Detailled semantic labeling (2D) result


Name D. Gonzalez et al.
Affiliation Wageningen University and Research, The Netherlands
Abbreviation WUR_1
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
0.890
0.029
0.046
0.022
0.013
0.000
building
0.068
0.895
0.019
0.016
0.002
0.000
low_veg
0.065
0.022
0.733
0.178
0.002
0.000
tree
0.018
0.005
0.087
0.890
0.000
0.000
car
0.294
0.028
0.007
0.008
0.663
0.000
clutter
0.501
0.276
0.054
0.015
0.154
0.000
Precision/Correctness
0.849
0.932
0.807
0.805
0.597
-nan
Recall/Completeness
0.890
0.895
0.733
0.890
0.663
0.000
F1
0.869
0.913
0.769
0.845
0.628
-nan

Overall accuracy 0.847

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
0.920
0.022
0.038
0.012
0.008
0.000
building
0.059
0.915
0.013
0.011
0.002
0.000
low_veg
0.052
0.014
0.774
0.159
0.001
0.000
tree
0.009
0.003
0.074
0.914
0.000
0.000
car
0.229
0.030
0.005
0.004
0.732
0.000
clutter
0.481
0.296
0.056
0.008
0.159
0.000
Precision/Correctness
0.879
0.951
0.840
0.838
0.618
-nan
Recall/Completeness
0.920
0.915
0.774
0.914
0.732
0.000
F1
0.899
0.933
0.806
0.875
0.670
-nan

Overall accuracy 0.877
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9258
0.0117
0.0386
0.0149
0.0090
0.0000
building
0.0400
0.9244
0.0242
0.0108
0.0006
0.0000
low_veg
0.0836
0.0204
0.7206
0.1741
0.0013
0.0000
tree
0.0275
0.0084
0.0842
0.8798
0.0000
0.0000
car
0.3592
0.0165
0.0021
0.0042
0.6180
0.0000
clutter
0.8754
0.0372
0.0272
0.0602
0.0000
0.0000
Precision/Correctness
0.799
0.951
0.828
0.813
0.778
-nan
Recall/Completeness
0.926
0.924
0.721
0.880
0.618
0.000
F1
0.858
0.938
0.771
0.845
0.689
-nan

Overall accuracy 0.842

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9556
0.0067
0.0271
0.0048
0.0057
0.0000
building
0.0308
0.9451
0.0173
0.0063
0.0005
0.0000
low_veg
0.0669
0.0107
0.7580
0.1632
0.0011
0.0000
tree
0.0135
0.0060
0.0732
0.9072
0.0000
0.0000
car
0.2766
0.0176
0.0024
0.0019
0.7015
0.0000
clutter
0.8993
0.0379
0.0282
0.0347
0.0000
0.0000
Precision/Correctness
0.831
0.971
0.860
0.842
0.823
-nan
Recall/Completeness
0.956
0.945
0.758
0.907
0.702
0.000
F1
0.889
0.958
0.806
0.873
0.757
-nan

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_area4_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9069
0.0618
0.0093
0.0073
0.0147
0.0000
building
0.0607
0.9241
0.0078
0.0058
0.0015
0.0000
low_veg
0.2039
0.0624
0.4136
0.3199
0.0001
0.0000
tree
0.0619
0.0079
0.0581
0.8717
0.0003
0.0000
car
0.3782
0.0187
0.0028
0.0012
0.5992
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.837
0.960
0.650
0.680
0.627
--
Recall/Completeness
0.907
0.924
0.414
0.872
0.599
--
F1
0.870
0.942
0.505
0.764
0.613
--

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_area4_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9346
0.0418
0.0076
0.0042
0.0118
0.0000
building
0.0447
0.9430
0.0069
0.0040
0.0014
0.0000
low_veg
0.1605
0.0390
0.4659
0.3346
0.0000
0.0000
tree
0.0310
0.0030
0.0567
0.9093
0.0000
0.0000
car
0.3126
0.0112
0.0020
0.0000
0.6743
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.876
0.976
0.676
0.716
0.639
--
Recall/Completeness
0.935
0.943
0.466
0.909
0.674
--
F1
0.905
0.959
0.552
0.801
0.656
--

