Detailled semantic labeling (2D) result


Name M. N. Duc and S. D. Viet
Affiliation Hanoi University of Science and Technology, Vietnam
Abbreviation BKHN11
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
0.915
0.025
0.040
0.016
0.004
0.000
building
0.038
0.940
0.016
0.006
0.000
0.000
low_veg
0.052
0.019
0.794
0.135
0.000
0.000
tree
0.021
0.005
0.086
0.888
0.000
0.000
car
0.183
0.029
0.005
0.004
0.778
0.001
clutter
0.448
0.169
0.035
0.006
0.029
0.313
Precision/Correctness
0.888
0.946
0.830
0.851
0.858
0.947
Recall/Completeness
0.915
0.940
0.794
0.888
0.778
0.313
F1
0.901
0.943
0.812
0.869
0.816
0.471

Overall accuracy 0.882

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
0.938
0.019
0.033
0.007
0.002
0.000
building
0.030
0.957
0.009
0.003
0.000
0.000
low_veg
0.039
0.011
0.829
0.120
0.000
0.000
tree
0.010
0.002
0.070
0.919
0.000
0.000
car
0.078
0.033
0.002
0.002
0.884
0.001
clutter
0.420
0.175
0.033
0.001
0.029
0.341
Precision/Correctness
0.920
0.963
0.864
0.880
0.888
0.961
Recall/Completeness
0.938
0.957
0.829
0.919
0.884
0.341
F1
0.929
0.960
0.846
0.899
0.886
0.503

Overall accuracy 0.910
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9590
0.0077
0.0175
0.0108
0.0050
0.0000
building
0.0291
0.9510
0.0169
0.0028
0.0002
0.0000
low_veg
0.0741
0.0205
0.7485
0.1569
0.0000
0.0000
tree
0.0293
0.0051
0.0894
0.8748
0.0003
0.0012
car
0.2108
0.0007
0.0004
0.0010
0.7872
0.0000
clutter
0.0040
0.0007
0.0000
0.0122
0.0000
0.9831
Precision/Correctness
0.872
0.964
0.858
0.837
0.899
0.984
Recall/Completeness
0.959
0.951
0.748
0.875
0.787
0.983
F1
0.913
0.957
0.799
0.856
0.839
0.983

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_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9801
0.0045
0.0090
0.0029
0.0034
0.0000
building
0.0210
0.9687
0.0097
0.0005
0.0002
0.0000
low_veg
0.0559
0.0127
0.7811
0.1503
0.0000
0.0000
tree
0.0139
0.0021
0.0755
0.9080
0.0002
0.0004
car
0.0868
0.0000
0.0000
0.0001
0.9131
0.0000
clutter
0.0040
0.0004
0.0000
0.0014
0.0000
0.9941
Precision/Correctness
0.913
0.980
0.889
0.860
0.921
0.995
Recall/Completeness
0.980
0.969
0.781
0.908
0.913
0.994
F1
0.945
0.974
0.832
0.883
0.917
0.994

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_area4_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9396
0.0418
0.0118
0.0038
0.0030
0.0000
building
0.0462
0.9448
0.0072
0.0018
0.0000
0.0000
low_veg
0.1554
0.0393
0.5228
0.2815
0.0011
0.0000
tree
0.0567
0.0136
0.0304
0.8992
0.0000
0.0000
car
0.2425
0.0040
0.0007
0.0019
0.7509
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.875
0.973
0.723
0.746
0.921
--
Recall/Completeness
0.940
0.945
0.523
0.899
0.751
--
F1
0.906
0.959
0.607
0.815
0.827
--

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_area4_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9639
0.0254
0.0087
0.0011
0.0010
0.0000
building
0.0323
0.9607
0.0062
0.0007
0.0000
0.0000
low_veg
0.1185
0.0120
0.5558
0.3128
0.0008
0.0000
tree
0.0281
0.0051
0.0232
0.9436
0.0000
0.0000
car
0.1161
0.0016
0.0001
0.0006
0.8817
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.912
0.986
0.755
0.769
0.968
--
Recall/Completeness
0.964
0.961
0.556
0.944
0.882
--
F1
0.937
0.973
0.640
0.848
0.923
--

