter
0.5910
0.2037
0.0655
0.0224
0.0028
0.1147
Precision/Correctness
0.811
0.932
0.824
0.818
0.838
0.948
Recall/Completeness
0.947
0.950
0.691
0.856
0.716
0.115
F1
0.874
0.941
0.752
0.837
0.772
0.205

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_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9692
0.0087
0.0135
0.0030
0.0056
0.0000
building
0.0220
0.9666
0.0103
0.0011
0.0000
0.0000
low_veg
0.0936
0.0160
0.7213
0.1686
0.0005
0.0000
tree
0.0144
0.0074
0.0885
0.8894
0.0003
0.0001
car
0.1536
0.0168
0.0000
0.0032
0.8214
0.0050
clutter
0.6036
0.2047
0.0663
0.0069
0.0027
0.1157
Precision/Correctness
0.842
0.950
0.856
0.842
0.858
0.964
Recall/Completeness
0.969
0.967
0.721
0.889
0.821
0.116
F1
0.901
0.958
0.783
0.865
0.839
0.207

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: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9193
0.0580
0.0101
0.0056
0.0071
0.0000
building
0.0541
0.9333
0.0101
0.0016
0.0007
0.0000
low_veg
0.1915
0.0534
0.4594
0.2940
0.0016
0.0000
tree
0.0559
0.0187
0.0790
0.8462
0.0002
0.0000
car
0.3608
0.0322
0.0115
0.0010
0.5944
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.851
0.962
0.619
0.721
0.771
--
Recall/Completeness
0.919
0.933
0.459
0.846
0.594
--
F1
0.884
0.947
0.527
0.779
0.671
--

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_area4_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9479
0.0367
0.0079
0.0025
0.0051
0.0000
building
0.0414
0.9483
0.0090
0.0006
0.0007
0.0000
low_veg
0.1587
0.0252
0.4931
0.3217
0.0013
0.0000
tree
0.0283
0.0084
0.0754
0.8878
0.0000
0.0000
car
0.2857
0.0266
0.0103
0.0001
0.6774
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.885
0.979
0.639
0.749
0.794
--
Recall/Completeness
0.948
0.948
0.493
0.888
0.677
--
F1
0.915
0.963
0.556
0.813
0.731
--

Overall accuracy 0.923

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
0.8998
0.0617
0.0252
0.0081
0.0048
0.0004
building
0.0424
0.9428
0.0109
0.0035
0.0003
0.0000
low_veg
0.1029
0.0386
0.7242
0.1340
0.0002
0.0000
tree
0.0232
0.0259
0.1048
0.8459
0.0002
0.0001
car
0.2565
0.0096
0.0019
0.0019
0.7299
0.0003
clutter
--
--
--
--
--
--
Precision/Correctness
0.865
0.919
0.657
0.933
0.896
--
Recall/Completeness
0.900
0.943
0.724
0.846
0.730
--
F1
0.882
0.931
0.689
0.887
0.804
--

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_area6_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9306
0.0473
0.0176
0.0023
0.0019
0.0003
building
0.0318
0.9600
0.0068
0.0013
0.0001
0.0000
low_veg
0.0831
0.0250
0.7730
0.1190
0.0000
0.0000
tree
0.0105
0.0246
0.0938
0.8710
0.0000
0.0000
car
0.1606
0.0091
0.0015
0.0005
0.8281
0.0002
clutter
--
--
--
--
--
--
Precision/Correctness
0.906
0.938
0.685
0.954
0.952
--
Recall/Completeness
0.931
0.960
0.773
0.871
0.828
--
F1
0.918
0.949
0.726
0.910
0.886
--

Overall accuracy 0.906

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
0.8809
0.0368
0.0640
0.0128
0.0056
0.0000
building
0.0260
0.9524
0.0158
0.0053
0.0005
0.0000
low_veg
0.0492
0.0160
0.8626
0.0717
0.0005
0.0000
tree
0.0249
0.0070
0.0750
0.8930
0.0002
0.0000
car
0.2487
0.0037
0.0183
0.0052
0.7236
0.0005
clutter
--
--
--
--
--
--
Precision/Correctness
0.915
0.931
0.802
0.917
0.860
--
Recall/Completeness
0.881
0.952
0.863
0.893
0.724
--
F1
0.897
0.941
0.831
0.905
0.786
--

