Detailled semantic labeling (2D) result


Name D. Tran and T. Bui
Affiliation University​ ​of​ ​Engineering​ ​and​ ​Technology, Vietnam
Abbreviation VNU5
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
0.911
0.032
0.037
0.015
0.005
0.000
building
0.076
0.892
0.025
0.006
0.001
0.000
low_veg
0.068
0.024
0.762
0.145
0.000
0.000
tree
0.028
0.005
0.098
0.868
0.000
0.000
car
0.322
0.022
0.012
0.006
0.638
0.000
clutter
0.348
0.414
0.009
0.010
0.068
0.151
Precision/Correctness
0.841
0.924
0.808
0.841
0.766
0.928
Recall/Completeness
0.911
0.892
0.762
0.868
0.638
0.151
F1
0.874
0.907
0.784
0.854
0.696
0.260

Overall accuracy 0.854

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
0.935
0.025
0.030
0.007
0.003
0.000
building
0.067
0.911
0.018
0.003
0.001
0.000
low_veg
0.054
0.017
0.797
0.131
0.000
0.000
tree
0.015
0.002
0.082
0.901
0.000
0.000
car
0.227
0.022
0.008
0.002
0.740
0.000
clutter
0.314
0.437
0.006
0.004
0.070
0.169
Precision/Correctness
0.873
0.943
0.842
0.869
0.796
0.937
Recall/Completeness
0.935
0.911
0.797
0.901
0.740
0.169
F1
0.903
0.927
0.819
0.885
0.767
0.286

Overall accuracy 0.883
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9527
0.0112
0.0198
0.0107
0.0057
0.0000
building
0.0595
0.9104
0.0265
0.0031
0.0004
0.0000
low_veg
0.0987
0.0155
0.7163
0.1692
0.0003
0.0000
tree
0.0386
0.0026
0.1199
0.8378
0.0001
0.0011
car
0.3086
0.0049
0.0003
0.0016
0.6846
0.0000
clutter
0.0173
0.0023
0.0000
0.0188
0.0000
0.9616
Precision/Correctness
0.820
0.966
0.812
0.821
0.868
0.985
Recall/Completeness
0.953
0.910
0.716
0.838
0.685
0.962
F1
0.881
0.937
0.761
0.829
0.766
0.973

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
0.9742
0.0081
0.0110
0.0031
0.0035
0.0000
building
0.0491
0.9350
0.0146
0.0007
0.0005
0.0000
low_veg
0.0796
0.0084
0.7472
0.1644
0.0003
0.0000
tree
0.0198
0.0006
0.1070
0.8720
0.0000
0.0005
car
0.1888
0.0027
0.0000
0.0005
0.8079
0.0000
clutter
0.0162
0.0023
0.0000
0.0050
0.0000
0.9765
Precision/Correctness
0.863
0.981
0.845
0.843
0.901
0.993
Recall/Completeness
0.974
0.935
0.747
0.872
0.808
0.976
F1
0.915
0.958
0.793
0.857
0.852
0.985

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
0.9426
0.0370
0.0082
0.0048
0.0074
0.0000
building
0.0875
0.8990
0.0082
0.0020
0.0019
0.0014
low_veg
0.2146
0.0421
0.4636
0.2789
0.0008
0.0000
tree
0.0601
0.0132
0.0822
0.8444
0.0001
0.0000
car
0.4418
0.0142
0.0017
0.0022
0.5400
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.802
0.974
0.654
0.730
0.704
--
Recall/Completeness
0.943
0.899
0.464
0.844
0.540
--
F1
0.867
0.935
0.542
0.783
0.611
--

Overall accuracy 0.884

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
0.9692
0.0178
0.0054
0.0021
0.0054
0.0000
building
0.0741
0.9147
0.0070
0.0009
0.0019
0.0015
low_veg
0.1779
0.0127
0.5042
0.3049
0.0003
0.0000
tree
0.0286
0.0066
0.0769
0.8879
0.0000
0.0000
car
0.3740
0.0069
0.0006
0.0007
0.6178
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.831
0.989
0.685
0.758
0.719
--
Recall/Completeness
0.969
0.915
0.504
0.888
0.618
--
F1
0.895
0.950
0.581
0.818
0.665
--