Overall accuracy 0.943

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
0.9122
0.0421
0.0321
0.0084
0.0051
0.0000
building
0.0384
0.9463
0.0121
0.0031
0.0001
0.0000
low_veg
0.0878
0.0282
0.7249
0.1588
0.0003
0.0000
tree
0.0176
0.0033
0.0521
0.9269
0.0002
0.0000
car
0.1981
0.0026
0.0003
0.0016
0.7974
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.884
0.955
0.740
0.930
0.902
--
Recall/Completeness
0.912
0.946
0.725
0.927
0.797
--
F1
0.898
0.951
0.732
0.928
0.846
--

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_area6_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9428
0.0290
0.0236
0.0019
0.0028
0.0000
building
0.0289
0.9630
0.0073
0.0008
0.0000
0.0000
low_veg
0.0720
0.0146
0.7741
0.1393
0.0000
0.0000
tree
0.0072
0.0009
0.0405
0.9514
0.0000
0.0000
car
0.0941
0.0000
0.0001
0.0001
0.9057
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.921
0.974
0.787
0.952
0.941
--
Recall/Completeness
0.943
0.963
0.774
0.951
0.906
--
F1
0.932
0.968
0.780
0.952
0.923
--

Overall accuracy 0.935

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
0.8917
0.0256
0.0708
0.0088
0.0031
0.0000
building
0.0250
0.9547
0.0159
0.0041
0.0004
0.0000
low_veg
0.0421
0.0118
0.9033
0.0426
0.0002
0.0000
tree
0.0251
0.0049
0.0772
0.8928
0.0000
0.0000
car
0.2371
0.0035
0.0139
0.0036
0.7419
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.921
0.950
0.799
0.946
0.919
--
Recall/Completeness
0.892
0.955
0.903
0.893
0.742
--
F1
0.906
0.952
0.848
0.919
0.821
--

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: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9147
0.0203
0.0613
0.0022
0.0015
0.0000
building
0.0154
0.9753
0.0075
0.0015
0.0004
0.0000
low_veg
0.0255
0.0050
0.9380
0.0315
0.0000
0.0000
tree
0.0098
0.0018
0.0565
0.9318
0.0000
0.0000
car
0.1162
0.0028
0.0070
0.0021
0.8718
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.958
0.968
0.840
0.969
0.953
--
Recall/Completeness
0.915
0.975
0.938
0.932
0.872
--
F1
0.936
0.972
0.886
0.950
0.910
--

Overall accuracy 0.937

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
0.8505
0.0491
0.0781
0.0185
0.0030
0.0008
building
0.0184
0.9513
0.0182
0.0108
0.0009
0.0005
low_veg
0.0733
0.0227
0.7606
0.1429
0.0003
0.0002
tree
0.0144
0.0073
0.0820
0.8963
0.0000
0.0000
car
0.1662
0.0164
0.0076
0.0009
0.8089
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.937
0.903
0.726
0.842
0.806
--
Recall/Completeness
0.851
0.951
0.761
0.896
0.809
--
F1
0.892
0.927
0.743
0.868
0.807
--

Overall accuracy 0.868

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
0.8795
0.0374
0.0732
0.0075
0.0017
0.0008
building
0.0134
0.9634
0.0142
0.0081
0.0006
0.0004
low_veg
0.0690
0.0108
0.8054
0.1142
0.0003
0.0003
tree
0.0054
0.0033
0.0651
0.9262
0.0000
0.0000
car
0.0759
0.0152
0.0040
0.0000
0.9048
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.954
0.932
0.753
0.885
0.853
--
Recall/Completeness
0.879
0.963
0.805
0.926
0.905
--
F1
0.915
0.947
0.778
0.905
0.878
--

