Detailled semantic labeling (2D) result


Name D. Tran and T. Bui
Affiliation University​ ​of​ ​Engineering​ ​and​ ​Technology, Vietnam
Abbreviation VNU3
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
0.907
0.031
0.041
0.016
0.005
0.000
building
0.064
0.907
0.023
0.005
0.001
0.000
low_veg
0.062
0.025
0.769
0.143
0.000
0.000
tree
0.024
0.005
0.102
0.869
0.000
0.000
car
0.292
0.041
0.011
0.006
0.647
0.003
clutter
0.361
0.265
0.015
0.009
0.065
0.285
Precision/Correctness
0.856
0.928
0.804
0.842
0.780
0.939
Recall/Completeness
0.907
0.907
0.769
0.869
0.647
0.285
F1
0.881
0.917
0.786
0.855
0.708
0.437

Overall accuracy 0.860

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
0.024
0.033
0.007
0.003
0.000
building
0.056
0.924
0.017
0.002
0.001
0.000
low_veg
0.049
0.016
0.805
0.129
0.000
0.000
tree
0.012
0.002
0.085
0.901
0.000
0.000
car
0.196
0.046
0.006
0.003
0.745
0.004
clutter
0.321
0.285
0.013
0.003
0.067
0.311
Precision/Correctness
0.887
0.949
0.838
0.871
0.811
0.958
Recall/Completeness
0.933
0.924
0.805
0.901
0.745
0.311
F1
0.910
0.936
0.821
0.886
0.777
0.470

Overall accuracy 0.889
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9446
0.0127
0.0243
0.0129
0.0055
0.0000
building
0.0480
0.9273
0.0201
0.0040
0.0006
0.0000
low_veg
0.0822
0.0215
0.7171
0.1790
0.0002
0.0000
tree
0.0321
0.0045
0.1113
0.8504
0.0001
0.0015
car
0.3035
0.0070
0.0005
0.0017
0.6873
0.0000
clutter
0.0010
0.0038
0.0000
0.0176
0.0000
0.9776
Precision/Correctness
0.844
0.956
0.821
0.813
0.870
0.979
Recall/Completeness
0.945
0.927
0.717
0.850
0.687
0.978
F1
0.891
0.942
0.766
0.831
0.768
0.978

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_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9684
0.0090
0.0154
0.0037
0.0036
0.0000
building
0.0391
0.9480
0.0107
0.0015
0.0006
0.0000
low_veg
0.0643
0.0122
0.7497
0.1736
0.0001
0.0000
tree
0.0162
0.0017
0.0991
0.8823
0.0000
0.0008
car
0.1863
0.0049
0.0000
0.0007
0.8081
0.0000
clutter
0.0010
0.0033
0.0000
0.0046
0.0000
0.9911
Precision/Correctness
0.885
0.975
0.853
0.837
0.901
0.990
Recall/Completeness
0.968
0.948
0.750
0.882
0.808
0.991
F1
0.925
0.961
0.798
0.859
0.852
0.991

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_area4_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9349
0.0459
0.0102
0.0034
0.0056
0.0000
building
0.0887
0.8996
0.0087
0.0018
0.0013
0.0000
low_veg
0.2122
0.0459
0.4766
0.2647
0.0006
0.0000
tree
0.0644
0.0176
0.1005
0.8174
0.0001
0.0000
car
0.4197
0.0157
0.0007
0.0026
0.5613
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.800
0.968
0.626
0.739
0.773
--
Recall/Completeness
0.935
0.900
0.477
0.817
0.561
--
F1
0.862
0.933
0.541
0.776
0.651
--

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_area4_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9617
0.0262
0.0072
0.0010
0.0039
0.0000
building
0.0759
0.9144
0.0075
0.0010
0.0013
0.0000
low_veg
0.1770
0.0169
0.5117
0.2940
0.0004
0.0000
tree
0.0321
0.0081
0.0988
0.8610
0.0000
0.0000
car
0.3361
0.0081
0.0000
0.0016
0.6541
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.828
0.984
0.649
0.762
0.793
--
Recall/Completeness
0.962
0.914
0.512
0.861
0.654
--
F1
0.890
0.948
0.572
0.808
0.717
--