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_area6_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9143
0.0404
0.0299
0.0091
0.0061
0.0000
building
0.0781
0.9055
0.0121
0.0035
0.0008
0.0000
low_veg
0.1170
0.0258
0.6911
0.1650
0.0011
0.0000
tree
0.0253
0.0030
0.0551
0.9163
0.0002
0.0000
car
0.3863
0.0125
0.0049
0.0012
0.5950
0.0001
clutter
--
--
--
--
--
--
Precision/Correctness
0.818
0.955
0.728
0.926
0.828
--
Recall/Completeness
0.914
0.906
0.691
0.916
0.595
--
F1
0.863
0.930
0.709
0.921
0.692
--

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_area6_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9454
0.0256
0.0226
0.0027
0.0038
0.0000
building
0.0682
0.9219
0.0078
0.0013
0.0008
0.0000
low_veg
0.0972
0.0133
0.7419
0.1469
0.0008
0.0000
tree
0.0129
0.0008
0.0431
0.9432
0.0000
0.0000
car
0.2935
0.0056
0.0041
0.0000
0.6967
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.854
0.975
0.773
0.948
0.868
--
Recall/Completeness
0.945
0.922
0.742
0.943
0.697
--
F1
0.897
0.948
0.757
0.945
0.773
--

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_area8_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9008
0.0243
0.0616
0.0088
0.0046
0.0000
building
0.0433
0.9298
0.0220
0.0041
0.0007
0.0001
low_veg
0.0610
0.0127
0.8732
0.0522
0.0009
0.0000
tree
0.0306
0.0056
0.0939
0.8696
0.0000
0.0002
car
0.3127
0.0108
0.0250
0.0052
0.6456
0.0007
clutter
--
--
--
--
--
--
Precision/Correctness
0.891
0.949
0.784
0.937
0.859
--
Recall/Completeness
0.901
0.930
0.873
0.870
0.646
--
F1
0.896
0.939
0.826
0.902
0.737
--

Overall accuracy 0.890

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
0.9265
0.0169
0.0518
0.0025
0.0024
0.0000
building
0.0335
0.9509
0.0132
0.0018
0.0005
0.0001
low_veg
0.0433
0.0058
0.9094
0.0409
0.0005
0.0000
tree
0.0136
0.0025
0.0734
0.9103
0.0000
0.0002
car
0.2101
0.0092
0.0162
0.0035
0.7602
0.0008
clutter
--
--
--
--
--
--
Precision/Correctness
0.928
0.970
0.826
0.960
0.909
--
Recall/Completeness
0.926
0.951
0.909
0.910
0.760
--
F1
0.927
0.960
0.866
0.934
0.828
--

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_area10_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8534
0.0661
0.0565
0.0185
0.0054
0.0000
building
0.0485
0.9197
0.0169
0.0122
0.0027
0.0000
low_veg
0.0941
0.0355
0.7010
0.1690
0.0003
0.0001
tree
0.0177
0.0059
0.0745
0.9018
0.0001
0.0000
car
0.2583
0.0043
0.0288
0.0054
0.7032
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.905
0.871
0.752
0.824
0.644
--
Recall/Completeness
0.853
0.920
0.701
0.902
0.703
--
F1
0.879
0.894
0.726
0.861
0.672
--

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_area10_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8832
0.0558
0.0495
0.0074
0.0041
0.0000
building
0.0419
0.9349
0.0121
0.0089
0.0023
0.0000
low_veg
0.0902
0.0233
0.7440
0.1422
0.0002
0.0001
tree
0.0077
0.0026
0.0567
0.9331
0.0000
0.0000
car
0.1698
0.0047
0.0288
0.0014
0.7953
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.924
0.897
0.790
0.865
0.659
--
Recall/Completeness
0.883
0.935
0.744
0.933
0.795
--
F1
0.903
0.916
0.766
0.898
0.721
--

