Detailled semantic labeling (2D) result


Name J. Sherrah (DFCN)
Affiliation DST Group, Australia
Abbreviation DST_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
0.901
0.037
0.041
0.016
0.004
0.000
building
0.060
0.913
0.018
0.008
0.000
0.000
low_veg
0.063
0.026
0.761
0.150
0.000
0.000
tree
0.025
0.007
0.086
0.882
0.000
0.000
car
0.366
0.052
0.013
0.006
0.563
0.000
clutter
0.579
0.332
0.040
0.007
0.042
0.000
Precision/Correctness
0.848
0.918
0.820
0.837
0.803
-nan
Recall/Completeness
0.901
0.913
0.761
0.882
0.563
0.000
F1
0.874
0.916
0.789
0.859
0.662
-nan

Overall accuracy 0.857

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
0.928
0.029
0.032
0.008
0.002
0.000
building
0.053
0.930
0.011
0.005
0.000
0.000
low_veg
0.052
0.016
0.797
0.135
0.000
0.000
tree
0.013
0.003
0.071
0.913
0.000
0.000
car
0.274
0.057
0.009
0.003
0.657
0.000
clutter
0.562
0.354
0.038
0.002
0.044
0.000
Precision/Correctness
0.879
0.940
0.856
0.865
0.844
-nan
Recall/Completeness
0.928
0.930
0.797
0.913
0.657
0.000
F1
0.903
0.935
0.825
0.888
0.739
-nan

Overall accuracy 0.887
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9488
0.0093
0.0271
0.0103
0.0045
0.0000
building
0.0411
0.9325
0.0216
0.0048
0.0000
0.0000
low_veg
0.1101
0.0214
0.7137
0.1541
0.0006
0.0000
tree
0.0418
0.0084
0.0908
0.8589
0.0002
0.0000
car
0.3921
0.0181
0.0002
0.0006
0.5890
0.0000
clutter
0.9751
0.0033
0.0061
0.0155
0.0000
0.0000
Precision/Correctness
0.770
0.955
0.836
0.836
0.874
-nan
Recall/Completeness
0.949
0.933
0.714
0.859
0.589
0.000
F1
0.850
0.944
0.770
0.847
0.704
-nan

Overall accuracy 0.843

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
0.9733
0.0055
0.0160
0.0026
0.0026
0.0000
building
0.0318
0.9531
0.0123
0.0028
0.0000
0.0000
low_veg
0.0949
0.0127
0.7432
0.1486
0.0006
0.0000
tree
0.0245
0.0058
0.0763
0.8933
0.0000
0.0000
car
0.2728
0.0183
0.0000
0.0000
0.7089
0.0000
clutter
0.9888
0.0021
0.0057
0.0034
0.0000
0.0000
Precision/Correctness
0.802
0.974
0.873
0.858
0.913
-nan
Recall/Completeness
0.973
0.953
0.743
0.893
0.709
0.000
F1
0.880
0.963
0.803
0.875
0.798
-nan

Overall accuracy 0.871

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area4_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9065
0.0743
0.0088
0.0052
0.0052
0.0000
building
0.0529
0.9392
0.0059
0.0018
0.0002
0.0000
low_veg
0.1830
0.0575
0.4924
0.2671
0.0000
0.0000
tree
0.0569
0.0174
0.0742
0.8515
0.0001
0.0000
car
0.4681
0.0439
0.0000
0.0017
0.4863
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.848
0.954
0.699
0.738
0.815
--
Recall/Completeness
0.907
0.939
0.492
0.851
0.486
--
F1
0.876
0.946
0.578
0.791
0.609
--

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_area4_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9372
0.0512
0.0060
0.0027
0.0030
0.0000
building
0.0399
0.9545
0.0048
0.0007
0.0001
0.0000
low_veg
0.1470
0.0241
0.5355
0.2935
0.0000
0.0000
tree
0.0288
0.0069
0.0700
0.8943
0.0000
0.0000
car
0.3935
0.0365
0.0000
0.0003
0.5697
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.884
0.972
0.732
0.764
0.875
--
Recall/Completeness
0.937
0.954
0.535
0.894
0.570
--
F1
0.910
0.963
0.619
0.824
0.690
--