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_area6_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8707
0.0614
0.0392
0.0157
0.0130
0.0000
building
0.0417
0.9202
0.0239
0.0134
0.0009
0.0000
low_veg
0.0431
0.0440
0.6522
0.2600
0.0006
0.0000
tree
0.0106
0.0022
0.0632
0.9239
0.0000
0.0000
car
0.3629
0.0065
0.0062
0.0032
0.6212
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.890
0.935
0.658
0.880
0.734
--
Recall/Completeness
0.871
0.920
0.652
0.924
0.621
--
F1
0.880
0.928
0.655
0.902
0.673
--

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_area6_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9077
0.0479
0.0309
0.0055
0.0080
0.0000
building
0.0305
0.9414
0.0193
0.0081
0.0007
0.0000
low_veg
0.0278
0.0321
0.6999
0.2396
0.0006
0.0000
tree
0.0028
0.0009
0.0537
0.9426
0.0000
0.0000
car
0.2922
0.0027
0.0037
0.0002
0.7011
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.928
0.955
0.692
0.911
0.792
--
Recall/Completeness
0.908
0.941
0.700
0.943
0.701
--
F1
0.918
0.948
0.696
0.926
0.744
--

Overall accuracy 0.907

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
0.8753
0.0374
0.0614
0.0159
0.0099
0.0000
building
0.0332
0.9394
0.0147
0.0123
0.0005
0.0000
low_veg
0.0618
0.0182
0.8411
0.0780
0.0009
0.0000
tree
0.0183
0.0065
0.0692
0.9060
0.0000
0.0000
car
0.3152
0.0153
0.0102
0.0099
0.6494
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.903
0.927
0.808
0.903
0.764
--
Recall/Completeness
0.875
0.939
0.841
0.906
0.649
--
F1
0.889
0.933
0.824
0.904
0.702
--

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_area8_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9044
0.0317
0.0531
0.0054
0.0054
0.0000
building
0.0222
0.9604
0.0089
0.0082
0.0004
0.0000
low_veg
0.0444
0.0098
0.8839
0.0614
0.0005
0.0000
tree
0.0064
0.0035
0.0546
0.9354
0.0000
0.0000
car
0.2528
0.0156
0.0057
0.0077
0.7182
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.938
0.947
0.843
0.935
0.831
--
Recall/Completeness
0.904
0.960
0.884
0.935
0.718
--
F1
0.921
0.954
0.863
0.935
0.770
--

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_area10_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8505
0.0591
0.0541
0.0287
0.0076
0.0000
building
0.0242
0.9300
0.0223
0.0220
0.0015
0.0000
low_veg
0.0700
0.0346
0.7131
0.1814
0.0009
0.0000
tree
0.0121
0.0051
0.0696
0.9131
0.0000
0.0000
car
0.3124
0.0146
0.0317
0.0064
0.6350
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.934
0.882
0.758
0.797
0.571
--
Recall/Completeness
0.851
0.930
0.713
0.913
0.635
--
F1
0.890
0.905
0.735
0.851
0.601
--

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_area10_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8865
0.0470
0.0462
0.0146
0.0057
0.0000
building
0.0170
0.9498
0.0156
0.0165
0.0011
0.0000
low_veg
0.0668
0.0241
0.7615
0.1467
0.0008
0.0000
tree
0.0054
0.0024
0.0545
0.9376
0.0000
0.0000
car
0.2671
0.0161
0.0289
0.0010
0.6869
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.950
0.910
0.798
0.845
0.582
--
Recall/Completeness
0.886
0.950
0.762
0.938
0.687
--
F1
0.917
0.929
0.779
0.889
0.630
--