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_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8842
0.0266
0.0521
0.0336
0.0035
0.0000
building
0.1003
0.8755
0.0152
0.0079
0.0002
0.0010
low_veg
0.0389
0.0204
0.7267
0.2136
0.0004
0.0000
tree
0.0116
0.0071
0.0916
0.8897
0.0000
0.0001
car
0.2042
0.0000
0.0172
0.0045
0.7740
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.778
0.932
0.826
0.828
0.857
--
Recall/Completeness
0.884
0.875
0.727
0.890
0.774
--
F1
0.828
0.903
0.773
0.858
0.813
--

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
0.9127
0.0238
0.0448
0.0177
0.0011
0.0000
building
0.1027
0.8855
0.0081
0.0025
0.0002
0.0011
low_veg
0.0361
0.0116
0.7597
0.1923
0.0003
0.0000
tree
0.0060
0.0029
0.0757
0.9153
0.0000
0.0001
car
0.1060
0.0000
0.0132
0.0004
0.8804
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.799
0.957
0.856
0.855
0.922
--
Recall/Completeness
0.913
0.886
0.760
0.915
0.880
--
F1
0.852
0.920
0.805
0.884
0.901
--

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_area14_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8460
0.0340
0.0779
0.0378
0.0041
0.0002
building
0.0165
0.9543
0.0217
0.0067
0.0008
0.0000
low_veg
0.0856
0.0501
0.6965
0.1676
0.0003
0.0000
tree
0.0344
0.0099
0.1202
0.8354
0.0001
0.0000
car
0.1957
0.0000
0.0010
0.0047
0.7986
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.841
0.875
0.741
0.842
0.639
--
Recall/Completeness
0.846
0.954
0.696
0.835
0.799
--
F1
0.843
0.913
0.718
0.839
0.710
--

Overall accuracy 0.823

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
0.8656
0.0292
0.0743
0.0273
0.0033
0.0002
building
0.0108
0.9740
0.0123
0.0023
0.0006
0.0000
low_veg
0.0810
0.0348
0.7267
0.1573
0.0002
0.0000
tree
0.0258
0.0041
0.1081
0.8619
0.0001
0.0000
car
0.0884
0.0000
0.0000
0.0009
0.9107
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.867
0.910
0.763
0.864
0.648
--
Recall/Completeness
0.866
0.974
0.727
0.862
0.911
--
F1
0.866
0.941
0.745
0.863
0.757
--

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_area16_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8397
0.0233
0.0841
0.0497
0.0032
0.0000
building
0.0360
0.9282
0.0204
0.0146
0.0007
0.0000
low_veg
0.0174
0.0141
0.8313
0.1364
0.0002
0.0007
tree
0.0268
0.0030
0.1108
0.8593
0.0000
0.0000
car
0.2030
0.0019
0.0022
0.0114
0.7815
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.856
0.949
0.811
0.861
0.719
--
Recall/Completeness
0.840
0.928
0.831
0.859
0.782
--
F1
0.848
0.938
0.821
0.860
0.749
--

Overall accuracy 0.860

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
0.8728
0.0190
0.0759
0.0307
0.0017
0.0000
building
0.0315
0.9520
0.0102
0.0057
0.0006
0.0000
low_veg
0.0136
0.0088
0.8548
0.1220
0.0001
0.0007
tree
0.0182
0.0007
0.0965
0.8846
0.0000
0.0000
car
0.1226
0.0000
0.0017
0.0028
0.8730
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.888
0.968
0.839
0.886
0.777
--
Recall/Completeness
0.873
0.952
0.855
0.885
0.873
--
F1
0.880
0.960
0.847
0.885
0.822
--

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_area20_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8571
0.0530
0.0459
0.0372
0.0067
0.0000
building
0.0177
0.9505
0.0248
0.0070
0.0000
0.0000
low_veg
0.0520
0.0308
0.7580
0.1589
0.0003
0.0000
tree
0.0119
0.0022
0.0534
0.9325
0.0000
0.0000
car
0.1922
0.0049
0.0286
0.0058
0.7685
0.0000
clutter
0.0213
0.9756
0.0022
0.0009
0.0000
0.0000
Precision/Correctness
0.900
0.780
0.806
0.907
0.691
-nan
Recall/Completeness
0.857
0.951
0.758
0.933
0.769
0.000
F1
0.878
0.857
0.781
0.919
0.728
-nan