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: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9089
0.0442
0.0323
0.0096
0.0051
0.0000
building
0.0700
0.9142
0.0116
0.0036
0.0006
0.0000
low_veg
0.1065
0.0339
0.6960
0.1628
0.0007
0.0000
tree
0.0188
0.0030
0.0565
0.9214
0.0003
0.0000
car
0.3805
0.0141
0.0023
0.0012
0.6012
0.0007
clutter
--
--
--
--
--
--
Precision/Correctness
0.834
0.950
0.723
0.927
0.855
--
Recall/Completeness
0.909
0.914
0.696
0.921
0.601
--
F1
0.870
0.932
0.709
0.924
0.706
--

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_area6_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9419
0.0286
0.0242
0.0025
0.0028
0.0000
building
0.0609
0.9299
0.0072
0.0014
0.0005
0.0000
low_veg
0.0897
0.0189
0.7487
0.1424
0.0002
0.0000
tree
0.0075
0.0006
0.0443
0.9475
0.0001
0.0000
car
0.2729
0.0078
0.0014
0.0002
0.7171
0.0006
clutter
--
--
--
--
--
--
Precision/Correctness
0.870
0.972
0.771
0.949
0.904
--
Recall/Completeness
0.942
0.930
0.749
0.947
0.717
--
F1
0.904
0.950
0.760
0.948
0.800
--

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_area8_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8925
0.0259
0.0685
0.0091
0.0039
0.0000
building
0.0418
0.9340
0.0185
0.0048
0.0008
0.0000
low_veg
0.0556
0.0136
0.8664
0.0638
0.0005
0.0000
tree
0.0281
0.0061
0.0917
0.8740
0.0001
0.0000
car
0.3133
0.0051
0.0212
0.0030
0.6560
0.0013
clutter
--
--
--
--
--
--
Precision/Correctness
0.896
0.946
0.780
0.927
0.878
--
Recall/Completeness
0.893
0.934
0.866
0.874
0.656
--
F1
0.894
0.940
0.821
0.899
0.751
--

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_area8_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9189
0.0187
0.0584
0.0021
0.0020
0.0000
building
0.0325
0.9539
0.0107
0.0023
0.0007
0.0000
low_veg
0.0390
0.0058
0.9025
0.0526
0.0002
0.0000
tree
0.0123
0.0026
0.0715
0.9136
0.0000
0.0000
car
0.2037
0.0028
0.0138
0.0017
0.7765
0.0016
clutter
--
--
--
--
--
--
Precision/Correctness
0.932
0.968
0.821
0.951
0.922
--
Recall/Completeness
0.919
0.954
0.902
0.914
0.777
--
F1
0.925
0.961
0.860
0.932
0.843
--

Overall accuracy 0.921

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
0.8407
0.0767
0.0602
0.0180
0.0045
0.0000
building
0.0400
0.9281
0.0202
0.0107
0.0006
0.0004
low_veg
0.0839
0.0317
0.7264
0.1567
0.0012
0.0001
tree
0.0185
0.0070
0.0782
0.8963
0.0000
0.0000
car
0.2530
0.0336
0.0115
0.0061
0.6955
0.0004
clutter
--
--
--
--
--
--
Precision/Correctness
0.914
0.859
0.746
0.833
0.703
--
Recall/Completeness
0.841
0.928
0.726
0.896
0.696
--
F1
0.876
0.892
0.736
0.864
0.699
--

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_area10_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8726
0.0643
0.0525
0.0072
0.0033
0.0000
building
0.0337
0.9428
0.0149
0.0076
0.0005
0.0005
low_veg
0.0807
0.0185
0.7672
0.1322
0.0014
0.0001
tree
0.0088
0.0031
0.0577
0.9304
0.0000
0.0000
car
0.1676
0.0387
0.0078
0.0020
0.7834
0.0005
clutter
--
--
--
--
--
--
Precision/Correctness
0.932
0.888
0.786
0.873
0.716
--
Recall/Completeness
0.873
0.943
0.767
0.930
0.783
--
F1
0.901
0.915
0.776
0.901
0.748
--