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_area8_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9078
0.0309
0.0544
0.0040
0.0029
0.0000
building
0.0165
0.9728
0.0074
0.0028
0.0004
0.0000
low_veg
0.0341
0.0078
0.8988
0.0592
0.0001
0.0000
tree
0.0104
0.0033
0.0572
0.9290
0.0001
0.0000
car
0.1659
0.0018
0.0124
0.0036
0.8156
0.0007
clutter
--
--
--
--
--
--
Precision/Correctness
0.949
0.951
0.842
0.943
0.907
--
Recall/Completeness
0.908
0.973
0.899
0.929
0.816
--
F1
0.928
0.962
0.870
0.936
0.859
--

Overall accuracy 0.926

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
0.8710
0.0597
0.0440
0.0202
0.0048
0.0002
building
0.0159
0.9522
0.0179
0.0132
0.0007
0.0000
low_veg
0.0940
0.0265
0.7473
0.1316
0.0006
0.0000
tree
0.0163
0.0077
0.0723
0.9038
0.0000
0.0000
car
0.1877
0.0285
0.0104
0.0049
0.7686
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.929
0.886
0.786
0.846
0.722
--
Recall/Completeness
0.871
0.952
0.747
0.904
0.769
--
F1
0.899
0.918
0.766
0.874
0.745
--

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_area10_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9035
0.0479
0.0362
0.0088
0.0033
0.0003
building
0.0102
0.9670
0.0127
0.0096
0.0004
0.0000
low_veg
0.0925
0.0153
0.7904
0.1010
0.0007
0.0001
tree
0.0067
0.0037
0.0540
0.9356
0.0000
0.0000
car
0.1190
0.0319
0.0088
0.0007
0.8395
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.945
0.914
0.828
0.891
0.747
--
Recall/Completeness
0.904
0.967
0.790
0.936
0.840
--
F1
0.924
0.940
0.809
0.913
0.791
--

Overall accuracy 0.906

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
0.8950
0.0301
0.0436
0.0278
0.0034
0.0001
building
0.1433
0.8292
0.0217
0.0044
0.0010
0.0003
low_veg
0.0532
0.0250
0.7752
0.1460
0.0005
0.0001
tree
0.0120
0.0072
0.1266
0.8542
0.0000
0.0000
car
0.1396
0.0000
0.0075
0.0040
0.8489
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.726
0.918
0.797
0.870
0.837
--
Recall/Completeness
0.895
0.829
0.775
0.854
0.849
--
F1
0.802
0.871
0.786
0.862
0.843
--

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_area12_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9227
0.0274
0.0353
0.0142
0.0004
0.0000
building
0.1503
0.8344
0.0124
0.0015
0.0011
0.0003
low_veg
0.0508
0.0170
0.8087
0.1229
0.0004
0.0001
tree
0.0059
0.0034
0.1098
0.8809
0.0000
0.0000
car
0.0585
0.0000
0.0059
0.0011
0.9345
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.741
0.942
0.826
0.898
0.898
--
Recall/Completeness
0.923
0.834
0.809
0.881
0.934
--
F1
0.822
0.885
0.817
0.889
0.916
--

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_area14_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8605
0.0362
0.0600
0.0356
0.0074
0.0002
building
0.0057
0.9653
0.0213
0.0069
0.0006
0.0002
low_veg
0.0651
0.0582
0.7289
0.1468
0.0009
0.0000
tree
0.0230
0.0127
0.1254
0.8388
0.0000
0.0000
car
0.1258
0.0000
0.0007
0.0036
0.8698
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.885
0.861
0.757
0.857
0.530
--
Recall/Completeness
0.861
0.965
0.729
0.839
0.870
--
F1
0.873
0.910
0.743
0.848
0.659
--

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_area14_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8812
0.0322
0.0551
0.0247
0.0066
0.0002
building
0.0020
0.9838
0.0108
0.0026
0.0005
0.0002
low_veg
0.0597
0.0452
0.7604
0.1338
0.0009
0.0000
tree
0.0151
0.0067
0.1139
0.8643
0.0000
0.0000
car
0.0311
0.0000
0.0000
0.0006
0.9683
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.910
0.891
0.780
0.881
0.508
--
Recall/Completeness
0.881
0.984
0.760
0.864
0.968
--
F1
0.895
0.935
0.770
0.873
0.666
--

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_area16_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8444
0.0314
0.0719
0.0493
0.0031
0.0000
building
0.0193
0.9486
0.0227
0.0091
0.0002
0.0000
low_veg
0.0513
0.0176
0.8006
0.1291
0.0000
0.0012
tree
0.0282
0.0049
0.1471
0.8198
0.0000
0.0000
car
0.1404
0.0000
0.0458
0.0095
0.8042
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.816
0.934
0.774
0.863
0.776
--
Recall/Completeness
0.844
0.949
0.801
0.820
0.804
--
F1
0.830
0.941
0.787
0.841
0.790
--