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_area20_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8855
0.0451
0.0426
0.0215
0.0053
0.0000
building
0.0151
0.9634
0.0191
0.0024
0.0000
0.0000
low_veg
0.0446
0.0192
0.8039
0.1320
0.0004
0.0000
tree
0.0059
0.0007
0.0409
0.9525
0.0000
0.0000
car
0.1096
0.0019
0.0185
0.0002
0.8699
0.0000
clutter
0.0162
0.9817
0.0021
0.0000
0.0000
0.0000
Precision/Correctness
0.927
0.798
0.837
0.932
0.695
-nan
Recall/Completeness
0.885
0.963
0.804
0.953
0.870
0.000
F1
0.906
0.873
0.820
0.942
0.773
-nan

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: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9019
0.0229
0.0423
0.0273
0.0056
0.0000
building
0.0361
0.9437
0.0131
0.0062
0.0009
0.0000
low_veg
0.1138
0.0308
0.7002
0.1548
0.0005
0.0000
tree
0.0263
0.0040
0.0651
0.9044
0.0001
0.0000
car
0.3213
0.0053
0.0133
0.0116
0.6485
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.877
0.920
0.803
0.864
0.774
--
Recall/Completeness
0.902
0.944
0.700
0.904
0.649
--
F1
0.889
0.931
0.748
0.884
0.706
--

Overall accuracy 0.867

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
0.9326
0.0160
0.0355
0.0124
0.0035
0.0000
building
0.0291
0.9633
0.0039
0.0029
0.0008
0.0000
low_veg
0.1110
0.0180
0.7423
0.1284
0.0003
0.0000
tree
0.0119
0.0014
0.0482
0.9384
0.0001
0.0000
car
0.2299
0.0056
0.0081
0.0051
0.7512
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.904
0.950
0.847
0.901
0.819
--
Recall/Completeness
0.933
0.963
0.742
0.938
0.751
--
F1
0.918
0.957
0.791
0.919
0.783
--

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_area24_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8160
0.0479
0.0972
0.0308
0.0081
0.0000
building
0.0643
0.8761
0.0504
0.0091
0.0001
0.0000
low_veg
0.0249
0.0210
0.8747
0.0792
0.0002
0.0000
tree
0.0191
0.0075
0.1669
0.8065
0.0000
0.0000
car
0.2557
0.0004
0.0114
0.0094
0.7231
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.808
0.904
0.845
0.841
0.685
--
Recall/Completeness
0.816
0.876
0.875
0.807
0.723
--
F1
0.812
0.890
0.860
0.823
0.703
--

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_area24_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8456
0.0368
0.0911
0.0204
0.0061
0.0000
building
0.0613
0.8881
0.0442
0.0064
0.0000
0.0000
low_veg
0.0212
0.0166
0.8924
0.0697
0.0001
0.0000
tree
0.0122
0.0038
0.1432
0.8408
0.0000
0.0000
car
0.1707
0.0006
0.0049
0.0037
0.8201
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.834
0.928
0.867
0.863
0.704
--
Recall/Completeness
0.846
0.888
0.892
0.841
0.820
--
F1
0.840
0.908
0.879
0.852
0.757
--

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_area27_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9454
0.0213
0.0187
0.0065
0.0081
0.0000
building
0.1026
0.8691
0.0225
0.0050
0.0007
0.0000
low_veg
0.1168
0.0182
0.6897
0.1748
0.0006
0.0000
tree
0.0208
0.0035
0.0619
0.9136
0.0001
0.0000
car
0.3714
0.0047
0.0027
0.0060
0.6151
0.0000
clutter
0.7076
0.1063
0.0866
0.0113
0.0882
0.0000
Precision/Correctness
0.802
0.965
0.869
0.705
0.862
0.000
Recall/Completeness
0.945
0.869
0.690
0.914
0.615
0.000
F1
0.868
0.914
0.769
0.796
0.718
-nan