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_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8908
0.0287
0.0449
0.0327
0.0029
0.0000
building
0.1354
0.8445
0.0143
0.0056
0.0000
0.0001
low_veg
0.0499
0.0295
0.7338
0.1861
0.0006
0.0001
tree
0.0113
0.0079
0.1185
0.8620
0.0001
0.0002
car
0.2070
0.0037
0.0093
0.0057
0.7743
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.735
0.912
0.801
0.842
0.861
--
Recall/Completeness
0.891
0.845
0.734
0.862
0.774
--
F1
0.806
0.877
0.766
0.852
0.816
--

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_area12_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9187
0.0256
0.0376
0.0173
0.0007
0.0000
building
0.1405
0.8510
0.0067
0.0017
0.0000
0.0000
low_veg
0.0470
0.0201
0.7672
0.1650
0.0005
0.0002
tree
0.0056
0.0031
0.1030
0.8881
0.0000
0.0002
car
0.1010
0.0021
0.0048
0.0000
0.8921
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.753
0.940
0.828
0.869
0.925
--
Recall/Completeness
0.919
0.851
0.767
0.888
0.892
--
F1
0.828
0.893
0.797
0.879
0.908
--

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_area14_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8367
0.0311
0.0966
0.0318
0.0039
0.0000
building
0.0135
0.9605
0.0193
0.0065
0.0003
0.0000
low_veg
0.0794
0.0508
0.7109
0.1584
0.0004
0.0000
tree
0.0303
0.0122
0.1272
0.8302
0.0001
0.0001
car
0.1511
0.0000
0.0001
0.0037
0.8451
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.853
0.875
0.726
0.851
0.678
--
Recall/Completeness
0.837
0.960
0.711
0.830
0.845
--
F1
0.845
0.916
0.718
0.840
0.752
--

Overall accuracy 0.824

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
0.8567
0.0257
0.0935
0.0210
0.0030
0.0000
building
0.0083
0.9791
0.0100
0.0024
0.0002
0.0000
low_veg
0.0749
0.0353
0.7409
0.1485
0.0004
0.0000
tree
0.0219
0.0057
0.1154
0.8569
0.0000
0.0001
car
0.0472
0.0000
0.0000
0.0002
0.9526
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.879
0.911
0.747
0.873
0.692
--
Recall/Completeness
0.857
0.979
0.741
0.857
0.953
--
F1
0.868
0.944
0.744
0.865
0.801
--

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
0.8378
0.0299
0.0799
0.0497
0.0027
0.0000
building
0.0217
0.9475
0.0218
0.0085
0.0004
0.0000
low_veg
0.0222
0.0185
0.8425
0.1159
0.0003
0.0006
tree
0.0270
0.0039
0.1336
0.8355
0.0000
0.0000
car
0.2161
0.0004
0.0072
0.0042
0.7722
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.862
0.936
0.793
0.875
0.744
--
Recall/Completeness
0.838
0.948
0.842
0.836
0.772
--
F1
0.850
0.942
0.817
0.855
0.758
--

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_area16_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8711
0.0259
0.0713
0.0307
0.0011
0.0000
building
0.0170
0.9694
0.0107
0.0026
0.0003
0.0000
low_veg
0.0179
0.0124
0.8671
0.1016
0.0002
0.0007
tree
0.0188
0.0010
0.1186
0.8616
0.0000
0.0000
car
0.1368
0.0000
0.0025
0.0003
0.8604
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.894
0.956
0.821
0.900
0.823
--
Recall/Completeness
0.871
0.969
0.867
0.862
0.860
--
F1
0.883
0.963
0.843
0.880
0.841
--