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_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8649
0.0241
0.0529
0.0466
0.0115
0.0000
building
0.1841
0.7748
0.0232
0.0151
0.0029
0.0000
low_veg
0.0684
0.0252
0.6541
0.2500
0.0023
0.0000
tree
0.0081
0.0048
0.1061
0.8810
0.0000
0.0000
car
0.1464
0.0083
0.0007
0.0085
0.8361
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.677
0.922
0.787
0.799
0.596
--
Recall/Completeness
0.865
0.775
0.654
0.881
0.836
--
F1
0.759
0.842
0.715
0.838
0.696
--

Overall accuracy 0.792

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
0.8971
0.0214
0.0474
0.0278
0.0063
0.0000
building
0.1905
0.7846
0.0160
0.0059
0.0030
0.0000
low_veg
0.0664
0.0168
0.6913
0.2231
0.0023
0.0000
tree
0.0033
0.0023
0.0947
0.8996
0.0000
0.0000
car
0.0724
0.0086
0.0002
0.0022
0.9168
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.691
0.946
0.813
0.830
0.614
--
Recall/Completeness
0.897
0.785
0.691
0.900
0.917
--
F1
0.781
0.858
0.747
0.864
0.736
--

Overall accuracy 0.818

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
0.8420
0.0276
0.0801
0.0437
0.0066
0.0000
building
0.0245
0.9301
0.0295
0.0154
0.0006
0.0000
low_veg
0.0741
0.0480
0.6825
0.1921
0.0033
0.0000
tree
0.0220
0.0108
0.1105
0.8567
0.0000
0.0000
car
0.1708
0.0163
0.0000
0.0150
0.7979
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.862
0.880
0.741
0.823
0.464
--
Recall/Completeness
0.842
0.930
0.682
0.857
0.798
--
F1
0.852
0.905
0.711
0.840
0.587
--

Overall accuracy 0.822

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area14_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8655
0.0235
0.0752
0.0308
0.0051
0.0000
building
0.0174
0.9537
0.0192
0.0092
0.0005
0.0000
low_veg
0.0674
0.0348
0.7173
0.1769
0.0036
0.0000
tree
0.0148
0.0060
0.1004
0.8789
0.0000
0.0000
car
0.1029
0.0180
0.0000
0.0099
0.8692
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.890
0.911
0.765
0.849
0.440
--
Recall/Completeness
0.866
0.954
0.717
0.879
0.869
--
F1
0.878
0.932
0.740
0.864
0.584
--

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_area16_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8206
0.0225
0.0793
0.0674
0.0102
0.0000
building
0.0319
0.9127
0.0315
0.0220
0.0019
0.0000
low_veg
0.0281
0.0159
0.7338
0.2189
0.0034
0.0000
tree
0.0210
0.0050
0.1052
0.8685
0.0003
0.0000
car
0.1906
0.0032
0.0025
0.0056
0.7981
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.851
0.942
0.794
0.801
0.372
--
Recall/Completeness
0.821
0.913
0.734
0.869
0.798
--
F1
0.836
0.927
0.763
0.833
0.507
--

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_area16_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8584
0.0182
0.0713
0.0443
0.0078
0.0000
building
0.0264
0.9382
0.0216
0.0119
0.0018
0.0000
low_veg
0.0242
0.0100
0.7582
0.2043
0.0034
0.0000
tree
0.0141
0.0024
0.0937
0.8895
0.0002
0.0000
car
0.1438
0.0001
0.0006
0.0000
0.8555
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.882
0.962
0.821
0.825
0.344
--
Recall/Completeness
0.858
0.938
0.758
0.890
0.855
--
F1
0.870
0.950
0.788
0.856
0.491
--

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_area20_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8197
0.0188
0.1007
0.0562
0.0047
0.0000
building
0.0179
0.9242
0.0288
0.0286
0.0006
0.0000
low_veg
0.0577
0.0144
0.7546
0.1712
0.0022
0.0000
tree
0.0061
0.0007
0.0698
0.9234
0.0000
0.0000
car
0.2756
0.0693
0.0224
0.0258
0.6069
0.0000
clutter
0.1110
0.5882
0.2998
0.0006
0.0005
0.0000
Precision/Correctness
0.888
0.868
0.703
0.885
0.632
-nan
Recall/Completeness
0.820
0.924
0.755
0.923
0.607
0.000
F1
0.853
0.895
0.728
0.904
0.619
-nan