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_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8914
0.0332
0.0418
0.0309
0.0027
0.0000
building
0.1668
0.8146
0.0134
0.0047
0.0005
0.0000
low_veg
0.0373
0.0215
0.7711
0.1698
0.0001
0.0001
tree
0.0099
0.0060
0.1014
0.8826
0.0000
0.0000
car
0.1510
0.0000
0.0006
0.0008
0.8475
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.729
0.922
0.829
0.857
0.889
--
Recall/Completeness
0.891
0.815
0.771
0.883
0.848
--
F1
0.802
0.865
0.799
0.870
0.868
--

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
0.9183
0.0310
0.0343
0.0158
0.0006
0.0000
building
0.1745
0.8178
0.0061
0.0011
0.0006
0.0000
low_veg
0.0339
0.0139
0.8042
0.1479
0.0001
0.0001
tree
0.0043
0.0026
0.0840
0.9090
0.0000
0.0000
car
0.0483
0.0000
0.0000
0.0000
0.9517
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.743
0.945
0.859
0.884
0.942
--
Recall/Completeness
0.918
0.818
0.804
0.909
0.952
--
F1
0.821
0.877
0.831
0.896
0.947
--

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_area14_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8247
0.0329
0.0995
0.0363
0.0065
0.0000
building
0.0073
0.9683
0.0192
0.0052
0.0000
0.0000
low_veg
0.0588
0.0388
0.7525
0.1494
0.0006
0.0000
tree
0.0222
0.0102
0.1175
0.8500
0.0000
0.0000
car
0.1144
0.0000
0.0000
0.0020
0.8837
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.888
0.891
0.745
0.858
0.589
--
Recall/Completeness
0.825
0.968
0.752
0.850
0.884
--
F1
0.855
0.928
0.749
0.854
0.707
--

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_area14_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8440
0.0286
0.0963
0.0253
0.0058
0.0000
building
0.0034
0.9863
0.0090
0.0014
0.0000
0.0000
low_veg
0.0533
0.0252
0.7835
0.1375
0.0006
0.0000
tree
0.0148
0.0046
0.1042
0.8764
0.0000
0.0000
car
0.0220
0.0000
0.0000
0.0000
0.9780
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.913
0.922
0.767
0.880
0.566
--
Recall/Completeness
0.844
0.986
0.784
0.876
0.978
--
F1
0.877
0.953
0.775
0.878
0.717
--

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_area16_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8439
0.0214
0.0822
0.0495
0.0032
0.0000
building
0.0190
0.9470
0.0205
0.0134
0.0001
0.0000
low_veg
0.0171
0.0128
0.8373
0.1318
0.0000
0.0010
tree
0.0235
0.0036
0.0920
0.8809
0.0000
0.0000
car
0.1163
0.0004
0.0002
0.0012
0.8820
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.883
0.952
0.832
0.868
0.794
--
Recall/Completeness
0.844
0.947
0.837
0.881
0.882
--
F1
0.863
0.950
0.835
0.874
0.836
--

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_area16_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8774
0.0179
0.0732
0.0299
0.0016
0.0000
building
0.0155
0.9715
0.0078
0.0052
0.0000
0.0000
low_veg
0.0134
0.0080
0.8613
0.1163
0.0000
0.0011
tree
0.0158
0.0010
0.0780
0.9053
0.0000
0.0000
car
0.0382
0.0000
0.0000
0.0000
0.9618
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.913
0.970
0.862
0.893
0.859
--
Recall/Completeness
0.877
0.972
0.861
0.905
0.962
--
F1
0.895
0.971
0.861
0.899
0.907
--

Overall accuracy 0.900

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
0.8743
0.0256
0.0543
0.0407
0.0050
0.0000
building
0.0132
0.9621
0.0185
0.0062
0.0000
0.0000
low_veg
0.0515
0.0141
0.7533
0.1807
0.0002
0.0000
tree
0.0081
0.0011
0.0477
0.9432
0.0000
0.0000
car
0.1238
0.0013
0.0320
0.0123
0.8306
0.0000
clutter
0.6288
0.2161
0.1541
0.0009
0.0000
0.0000
Precision/Correctness
0.842
0.917
0.794
0.897
0.764
0.000
Recall/Completeness
0.874
0.962
0.753
0.943
0.831
0.000
F1
0.858
0.939
0.773
0.920
0.796
-nan