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_area20_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8567
0.0548
0.0377
0.0452
0.0055
0.0001
building
0.0257
0.9423
0.0260
0.0060
0.0000
0.0000
low_veg
0.0551
0.0354
0.7557
0.1536
0.0001
0.0000
tree
0.0094
0.0020
0.0535
0.9351
0.0000
0.0000
car
0.2305
0.0058
0.0400
0.0156
0.7081
0.0000
clutter
0.0360
0.9633
0.0000
0.0006
0.0000
0.0001
Precision/Correctness
0.893
0.775
0.811
0.906
0.718
0.156
Recall/Completeness
0.857
0.942
0.756
0.935
0.708
0.000
F1
0.874
0.850
0.783
0.920
0.713
0.000

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_area20_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8855
0.0473
0.0357
0.0275
0.0040
0.0001
building
0.0225
0.9541
0.0214
0.0020
0.0000
0.0000
low_veg
0.0487
0.0228
0.8015
0.1270
0.0002
0.0000
tree
0.0043
0.0005
0.0408
0.9544
0.0000
0.0000
car
0.1767
0.0036
0.0358
0.0074
0.7765
0.0000
clutter
0.0275
0.9725
0.0000
0.0000
0.0000
0.0000
Precision/Correctness
0.918
0.793
0.842
0.931
0.732
0.000
Recall/Completeness
0.885
0.954
0.801
0.954
0.777
0.000
F1
0.902
0.866
0.821
0.943
0.754
-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_area22_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9003
0.0220
0.0419
0.0297
0.0060
0.0000
building
0.0334
0.9473
0.0133
0.0056
0.0004
0.0000
low_veg
0.1094
0.0402
0.7096
0.1405
0.0003
0.0000
tree
0.0243
0.0040
0.0708
0.9008
0.0001
0.0000
car
0.3005
0.0009
0.0213
0.0110
0.6664
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.882
0.912
0.797
0.870
0.778
--
Recall/Completeness
0.900
0.947
0.710
0.901
0.666
--
F1
0.891
0.929
0.751
0.885
0.718
--

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_area22_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9316
0.0145
0.0358
0.0143
0.0038
0.0000
building
0.0264
0.9651
0.0055
0.0026
0.0003
0.0000
low_veg
0.1059
0.0275
0.7530
0.1133
0.0003
0.0000
tree
0.0108
0.0011
0.0536
0.9344
0.0001
0.0000
car
0.2138
0.0000
0.0176
0.0042
0.7643
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.909
0.944
0.839
0.908
0.819
--
Recall/Completeness
0.932
0.965
0.753
0.934
0.764
--
F1
0.920
0.954
0.794
0.921
0.791
--

Overall accuracy 0.902

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
0.8032
0.0451
0.1169
0.0304
0.0044
0.0000
building
0.0715
0.8740
0.0396
0.0146
0.0003
0.0000
low_veg
0.0257
0.0228
0.8781
0.0731
0.0002
0.0000
tree
0.0200
0.0067
0.1729
0.8003
0.0001
0.0000
car
0.2463
0.0034
0.0096
0.0047
0.7285
0.0074
clutter
--
--
--
--
--
--
Precision/Correctness
0.796
0.903
0.841
0.845
0.769
--
Recall/Completeness
0.803
0.874
0.878
0.800
0.728
--
F1
0.799
0.888
0.859
0.822
0.748
--

Overall accuracy 0.846

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
0.8326
0.0343
0.1103
0.0201
0.0028
0.0000
building
0.0695
0.8861
0.0317
0.0124
0.0002
0.0000
low_veg
0.0221
0.0181
0.8960
0.0635
0.0002
0.0000
tree
0.0130
0.0031
0.1497
0.8340
0.0001
0.0000
car
0.1415
0.0043
0.0029
0.0017
0.8439
0.0056
clutter
--
--
--
--
--
--
Precision/Correctness
0.820
0.927
0.863
0.867
0.800
--
Recall/Completeness
0.833
0.886
0.896
0.834
0.844
--
F1
0.826
0.906
0.879
0.850
0.822
--