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_area20_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8524
0.0115
0.0969
0.0361
0.0031
0.0000
building
0.0158
0.9422
0.0206
0.0208
0.0006
0.0000
low_veg
0.0512
0.0074
0.8001
0.1390
0.0022
0.0000
tree
0.0023
0.0001
0.0580
0.9396
0.0000
0.0000
car
0.2017
0.0782
0.0114
0.0153
0.6935
0.0000
clutter
0.0982
0.6078
0.2935
0.0000
0.0005
0.0000
Precision/Correctness
0.912
0.881
0.727
0.915
0.644
-nan
Recall/Completeness
0.852
0.942
0.800
0.940
0.694
0.000
F1
0.881
0.911
0.762
0.927
0.668
-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_area22_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8681
0.0252
0.0497
0.0459
0.0110
0.0000
building
0.0279
0.9352
0.0209
0.0154
0.0006
0.0000
low_veg
0.0806
0.0369
0.6695
0.2120
0.0010
0.0000
tree
0.0175
0.0032
0.0538
0.9255
0.0001
0.0000
car
0.3271
0.0077
0.0096
0.0180
0.6375
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.903
0.910
0.793
0.816
0.645
--
Recall/Completeness
0.868
0.935
0.670
0.926
0.637
--
F1
0.885
0.922
0.726
0.867
0.641
--

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_area22_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9032
0.0179
0.0448
0.0262
0.0079
0.0000
building
0.0216
0.9560
0.0137
0.0082
0.0006
0.0000
low_veg
0.0768
0.0243
0.7175
0.1803
0.0011
0.0000
tree
0.0069
0.0013
0.0425
0.9493
0.0000
0.0000
car
0.2541
0.0094
0.0054
0.0075
0.7236
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.927
0.940
0.827
0.858
0.671
--
Recall/Completeness
0.903
0.956
0.717
0.949
0.724
--
F1
0.915
0.948
0.769
0.901
0.696
--

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_area24_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.7844
0.0340
0.1221
0.0454
0.0141
0.0000
building
0.0654
0.8695
0.0350
0.0293
0.0008
0.0000
low_veg
0.0283
0.0183
0.8511
0.1018
0.0005
0.0000
tree
0.0141
0.0065
0.1515
0.8277
0.0003
0.0000
car
0.2547
0.0000
0.0001
0.0024
0.7428
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.800
0.921
0.848
0.796
0.531
--
Recall/Completeness
0.784
0.870
0.851
0.828
0.743
--
F1
0.792
0.894
0.849
0.811
0.620
--

Overall accuracy 0.839

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area24_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8167
0.0253
0.1148
0.0322
0.0110
0.0000
building
0.0608
0.8859
0.0268
0.0258
0.0007
0.0000
low_veg
0.0240
0.0144
0.8740
0.0872
0.0005
0.0000
tree
0.0088
0.0034
0.1357
0.8519
0.0002
0.0000
car
0.1777
0.0000
0.0000
0.0002
0.8221
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.828
0.942
0.868
0.822
0.529
--
Recall/Completeness
0.817
0.886
0.874
0.852
0.822
--
F1
0.822
0.913
0.871
0.837
0.644
--

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_area27_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9231
0.0231
0.0242
0.0080
0.0215
0.0000
building
0.0749
0.9020
0.0105
0.0114
0.0012
0.0000
low_veg
0.1050
0.0284
0.6497
0.2161
0.0008
0.0000
tree
0.0165
0.0043
0.0296
0.9496
0.0000
0.0000
car
0.3307
0.0043
0.0035
0.0065
0.6551
0.0000
clutter
0.7428
0.0889
0.0263
0.0364
0.1056
0.0000
Precision/Correctness
0.829
0.958
0.897
0.660
0.734
-nan
Recall/Completeness
0.923
0.902
0.650
0.950
0.655
0.000
F1
0.873
0.929
0.754
0.778
0.692
-nan