Overall accuracy 0.870

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area20_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9037
0.0198
0.0499
0.0235
0.0031
0.0000
building
0.0109
0.9745
0.0129
0.0017
0.0000
0.0000
low_veg
0.0438
0.0051
0.7995
0.1513
0.0003
0.0000
tree
0.0031
0.0002
0.0362
0.9605
0.0000
0.0000
car
0.0671
0.0020
0.0224
0.0053
0.9033
0.0000
clutter
0.6345
0.2145
0.1509
0.0002
0.0000
0.0000
Precision/Correctness
0.861
0.936
0.824
0.924
0.798
0.000
Recall/Completeness
0.904
0.974
0.800
0.961
0.903
0.000
F1
0.882
0.955
0.811
0.942
0.847
-nan

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_area22_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9054
0.0193
0.0383
0.0313
0.0057
0.0000
building
0.0246
0.9568
0.0126
0.0059
0.0001
0.0000
low_veg
0.0883
0.0319
0.7418
0.1375
0.0005
0.0000
tree
0.0211
0.0033
0.0506
0.9248
0.0001
0.0000
car
0.1886
0.0025
0.0094
0.0093
0.7903
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.905
0.926
0.837
0.873
0.814
--
Recall/Completeness
0.905
0.957
0.742
0.925
0.790
--
F1
0.905
0.941
0.786
0.898
0.802
--

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_area22_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9356
0.0139
0.0315
0.0155
0.0035
0.0000
building
0.0187
0.9740
0.0052
0.0021
0.0000
0.0000
low_veg
0.0841
0.0219
0.7861
0.1075
0.0004
0.0000
tree
0.0087
0.0009
0.0355
0.9549
0.0000
0.0000
car
0.0866
0.0016
0.0031
0.0029
0.9057
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.929
0.951
0.878
0.912
0.856
--
Recall/Completeness
0.936
0.974
0.786
0.955
0.906
--
F1
0.933
0.963
0.829
0.933
0.880
--

Overall accuracy 0.919

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
0.8241
0.0301
0.1050
0.0357
0.0051
0.0000
building
0.0458
0.8939
0.0428
0.0175
0.0000
0.0000
low_veg
0.0192
0.0204
0.8868
0.0734
0.0003
0.0000
tree
0.0165
0.0058
0.1480
0.8297
0.0000
0.0000
car
0.1793
0.0000
0.0008
0.0037
0.8162
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.849
0.922
0.857
0.845
0.783
--
Recall/Completeness
0.824
0.894
0.887
0.830
0.816
--
F1
0.836
0.908
0.872
0.837
0.799
--

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_area24_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8527
0.0211
0.0969
0.0255
0.0038
0.0000
building
0.0431
0.9065
0.0359
0.0145
0.0000
0.0000
low_veg
0.0154
0.0161
0.9054
0.0628
0.0003
0.0000
tree
0.0100
0.0025
0.1265
0.8610
0.0000
0.0000
car
0.0709
0.0000
0.0000
0.0003
0.9288
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.876
0.943
0.879
0.868
0.794
--
Recall/Completeness
0.853
0.907
0.905
0.861
0.929
--
F1
0.864
0.925
0.892
0.864
0.856
--

Overall accuracy 0.887

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area27_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9471
0.0218
0.0168
0.0071
0.0071
0.0000
building
0.0547
0.9290
0.0122
0.0038
0.0003
0.0000
low_veg
0.0815
0.0212
0.7093
0.1877
0.0002
0.0000
tree
0.0120
0.0048
0.0558
0.9271
0.0002
0.0000
car
0.1903
0.0027
0.0033
0.0050
0.7984
0.0002
clutter
0.6151
0.0822
0.1812
0.0063
0.1079
0.0072
Precision/Correctness
0.873
0.965
0.898
0.696
0.906
0.564
Recall/Completeness
0.947
0.929
0.709
0.927
0.798
0.007
F1
0.909
0.946
0.792
0.795
0.849
0.014