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_area27_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9363
0.0271
0.0210
0.0073
0.0083
0.0000
building
0.0899
0.8808
0.0230
0.0054
0.0008
0.0001
low_veg
0.0967
0.0241
0.6731
0.2056
0.0004
0.0000
tree
0.0155
0.0029
0.0600
0.9214
0.0002
0.0000
car
0.3145
0.0079
0.0071
0.0053
0.6651
0.0001
clutter
0.7205
0.0998
0.0885
0.0033
0.0880
0.0000
Precision/Correctness
0.824
0.956
0.861
0.674
0.869
0.000
Recall/Completeness
0.936
0.881
0.673
0.921
0.665
0.000
F1
0.877
0.917
0.756
0.779
0.754
-nan

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_area27_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9629
0.0178
0.0138
0.0028
0.0028
0.0000
building
0.0782
0.9011
0.0171
0.0030
0.0006
0.0001
low_veg
0.0798
0.0119
0.7129
0.1950
0.0003
0.0000
tree
0.0070
0.0004
0.0414
0.9511
0.0001
0.0000
car
0.2150
0.0057
0.0041
0.0038
0.7714
0.0001
clutter
0.7462
0.0871
0.0610
0.0017
0.1040
0.0000
Precision/Correctness
0.857
0.975
0.901
0.704
0.933
0.000
Recall/Completeness
0.963
0.901
0.713
0.951
0.771
0.000
F1
0.907
0.937
0.796
0.809
0.844
-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
0.9341
0.0227
0.0251
0.0122
0.0056
0.0004
building
0.0520
0.9277
0.0141
0.0059
0.0003
0.0001
low_veg
0.0842
0.0215
0.5890
0.3045
0.0009
0.0000
tree
0.0067
0.0017
0.0291
0.9625
0.0000
0.0000
car
0.2297
0.0097
0.0007
0.0154
0.7131
0.0313
clutter
0.5624
0.3009
0.0140
0.0152
0.0773
0.0302
Precision/Correctness
0.894
0.920
0.828
0.667
0.663
0.601
Recall/Completeness
0.934
0.928
0.589
0.962
0.713
0.030
F1
0.913
0.924
0.688
0.788
0.687
0.058

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_area29_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9547
0.0172
0.0188
0.0052
0.0038
0.0002
building
0.0461
0.9419
0.0090
0.0028
0.0002
0.0001
low_veg
0.0608
0.0098
0.6344
0.2944
0.0006
0.0000
tree
0.0023
0.0003
0.0216
0.9758
0.0000
0.0000
car
0.1373
0.0065
0.0000
0.0132
0.8081
0.0348
clutter
0.5418
0.3242
0.0107
0.0056
0.0836
0.0340
Precision/Correctness
0.917
0.938
0.868
0.704
0.671
0.670
Recall/Completeness
0.955
0.942
0.634
0.976
0.808
0.034
F1
0.935
0.940
0.733
0.818
0.733
0.065

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
0.9661
0.0125
0.0109
0.0029
0.0076
0.0001
building
0.1070
0.8772
0.0103
0.0022
0.0032
0.0001
low_veg
0.0406
0.0061
0.9200
0.0327
0.0007
0.0000
tree
0.0412
0.0031
0.1060
0.8491
0.0006
0.0000
car
0.1955
0.1894
0.0097
0.0051
0.5926
0.0077
clutter
0.5419
0.1866
0.0482
0.0124
0.1271
0.0838
Precision/Correctness
0.851
0.927
0.867
0.930
0.721
0.885
Recall/Completeness
0.966
0.877
0.920
0.849
0.593
0.084
F1
0.905
0.901
0.893
0.888
0.651
0.153

Overall accuracy 0.878

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
0.9782
0.0098
0.0076
0.0003
0.0041
0.0001
building
0.0973
0.8961
0.0037
0.0004
0.0025
0.0001
low_veg
0.0221
0.0041
0.9459
0.0275
0.0003
0.0000
tree
0.0137
0.0013
0.0859
0.8990
0.0001
0.0000
car
0.1203
0.2135
0.0029
0.0014
0.6532
0.0088
clutter
0.4976
0.2147
0.0507
0.0046
0.1361
0.0963
Precision/Correctness
0.881
0.938
0.904
0.956
0.744
0.905
Recall/Completeness
0.978
0.896
0.946
0.899
0.653
0.096
F1
0.927
0.917
0.925
0.927
0.696
0.174