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_area27_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9532
0.0150
0.0177
0.0031
0.0110
0.0000
building
0.0606
0.9245
0.0061
0.0077
0.0010
0.0000
low_veg
0.0856
0.0164
0.6978
0.1997
0.0005
0.0000
tree
0.0077
0.0023
0.0208
0.9693
0.0000
0.0000
car
0.2680
0.0021
0.0015
0.0052
0.7232
0.0000
clutter
0.7637
0.0866
0.0064
0.0263
0.1171
0.0000
Precision/Correctness
0.866
0.976
0.930
0.694
0.808
-nan
Recall/Completeness
0.953
0.925
0.698
0.969
0.723
0.000
F1
0.907
0.950
0.797
0.809
0.763
-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_area29_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9304
0.0147
0.0275
0.0139
0.0136
0.0000
building
0.0879
0.8933
0.0090
0.0095
0.0003
0.0000
low_veg
0.0786
0.0286
0.5558
0.3351
0.0019
0.0000
tree
0.0086
0.0021
0.0146
0.9746
0.0000
0.0000
car
0.2559
0.0059
0.0099
0.0083
0.7200
0.0000
clutter
0.5339
0.2428
0.0156
0.0141
0.1936
0.0000
Precision/Correctness
0.876
0.931
0.835
0.646
0.449
-nan
Recall/Completeness
0.930
0.893
0.556
0.975
0.720
0.000
F1
0.902
0.912
0.667
0.777
0.553
-nan

Overall accuracy 0.839

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area29_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9534
0.0095
0.0212
0.0067
0.0092
0.0000
building
0.0829
0.9063
0.0055
0.0052
0.0002
0.0000
low_veg
0.0555
0.0152
0.6037
0.3243
0.0012
0.0000
tree
0.0034
0.0010
0.0103
0.9853
0.0000
0.0000
car
0.1986
0.0027
0.0102
0.0050
0.7834
0.0000
clutter
0.5224
0.2568
0.0116
0.0044
0.2048
0.0000
Precision/Correctness
0.897
0.951
0.871
0.682
0.452
-nan
Recall/Completeness
0.953
0.906
0.604
0.985
0.783
0.000
F1
0.924
0.928
0.713
0.806
0.573
-nan

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_area31_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9432
0.0151
0.0081
0.0056
0.0281
0.0000
building
0.1754
0.8039
0.0034
0.0056
0.0117
0.0000
low_veg
0.0683
0.0073
0.8408
0.0810
0.0026
0.0000
tree
0.0332
0.0034
0.0517
0.9116
0.0002
0.0000
car
0.1448
0.1082
0.0018
0.0091
0.7361
0.0000
clutter
0.3716
0.3807
0.0084
0.0088
0.2305
0.0000
Precision/Correctness
0.821
0.902
0.924
0.863
0.543
-nan
Recall/Completeness
0.943
0.804
0.841
0.912
0.736
0.000
F1
0.878
0.850
0.880
0.887
0.625
-nan

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_area31_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9646
0.0106
0.0068
0.0015
0.0165
0.0000
building
0.1685
0.8181
0.0012
0.0018
0.0104
0.0000
low_veg
0.0402
0.0046
0.8861
0.0680
0.0012
0.0000
tree
0.0103
0.0011
0.0435
0.9450
0.0000
0.0000
car
0.0964
0.1172
0.0008
0.0032
0.7824
0.0000
clutter
0.3129
0.4336
0.0052
0.0029
0.2454
0.0000
Precision/Correctness
0.846
0.917
0.943
0.900
0.569
-nan
Recall/Completeness
0.965
0.818
0.886
0.945
0.782
0.000
F1
0.902
0.865
0.914
0.922
0.659
-nan