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_area16_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8770
0.0274
0.0633
0.0307
0.0016
0.0000
building
0.0157
0.9715
0.0098
0.0030
0.0001
0.0000
low_veg
0.0490
0.0121
0.8200
0.1175
0.0000
0.0013
tree
0.0203
0.0018
0.1333
0.8446
0.0000
0.0000
car
0.0718
0.0000
0.0408
0.0019
0.8855
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.841
0.954
0.801
0.886
0.843
--
Recall/Completeness
0.877
0.972
0.820
0.845
0.886
--
F1
0.859
0.963
0.811
0.865
0.863
--

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
0.8517
0.0415
0.0621
0.0391
0.0056
0.0000
building
0.0150
0.9543
0.0268
0.0039
0.0000
0.0000
low_veg
0.0632
0.0185
0.7973
0.1207
0.0003
0.0001
tree
0.0104
0.0022
0.0692
0.9182
0.0000
0.0000
car
0.1131
0.0017
0.0405
0.0060
0.8386
0.0000
clutter
0.0633
0.7408
0.1944
0.0015
0.0000
0.0000
Precision/Correctness
0.890
0.826
0.753
0.922
0.742
0.000
Recall/Completeness
0.852
0.954
0.797
0.918
0.839
0.000
F1
0.871
0.886
0.774
0.920
0.788
-nan

Overall accuracy 0.862

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
0.8828
0.0349
0.0552
0.0238
0.0032
0.0000
building
0.0124
0.9668
0.0198
0.0010
0.0000
0.0000
low_veg
0.0574
0.0091
0.8395
0.0937
0.0002
0.0001
tree
0.0045
0.0008
0.0552
0.9395
0.0000
0.0000
car
0.0518
0.0011
0.0358
0.0007
0.9106
0.0000
clutter
0.0582
0.7602
0.1809
0.0007
0.0000
0.0000
Precision/Correctness
0.916
0.841
0.784
0.946
0.795
0.000
Recall/Completeness
0.883
0.967
0.840
0.939
0.911
0.000
F1
0.899
0.899
0.811
0.943
0.849
-nan

Overall accuracy 0.888

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
0.8849
0.0281
0.0437
0.0366
0.0068
0.0000
building
0.0183
0.9620
0.0112
0.0083
0.0001
0.0000
low_veg
0.0937
0.0330
0.7220
0.1512
0.0001
0.0000
tree
0.0173
0.0037
0.0553
0.9233
0.0003
0.0000
car
0.2533
0.0203
0.0166
0.0128
0.6970
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.904
0.910
0.820
0.859
0.768
--
Recall/Completeness
0.885
0.962
0.722
0.923
0.697
--
F1
0.894
0.935
0.768
0.890
0.731
--

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_area22_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9198
0.0216
0.0367
0.0180
0.0039
0.0000
building
0.0132
0.9789
0.0046
0.0033
0.0000
0.0000
low_veg
0.0919
0.0213
0.7685
0.1183
0.0001
0.0000
tree
0.0070
0.0011
0.0411
0.9507
0.0001
0.0000
car
0.1866
0.0231
0.0140
0.0030
0.7733
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.926
0.938
0.859
0.902
0.828
--
Recall/Completeness
0.920
0.979
0.768
0.951
0.773
--
F1
0.923
0.958
0.811
0.926
0.800
--

Overall accuracy 0.909

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
0.8293
0.0353
0.0870
0.0440
0.0043
0.0000
building
0.0500
0.9027
0.0325
0.0147
0.0000
0.0000
low_veg
0.0281
0.0342
0.8455
0.0921
0.0001
0.0000
tree
0.0181
0.0068
0.1416
0.8334
0.0000
0.0000
car
0.1885
0.0000
0.0114
0.0031
0.7969
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.821
0.890
0.864
0.818
0.817
--
Recall/Completeness
0.829
0.903
0.846
0.833
0.797
--
F1
0.825
0.897
0.855
0.826
0.807
--