Overall accuracy 0.852

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
0.9687
0.0132
0.0127
0.0023
0.0031
0.0000
building
0.0884
0.8925
0.0156
0.0029
0.0006
0.0000
low_veg
0.0976
0.0087
0.7290
0.1644
0.0004
0.0000
tree
0.0099
0.0009
0.0437
0.9455
0.0000
0.0000
car
0.2742
0.0029
0.0009
0.0040
0.7180
0.0000
clutter
0.7356
0.0999
0.0655
0.0040
0.0949
0.0000
Precision/Correctness
0.837
0.981
0.907
0.737
0.924
0.000
Recall/Completeness
0.969
0.893
0.729
0.946
0.718
0.000
F1
0.898
0.935
0.808
0.828
0.808
-nan

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_area29_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9416
0.0241
0.0169
0.0123
0.0050
0.0000
building
0.0555
0.9289
0.0092
0.0064
0.0001
0.0000
low_veg
0.1025
0.0201
0.5757
0.3015
0.0002
0.0000
tree
0.0103
0.0024
0.0232
0.9641
0.0000
0.0000
car
0.2999
0.0071
0.0004
0.0083
0.6843
0.0000
clutter
0.3913
0.4873
0.0071
0.0211
0.0932
0.0000
Precision/Correctness
0.895
0.900
0.873
0.669
0.649
-nan
Recall/Completeness
0.942
0.929
0.576
0.964
0.684
0.000
F1
0.918
0.914
0.694
0.790
0.666
-nan

Overall accuracy 0.855

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area29_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9615
0.0176
0.0123
0.0053
0.0032
0.0000
building
0.0492
0.9428
0.0050
0.0029
0.0001
0.0000
low_veg
0.0764
0.0092
0.6246
0.2897
0.0000
0.0000
tree
0.0041
0.0011
0.0156
0.9792
0.0000
0.0000
car
0.2125
0.0063
0.0000
0.0064
0.7748
0.0000
clutter
0.3559
0.5278
0.0034
0.0106
0.1023
0.0000
Precision/Correctness
0.919
0.919
0.910
0.707
0.655
-nan
Recall/Completeness
0.962
0.943
0.625
0.979
0.775
0.000
F1
0.940
0.931
0.741
0.821
0.710
-nan

Overall accuracy 0.884

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
0.9565
0.0214
0.0114
0.0034
0.0073
0.0000
building
0.1609
0.8208
0.0113
0.0041
0.0028
0.0000
low_veg
0.0452
0.0055
0.9013
0.0474
0.0006
0.0000
tree
0.0542
0.0023
0.0848
0.8582
0.0004
0.0000
car
0.2448
0.0870
0.0150
0.0061
0.6454
0.0017
clutter
0.5034
0.3605
0.0225
0.0119
0.1018
0.0000
Precision/Correctness
0.817
0.902
0.879
0.906
0.763
0.000
Recall/Completeness
0.956
0.821
0.901
0.858
0.645
0.000
F1
0.881
0.860
0.890
0.881
0.699
-nan

Overall accuracy 0.856

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area31_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9692
0.0178
0.0089
0.0004
0.0037
0.0000
building
0.1495
0.8404
0.0070
0.0008
0.0023
0.0000
low_veg
0.0254
0.0034
0.9304
0.0406
0.0003
0.0000
tree
0.0246
0.0005
0.0692
0.9056
0.0001
0.0000
car
0.1617
0.0931
0.0077
0.0017
0.7337
0.0021
clutter
0.4643
0.4043
0.0182
0.0042
0.1090
0.0000
Precision/Correctness
0.846
0.916
0.910
0.937
0.794
0.000
Recall/Completeness
0.969
0.840
0.930
0.906
0.734
0.000
F1
0.904
0.877
0.920
0.921
0.763
-nan