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_area27_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9726
0.0130
0.0098
0.0025
0.0021
0.0000
building
0.0435
0.9476
0.0074
0.0014
0.0002
0.0000
low_veg
0.0637
0.0097
0.7492
0.1773
0.0001
0.0000
tree
0.0052
0.0010
0.0370
0.9568
0.0000
0.0000
car
0.0846
0.0006
0.0016
0.0037
0.9091
0.0003
clutter
0.6220
0.0786
0.1636
0.0030
0.1226
0.0101
Precision/Correctness
0.907
0.982
0.935
0.728
0.957
0.630
Recall/Completeness
0.973
0.948
0.749
0.957
0.909
0.010
F1
0.939
0.965
0.832
0.827
0.932
0.020

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_area29_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9457
0.0134
0.0231
0.0120
0.0059
0.0000
building
0.0208
0.9627
0.0106
0.0059
0.0001
0.0000
low_veg
0.0560
0.0177
0.6544
0.2712
0.0006
0.0000
tree
0.0048
0.0036
0.0229
0.9687
0.0000
0.0000
car
0.1820
0.0017
0.0021
0.0097
0.7997
0.0048
clutter
0.5853
0.3174
0.0266
0.0112
0.0494
0.0102
Precision/Correctness
0.921
0.935
0.859
0.692
0.724
0.816
Recall/Completeness
0.946
0.963
0.654
0.969
0.800
0.010
F1
0.933
0.949
0.743
0.807
0.760
0.020

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_area29_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9662
0.0076
0.0167
0.0049
0.0046
0.0000
building
0.0158
0.9765
0.0051
0.0026
0.0001
0.0000
low_veg
0.0344
0.0062
0.7006
0.2584
0.0005
0.0000
tree
0.0011
0.0020
0.0150
0.9820
0.0000
0.0000
car
0.0829
0.0004
0.0016
0.0073
0.9018
0.0061
clutter
0.5780
0.3331
0.0205
0.0038
0.0523
0.0122
Precision/Correctness
0.942
0.954
0.899
0.731
0.725
0.841
Recall/Completeness
0.966
0.976
0.701
0.982
0.902
0.012
F1
0.954
0.965
0.787
0.838
0.803
0.024

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_area31_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9775
0.0059
0.0091
0.0029
0.0042
0.0004
building
0.0353
0.9495
0.0111
0.0020
0.0021
0.0000
low_veg
0.0303
0.0011
0.9333
0.0345
0.0003
0.0004
tree
0.0384
0.0024
0.0966
0.8622
0.0004
0.0000
car
0.1328
0.1561
0.0045
0.0037
0.7026
0.0003
clutter
0.5043
0.2124
0.0144
0.0064
0.0279
0.2346
Precision/Correctness
0.904
0.944
0.884
0.932
0.887
0.971
Recall/Completeness
0.977
0.950
0.933
0.862
0.703
0.235
F1
0.939
0.947
0.908
0.896
0.784
0.378

Overall accuracy 0.915

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area31_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9869
0.0040
0.0067
0.0003
0.0020
0.0001
building
0.0222
0.9703
0.0054
0.0002
0.0018
0.0000
low_veg
0.0125
0.0004
0.9585
0.0287
0.0000
0.0000
tree
0.0136
0.0003
0.0771
0.9090
0.0000
0.0000
car
0.0460
0.1760
0.0010
0.0006
0.7762
0.0004
clutter
0.4558
0.2390
0.0104
0.0013
0.0301
0.2635
Precision/Correctness
0.939
0.953
0.917
0.956
0.909
0.993
Recall/Completeness
0.987
0.970
0.958
0.909
0.776
0.263
F1
0.962
0.962
0.937
0.932
0.837
0.416