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_area33_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9724
0.0116
0.0044
0.0021
0.0095
0.0000
building
0.1724
0.7623
0.0125
0.0498
0.0030
0.0000
low_veg
0.1296
0.0083
0.7863
0.0725
0.0033
0.0000
tree
0.0603
0.0038
0.1428
0.7930
0.0000
0.0000
car
0.3534
0.0012
0.0025
0.0027
0.6402
0.0000
clutter
0.5586
0.1993
0.0012
0.0011
0.2399
0.0000
Precision/Correctness
0.771
0.929
0.856
0.758
0.313
-nan
Recall/Completeness
0.972
0.762
0.786
0.793
0.640
0.000
F1
0.860
0.837
0.820
0.775
0.421
-nan

Overall accuracy 0.807

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
0.9833
0.0072
0.0025
0.0004
0.0065
0.0000
building
0.1664
0.7720
0.0106
0.0485
0.0026
0.0000
low_veg
0.0850
0.0036
0.8363
0.0723
0.0029
0.0000
tree
0.0319
0.0020
0.1331
0.8330
0.0000
0.0000
car
0.2911
0.0011
0.0016
0.0007
0.7054
0.0000
clutter
0.5254
0.2101
0.0007
0.0002
0.2636
0.0000
Precision/Correctness
0.799
0.943
0.876
0.768
0.293
-nan
Recall/Completeness
0.983
0.772
0.836
0.833
0.705
0.000
F1
0.881
0.849
0.856
0.799
0.414
-nan

Overall accuracy 0.830

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
0.8399
0.0373
0.0959
0.0209
0.0059
0.0000
building
0.0597
0.8989
0.0297
0.0095
0.0022
0.0000
low_veg
0.0303
0.0129
0.7173
0.2390
0.0005
0.0000
tree
0.0213
0.0031
0.1116
0.8641
0.0000
0.0000
car
0.4281
0.0091
0.0070
0.0171
0.5387
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.870
0.947
0.754
0.751
0.648
--
Recall/Completeness
0.840
0.899
0.717
0.864
0.539
--
F1
0.854
0.922
0.735
0.803
0.588
--

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
0.8935
0.0321
0.0646
0.0057
0.0041
0.0000
building
0.0456
0.9322
0.0163
0.0039
0.0020
0.0000
low_veg
0.0201
0.0072
0.7446
0.2278
0.0004
0.0000
tree
0.0060
0.0009
0.0860
0.9071
0.0000
0.0000
car
0.3706
0.0084
0.0035
0.0090
0.6085
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.912
0.964
0.819
0.780
0.680
--
Recall/Completeness
0.893
0.932
0.745
0.907
0.608
--
F1
0.903
0.948
0.780
0.839
0.642
--

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_area38_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8974
0.0254
0.0482
0.0174
0.0116
0.0000
building
0.0347
0.9172
0.0269
0.0191
0.0020
0.0000
low_veg
0.0607
0.0125
0.7986
0.1272
0.0009
0.0000
tree
0.0201
0.0039
0.0964
0.8795
0.0002
0.0000
car
0.2828
0.0349
0.0225
0.0115
0.6483
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.881
0.953
0.852
0.791
0.613
--
Recall/Completeness
0.897
0.917
0.799
0.880
0.648
--
F1
0.889
0.935
0.825
0.833
0.630
--

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_area38_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9286
0.0227
0.0340
0.0063
0.0083
0.0000
building
0.0250
0.9446
0.0160
0.0128
0.0016
0.0000
low_veg
0.0449
0.0067
0.8414
0.1063
0.0007
0.0000
tree
0.0087
0.0023
0.0773
0.9116
0.0001
0.0000
car
0.2140
0.0409
0.0181
0.0049
0.7222
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.918
0.966
0.892
0.834
0.647
--
Recall/Completeness
0.929
0.945
0.841
0.912
0.722
--
F1
0.923
0.955
0.866
0.871
0.682
--

Overall accuracy 0.904

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image