Overall accuracy 0.925

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
0.8968
0.0588
0.0320
0.0060
0.0064
0.0000
building
0.0409
0.9378
0.0170
0.0041
0.0002
0.0000
low_veg
0.0808
0.0406
0.7011
0.1772
0.0003
0.0000
tree
0.0169
0.0061
0.0616
0.9153
0.0001
0.0000
car
0.3671
0.0150
0.0066
0.0013
0.6100
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.874
0.936
0.703
0.924
0.851
--
Recall/Completeness
0.897
0.938
0.701
0.915
0.610
--
F1
0.885
0.937
0.702
0.919
0.711
--

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_area6_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9296
0.0431
0.0232
0.0013
0.0028
0.0000
building
0.0309
0.9561
0.0114
0.0016
0.0000
0.0000
low_veg
0.0609
0.0308
0.7461
0.1622
0.0001
0.0000
tree
0.0051
0.0025
0.0490
0.9434
0.0000
0.0000
car
0.2825
0.0089
0.0049
0.0001
0.7035
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.915
0.957
0.749
0.944
0.925
--
Recall/Completeness
0.930
0.956
0.746
0.943
0.704
--
F1
0.922
0.957
0.748
0.944
0.799
--

Overall accuracy 0.922

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
0.8920
0.0344
0.0616
0.0075
0.0045
0.0000
building
0.0282
0.9540
0.0139
0.0039
0.0000
0.0000
low_veg
0.0622
0.0156
0.8650
0.0569
0.0002
0.0000
tree
0.0290
0.0072
0.0876
0.8762
0.0001
0.0000
car
0.3626
0.0130
0.0272
0.0055
0.5917
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.898
0.933
0.795
0.935
0.872
--
Recall/Completeness
0.892
0.954
0.865
0.876
0.592
--
F1
0.895
0.943
0.828
0.905
0.705
--

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_area8_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9179
0.0270
0.0506
0.0021
0.0024
0.0000
building
0.0191
0.9730
0.0064
0.0015
0.0000
0.0000
low_veg
0.0473
0.0074
0.9008
0.0445
0.0000
0.0000
tree
0.0129
0.0035
0.0685
0.9150
0.0000
0.0000
car
0.2670
0.0128
0.0187
0.0043
0.6972
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.934
0.955
0.837
0.958
0.921
--
Recall/Completeness
0.918
0.973
0.901
0.915
0.697
--
F1
0.926
0.964
0.868
0.936
0.793
--

Overall accuracy 0.924

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
0.8301
0.0978
0.0479
0.0210
0.0033
0.0000
building
0.0224
0.9518
0.0132
0.0118
0.0007
0.0000
low_veg
0.0785
0.0410
0.7051
0.1753
0.0001
0.0000
tree
0.0150
0.0093
0.0719
0.9039
0.0000
0.0000
car
0.3001
0.0355
0.0087
0.0020
0.6537
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.928
0.830
0.775
0.817
0.765
--
Recall/Completeness
0.830
0.952
0.705
0.904
0.654
--
F1
0.876
0.887
0.739
0.859
0.705
--

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
0.8646
0.0847
0.0394
0.0093
0.0019
0.0000
building
0.0181
0.9646
0.0080
0.0088
0.0005
0.0000
low_veg
0.0772
0.0268
0.7489
0.1471
0.0001
0.0000
tree
0.0067
0.0046
0.0549
0.9338
0.0000
0.0000
car
0.2155
0.0324
0.0052
0.0000
0.7469
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.944
0.859
0.818
0.859
0.817
--
Recall/Completeness
0.865
0.965
0.749
0.934
0.747
--
F1
0.902
0.909
0.782
0.895
0.780
--

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
0.0309
0.0466
0.0360
0.0023
0.0000
building
0.1757
0.8028
0.0139
0.0076
0.0000
0.0000
low_veg
0.0449
0.0398
0.6893
0.2258
0.0002
0.0000
tree
0.0120
0.0075
0.0871
0.8934
0.0000
0.0000
car
0.3916
0.0026
0.0123
0.0060
0.5875
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.703
0.891
0.828
0.821
0.887
--
Recall/Completeness
0.884
0.803
0.689
0.893
0.588
--
F1
0.783
0.845
0.752
0.856
0.707
--