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_area33_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9467
0.0458
0.0038
0.0018
0.0019
0.0000
building
0.1822
0.7179
0.0917
0.0039
0.0042
0.0000
low_veg
0.0823
0.0176
0.8168
0.0830
0.0003
0.0000
tree
0.0684
0.0138
0.1598
0.7579
0.0001
0.0000
car
0.4121
0.0502
0.0059
0.0033
0.5286
0.0000
clutter
0.5343
0.3647
0.0037
0.0002
0.0970
0.0000
Precision/Correctness
0.773
0.832
0.736
0.844
0.483
1.000
Recall/Completeness
0.947
0.718
0.817
0.758
0.529
0.000
F1
0.851
0.771
0.774
0.799
0.505
0.000

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_area33_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9575
0.0401
0.0010
0.0002
0.0012
0.0000
building
0.1755
0.7280
0.0900
0.0023
0.0041
0.0000
low_veg
0.0489
0.0104
0.8565
0.0839
0.0003
0.0000
tree
0.0355
0.0128
0.1467
0.8050
0.0000
0.0000
car
0.3048
0.0577
0.0027
0.0019
0.6329
0.0000
clutter
0.5199
0.3714
0.0021
0.0000
0.1065
0.0000
Precision/Correctness
0.799
0.854
0.752
0.859
0.471
-nan
Recall/Completeness
0.957
0.728
0.857
0.805
0.633
0.000
F1
0.871
0.786
0.801
0.831
0.540
-nan

Overall accuracy 0.806

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
0.8859
0.0385
0.0584
0.0157
0.0016
0.0000
building
0.0671
0.8996
0.0273
0.0048
0.0013
0.0000
low_veg
0.0617
0.0096
0.7226
0.2060
0.0001
0.0000
tree
0.0439
0.0036
0.1289
0.8232
0.0004
0.0000
car
0.3386
0.0207
0.0018
0.0096
0.6280
0.0012
clutter
--
--
--
--
--
--
Precision/Correctness
0.828
0.948
0.775
0.774
0.845
--
Recall/Completeness
0.886
0.900
0.723
0.823
0.628
--
F1
0.856
0.923
0.748
0.798
0.721
--

Overall accuracy 0.833

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
0.9254
0.0334
0.0372
0.0033
0.0006
0.0000
building
0.0534
0.9302
0.0141
0.0010
0.0012
0.0000
low_veg
0.0447
0.0044
0.7502
0.2006
0.0001
0.0000
tree
0.0193
0.0008
0.1016
0.8781
0.0002
0.0000
car
0.2224
0.0221
0.0005
0.0030
0.7502
0.0018
clutter
--
--
--
--
--
--
Precision/Correctness
0.878
0.965
0.835
0.800
0.885
--
Recall/Completeness
0.925
0.930
0.750
0.878
0.750
--
F1
0.901
0.947
0.790
0.837
0.812
--

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_area38_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9200
0.0263
0.0389
0.0106
0.0042
0.0000
building
0.0488
0.8955
0.0487
0.0056
0.0014
0.0000
low_veg
0.0500
0.0410
0.8111
0.0976
0.0003
0.0000
tree
0.0378
0.0042
0.1277
0.8302
0.0001
0.0000
car
0.3197
0.0057
0.0490
0.0080
0.6176
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.870
0.921
0.825
0.836
0.789
--
Recall/Completeness
0.920
0.895
0.811
0.830
0.618
--
F1
0.894
0.908
0.818
0.833
0.693
--

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_area38_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9433
0.0239
0.0270
0.0031
0.0026
0.0000
building
0.0398
0.9215
0.0352
0.0024
0.0011
0.0000
low_veg
0.0316
0.0382
0.8466
0.0834
0.0002
0.0000
tree
0.0183
0.0018
0.1056
0.8743
0.0000
0.0000
car
0.2304
0.0036
0.0379
0.0026
0.7256
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.912
0.933
0.864
0.871
0.831
--
Recall/Completeness
0.943
0.921
0.847
0.874
0.726
--
F1
0.927
0.927
0.855
0.873
0.775
--

Overall accuracy 0.896

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image