Overall accuracy 0.851

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
0.8605
0.0263
0.0781
0.0323
0.0028
0.0000
building
0.0481
0.9181
0.0226
0.0112
0.0000
0.0000
low_veg
0.0252
0.0312
0.8630
0.0805
0.0001
0.0000
tree
0.0116
0.0039
0.1222
0.8623
0.0000
0.0000
car
0.0942
0.0000
0.0072
0.0000
0.8986
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.843
0.908
0.887
0.842
0.846
--
Recall/Completeness
0.861
0.918
0.863
0.862
0.899
--
F1
0.852
0.913
0.875
0.852
0.871
--

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_area27_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9376
0.0233
0.0217
0.0091
0.0082
0.0001
building
0.0598
0.9189
0.0157
0.0054
0.0003
0.0000
low_veg
0.1006
0.0253
0.6680
0.2059
0.0003
0.0000
tree
0.0114
0.0059
0.0348
0.9478
0.0002
0.0000
car
0.2622
0.0168
0.0025
0.0083
0.7049
0.0052
clutter
0.7433
0.0908
0.0924
0.0120
0.0615
0.0000
Precision/Correctness
0.852
0.959
0.890
0.677
0.887
0.000
Recall/Completeness
0.938
0.919
0.668
0.948
0.705
0.000
F1
0.893
0.938
0.763
0.790
0.785
-nan

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_area27_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9642
0.0139
0.0157
0.0035
0.0027
0.0000
building
0.0483
0.9390
0.0103
0.0022
0.0002
0.0000
low_veg
0.0848
0.0131
0.7102
0.1919
0.0000
0.0000
tree
0.0058
0.0022
0.0215
0.9706
0.0000
0.0000
car
0.1760
0.0166
0.0012
0.0058
0.7949
0.0054
clutter
0.7813
0.0730
0.0744
0.0065
0.0649
0.0000
Precision/Correctness
0.884
0.978
0.924
0.712
0.949
0.000
Recall/Completeness
0.964
0.939
0.710
0.971
0.795
0.000
F1
0.923
0.958
0.803
0.821
0.865
-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
0.9374
0.0219
0.0189
0.0150
0.0067
0.0002
building
0.0449
0.9381
0.0093
0.0073
0.0005
0.0000
low_veg
0.0953
0.0245
0.5725
0.3075
0.0002
0.0000
tree
0.0069
0.0112
0.0290
0.9528
0.0000
0.0000
car
0.2741
0.0058
0.0073
0.0104
0.6930
0.0094
clutter
0.5399
0.3046
0.0199
0.0155
0.0943
0.0258
Precision/Correctness
0.895
0.916
0.855
0.657
0.615
0.790
Recall/Completeness
0.937
0.938
0.573
0.953
0.693
0.026
F1
0.916
0.927
0.686
0.778
0.652
0.050

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_area29_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9576
0.0163
0.0142
0.0070
0.0048
0.0001
building
0.0399
0.9507
0.0050
0.0038
0.0006
0.0000
low_veg
0.0756
0.0107
0.6195
0.2941
0.0000
0.0000
tree
0.0029
0.0093
0.0228
0.9650
0.0000
0.0000
car
0.2059
0.0023
0.0073
0.0073
0.7670
0.0102
clutter
0.5298
0.3187
0.0186
0.0067
0.0978
0.0284
Precision/Correctness
0.915
0.937
0.889
0.697
0.617
0.836
Recall/Completeness
0.958
0.951
0.620
0.965
0.767
0.028
F1
0.936
0.944
0.730
0.810
0.684
0.055

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_area31_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9585
0.0154
0.0156
0.0049
0.0051
0.0004
building
0.0676
0.9132
0.0135
0.0025
0.0027
0.0005
low_veg
0.0586
0.0051
0.9040
0.0320
0.0004
0.0000
tree
0.0357
0.0049
0.0912
0.8674
0.0005
0.0002
car
0.1394
0.2951
0.0072
0.0086
0.5317
0.0180
clutter
0.3880
0.4618
0.0290
0.0169
0.0920
0.0124
Precision/Correctness
0.883
0.883
0.863
0.923
0.763
0.299
Recall/Completeness
0.958
0.913
0.904
0.867
0.532
0.012
F1
0.919
0.898
0.883
0.894
0.627
0.024

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_area31_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9735
0.0099
0.0131
0.0010
0.0022
0.0002
building
0.0580
0.9306
0.0085
0.0004
0.0022
0.0004
low_veg
0.0367
0.0025
0.9363
0.0244
0.0000
0.0000
tree
0.0131
0.0018
0.0764
0.9085
0.0000
0.0001
car
0.0825
0.3277
0.0019
0.0034
0.5654
0.0192
clutter
0.3298
0.5167
0.0294
0.0123
0.0978
0.0139
Precision/Correctness
0.913
0.902
0.892
0.956
0.785
0.360
Recall/Completeness
0.974
0.931
0.936
0.909
0.565
0.014
F1
0.942
0.916
0.914
0.931
0.657
0.027