Overall accuracy 0.905

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
0.9705
0.0162
0.0066
0.0018
0.0027
0.0022
building
0.0706
0.8410
0.0826
0.0034
0.0021
0.0002
low_veg
0.0730
0.0182
0.8257
0.0824
0.0007
0.0000
tree
0.0545
0.0041
0.1367
0.8045
0.0002
0.0000
car
0.3718
0.0492
0.0037
0.0032
0.5716
0.0004
clutter
0.4358
0.0907
0.0019
0.0007
0.0785
0.3925
Precision/Correctness
0.850
0.942
0.756
0.854
0.549
0.959
Recall/Completeness
0.971
0.841
0.826
0.804
0.572
0.392
F1
0.906
0.889
0.790
0.828
0.560
0.557

Overall accuracy 0.857

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
0.9819
0.0121
0.0027
0.0004
0.0020
0.0009
building
0.0627
0.8520
0.0813
0.0018
0.0021
0.0002
low_veg
0.0421
0.0095
0.8641
0.0837
0.0007
0.0000
tree
0.0268
0.0012
0.1224
0.8494
0.0002
0.0000
car
0.2662
0.0550
0.0016
0.0008
0.6761
0.0003
clutter
0.4002
0.0889
0.0012
0.0001
0.0853
0.4244
Precision/Correctness
0.882
0.958
0.774
0.867
0.538
0.981
Recall/Completeness
0.982
0.852
0.864
0.849
0.676
0.424
F1
0.929
0.902
0.817
0.858
0.599
0.593

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_area35_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8642
0.0473
0.0687
0.0184
0.0013
0.0000
building
0.0630
0.9055
0.0246
0.0055
0.0013
0.0001
low_veg
0.0469
0.0146
0.7064
0.2320
0.0000
0.0000
tree
0.0356
0.0053
0.1191
0.8397
0.0003
0.0000
car
0.3420
0.0253
0.0062
0.0084
0.6181
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.846
0.934
0.772
0.755
0.862
--
Recall/Completeness
0.864
0.905
0.706
0.840
0.618
--
F1
0.855
0.920
0.738
0.795
0.720
--

Overall accuracy 0.829

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
0.9071
0.0405
0.0473
0.0047
0.0004
0.0000
building
0.0523
0.9308
0.0143
0.0013
0.0012
0.0001
low_veg
0.0332
0.0065
0.7341
0.2263
0.0000
0.0000
tree
0.0148
0.0016
0.0928
0.8906
0.0001
0.0000
car
0.2312
0.0268
0.0025
0.0029
0.7366
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.890
0.956
0.830
0.781
0.900
--
Recall/Completeness
0.907
0.931
0.734
0.891
0.737
--
F1
0.898
0.943
0.779
0.832
0.810
--

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_area38_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9221
0.0218
0.0401
0.0120
0.0041
0.0000
building
0.0403
0.9121
0.0408
0.0047
0.0019
0.0002
low_veg
0.0417
0.0244
0.8369
0.0967
0.0003
0.0000
tree
0.0259
0.0050
0.1105
0.8586
0.0000
0.0000
car
0.2868
0.0211
0.0396
0.0087
0.6438
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.893
0.943
0.845
0.842
0.789
--
Recall/Completeness
0.922
0.912
0.837
0.859
0.644
--
F1
0.907
0.927
0.841
0.850
0.709
--

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
0.9479
0.0181
0.0277
0.0037
0.0026
0.0000
building
0.0321
0.9361
0.0282
0.0017
0.0017
0.0002
low_veg
0.0260
0.0188
0.8745
0.0807
0.0001
0.0000
tree
0.0093
0.0020
0.0890
0.8998
0.0000
0.0000
car
0.1969
0.0244
0.0284
0.0017
0.7485
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.931
0.959
0.883
0.878
0.820
--
Recall/Completeness
0.948
0.936
0.874
0.900
0.748
--
F1
0.939
0.947
0.879
0.889
0.782
--

Overall accuracy 0.914

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image