Overall accuracy 0.941

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
0.9847
0.0047
0.0046
0.0028
0.0023
0.0010
building
0.0397
0.9202
0.0152
0.0222
0.0014
0.0014
low_veg
0.0712
0.0090
0.8191
0.1001
0.0006
0.0000
tree
0.0494
0.0043
0.1206
0.8257
0.0000
0.0000
car
0.1935
0.0012
0.0018
0.0011
0.7967
0.0057
clutter
0.4563
0.1120
0.0016
0.0008
0.0422
0.3872
Precision/Correctness
0.874
0.965
0.870
0.790
0.736
0.960
Recall/Completeness
0.985
0.920
0.819
0.826
0.797
0.387
F1
0.926
0.942
0.844
0.808
0.765
0.552

Overall accuracy 0.889

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
0.9939
0.0025
0.0015
0.0006
0.0013
0.0002
building
0.0305
0.9336
0.0124
0.0209
0.0014
0.0012
low_veg
0.0390
0.0026
0.8551
0.1027
0.0007
0.0000
tree
0.0226
0.0016
0.1098
0.8660
0.0000
0.0000
car
0.0830
0.0015
0.0000
0.0001
0.9097
0.0058
clutter
0.4155
0.1191
0.0004
0.0001
0.0452
0.4196
Precision/Correctness
0.908
0.974
0.893
0.801
0.733
0.977
Recall/Completeness
0.994
0.934
0.855
0.866
0.910
0.420
F1
0.949
0.953
0.873
0.832
0.812
0.587

Overall accuracy 0.912

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
0.8948
0.0342
0.0553
0.0148
0.0010
0.0000
building
0.0349
0.9426
0.0163
0.0055
0.0008
0.0000
low_veg
0.0536
0.0100
0.7248
0.2115
0.0001
0.0000
tree
0.0310
0.0045
0.1122
0.8522
0.0001
0.0000
car
0.2004
0.0211
0.0013
0.0046
0.7726
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.877
0.953
0.802
0.776
0.922
--
Recall/Completeness
0.895
0.943
0.725
0.852
0.773
--
F1
0.886
0.948
0.761
0.812
0.841
--

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_area35_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9283
0.0316
0.0372
0.0027
0.0001
0.0000
building
0.0213
0.9693
0.0075
0.0012
0.0007
0.0000
low_veg
0.0357
0.0048
0.7528
0.2066
0.0000
0.0000
tree
0.0101
0.0009
0.0846
0.9044
0.0000
0.0000
car
0.0731
0.0283
0.0001
0.0006
0.8979
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.929
0.967
0.858
0.800
0.956
--
Recall/Completeness
0.928
0.969
0.753
0.904
0.898
--
F1
0.929
0.968
0.802
0.849
0.926
--

Overall accuracy 0.892

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
0.9140
0.0310
0.0380
0.0123
0.0035
0.0011
building
0.0204
0.9490
0.0242
0.0053
0.0011
0.0000
low_veg
0.0388
0.0127
0.8675
0.0807
0.0003
0.0000
tree
0.0206
0.0040
0.0994
0.8758
0.0002
0.0000
car
0.1598
0.0187
0.0119
0.0053
0.8043
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.919
0.949
0.871
0.862
0.852
--
Recall/Completeness
0.914
0.949
0.867
0.876
0.804
--
F1
0.916
0.949
0.869
0.869
0.828
--

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_area38_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9386
0.0294
0.0253
0.0037
0.0019
0.0012
building
0.0130
0.9718
0.0120
0.0023
0.0009
0.0000
low_veg
0.0252
0.0076
0.9020
0.0650
0.0002
0.0000
tree
0.0069
0.0014
0.0755
0.9161
0.0000
0.0000
car
0.0611
0.0205
0.0018
0.0010
0.9155
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.954
0.961
0.911
0.899
0.893
--
Recall/Completeness
0.939
0.972
0.902
0.916
0.916
--
F1
0.946
0.966
0.907
0.907
0.904
--

Overall accuracy 0.933

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image