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_area33_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9666
0.0212
0.0042
0.0039
0.0037
0.0004
building
0.0936
0.8343
0.0441
0.0234
0.0045
0.0000
low_veg
0.0969
0.0127
0.7089
0.1808
0.0007
0.0000
tree
0.0434
0.0070
0.1326
0.8168
0.0001
0.0000
car
0.2975
0.0075
0.0013
0.0064
0.6872
0.0002
clutter
0.5190
0.2783
0.0065
0.0008
0.1214
0.0739
Precision/Correctness
0.826
0.903
0.792
0.703
0.483
0.954
Recall/Completeness
0.967
0.834
0.709
0.817
0.687
0.074
F1
0.891
0.867
0.748
0.755
0.567
0.137

Overall accuracy 0.821

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
0.9760
0.0185
0.0019
0.0010
0.0024
0.0002
building
0.0880
0.8427
0.0426
0.0224
0.0042
0.0000
low_veg
0.0626
0.0045
0.7425
0.1901
0.0004
0.0000
tree
0.0206
0.0022
0.1219
0.8552
0.0000
0.0000
car
0.2225
0.0087
0.0001
0.0053
0.7632
0.0002
clutter
0.4823
0.3009
0.0053
0.0006
0.1309
0.0801
Precision/Correctness
0.854
0.916
0.810
0.709
0.463
0.978
Recall/Completeness
0.976
0.843
0.742
0.855
0.763
0.080
F1
0.911
0.878
0.775
0.775
0.576
0.148

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_area35_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8620
0.0418
0.0702
0.0231
0.0023
0.0005
building
0.0236
0.9456
0.0238
0.0063
0.0007
0.0000
low_veg
0.0401
0.0137
0.7052
0.2407
0.0002
0.0000
tree
0.0266
0.0053
0.0893
0.8786
0.0001
0.0000
car
0.2245
0.0151
0.0017
0.0119
0.7384
0.0085
clutter
--
--
--
--
--
--
Precision/Correctness
0.899
0.943
0.796
0.754
0.866
--
Recall/Completeness
0.862
0.946
0.705
0.879
0.738
--
F1
0.880
0.944
0.748
0.811
0.797
--

Overall accuracy 0.848

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
0.9068
0.0359
0.0499
0.0063
0.0006
0.0006
building
0.0148
0.9695
0.0135
0.0015
0.0006
0.0000
low_veg
0.0268
0.0065
0.7351
0.2315
0.0001
0.0000
tree
0.0077
0.0011
0.0675
0.9237
0.0000
0.0000
car
0.1664
0.0124
0.0001
0.0044
0.8051
0.0116
clutter
--
--
--
--
--
--
Precision/Correctness
0.943
0.962
0.851
0.782
0.930
--
Recall/Completeness
0.907
0.970
0.735
0.924
0.805
--
F1
0.925
0.966
0.789
0.847
0.863
--

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_area38_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9045
0.0354
0.0387
0.0167
0.0048
0.0000
building
0.0150
0.9473
0.0290
0.0070
0.0015
0.0001
low_veg
0.0700
0.0259
0.8062
0.0975
0.0004
0.0000
tree
0.0187
0.0103
0.0934
0.8774
0.0001
0.0000
car
0.1629
0.0624
0.0249
0.0125
0.7370
0.0004
clutter
--
--
--
--
--
--
Precision/Correctness
0.894
0.925
0.862
0.836
0.796
--
Recall/Completeness
0.904
0.947
0.806
0.877
0.737
--
F1
0.899
0.936
0.833
0.856
0.765
--

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_area38_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9327
0.0320
0.0273
0.0056
0.0024
0.0000
building
0.0091
0.9677
0.0190
0.0028
0.0013
0.0001
low_veg
0.0577
0.0199
0.8437
0.0785
0.0002
0.0000
tree
0.0069
0.0075
0.0752
0.9104
0.0001
0.0000
car
0.0952
0.0730
0.0176
0.0056
0.8083
0.0004
clutter
--
--
--
--
--
--
Precision/Correctness
0.925
0.941
0.897
0.878
0.846
--
Recall/Completeness
0.933
0.968
0.844
0.910
0.808
--
F1
0.929
0.954
0.870
0.894
0.827
--

Overall accuracy 0.912

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image