Overall accuracy 0.814

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
0.9117
0.0265
0.0400
0.0206
0.0013
0.0000
building
0.1843
0.8072
0.0057
0.0028
0.0000
0.0000
low_veg
0.0423
0.0309
0.7262
0.2004
0.0001
0.0000
tree
0.0062
0.0030
0.0743
0.9164
0.0000
0.0000
car
0.2735
0.0009
0.0116
0.0007
0.7133
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.718
0.920
0.856
0.850
0.924
--
Recall/Completeness
0.912
0.807
0.726
0.916
0.713
--
F1
0.803
0.860
0.786
0.882
0.805
--

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: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8239
0.0742
0.0672
0.0312
0.0035
0.0000
building
0.0225
0.9516
0.0193
0.0066
0.0000
0.0000
low_veg
0.0748
0.0598
0.7034
0.1615
0.0005
0.0000
tree
0.0274
0.0135
0.1005
0.8585
0.0000
0.0000
car
0.1869
0.0000
0.0003
0.0125
0.8003
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.853
0.820
0.773
0.853
0.698
--
Recall/Completeness
0.824
0.952
0.703
0.859
0.800
--
F1
0.838
0.881
0.737
0.856
0.746
--

Overall accuracy 0.827

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
0.8417
0.0712
0.0629
0.0215
0.0027
0.0000
building
0.0173
0.9698
0.0104
0.0024
0.0000
0.0000
low_veg
0.0700
0.0442
0.7364
0.1490
0.0004
0.0000
tree
0.0191
0.0069
0.0891
0.8849
0.0000
0.0000
car
0.0777
0.0000
0.0000
0.0090
0.9132
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.879
0.850
0.797
0.876
0.709
--
Recall/Completeness
0.842
0.970
0.736
0.885
0.913
--
F1
0.860
0.906
0.766
0.880
0.798
--

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_area16_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8027
0.0390
0.1034
0.0530
0.0019
0.0000
building
0.0245
0.9391
0.0244
0.0120
0.0000
0.0000
low_veg
0.0318
0.0232
0.8093
0.1357
0.0000
0.0000
tree
0.0234
0.0077
0.1007
0.8682
0.0000
0.0000
car
0.2635
0.0090
0.0549
0.0098
0.6628
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.844
0.914
0.807
0.863
0.829
--
Recall/Completeness
0.803
0.939
0.809
0.868
0.663
--
F1
0.823
0.926
0.808
0.866
0.736
--

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_area16_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8376
0.0348
0.0939
0.0329
0.0008
0.0000
building
0.0209
0.9605
0.0140
0.0046
0.0000
0.0000
low_veg
0.0292
0.0172
0.8340
0.1197
0.0000
0.0000
tree
0.0159
0.0037
0.0881
0.8923
0.0000
0.0000
car
0.1947
0.0101
0.0477
0.0043
0.7433
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.872
0.936
0.834
0.888
0.904
--
Recall/Completeness
0.838
0.960
0.834
0.892
0.743
--
F1
0.854
0.948
0.834
0.890
0.816
--

Overall accuracy 0.879

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
0.8520
0.0305
0.0678
0.0463
0.0034
0.0000
building
0.0302
0.9365
0.0270
0.0063
0.0000
0.0000
low_veg
0.0557
0.0232
0.7344
0.1867
0.0000
0.0000
tree
0.0079
0.0018
0.0521
0.9382
0.0000
0.0000
car
0.2221
0.0069
0.0625
0.0147
0.6937
0.0000
clutter
0.0351
0.9064
0.0565
0.0021
0.0000
0.0000
Precision/Correctness
0.892
0.810
0.775
0.892
0.803
-nan
Recall/Completeness
0.852
0.937
0.734
0.938
0.694
0.000
F1
0.871
0.869
0.754
0.915
0.744
-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_area20_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8847
0.0216
0.0621
0.0294
0.0022
0.0000
building
0.0283
0.9488
0.0212
0.0017
0.0000
0.0000
low_veg
0.0503
0.0132
0.7797
0.1568
0.0000
0.0000
tree
0.0034
0.0006
0.0407
0.9554
0.0000
0.0000
car
0.1250
0.0009
0.0609
0.0031
0.8102
0.0000
clutter
0.0324
0.9165
0.0502
0.0009
0.0000
0.0000
Precision/Correctness
0.914
0.828
0.806
0.919
0.840
-nan
Recall/Completeness
0.885
0.949
0.780
0.955
0.810
0.000
F1
0.899
0.884
0.793
0.937
0.825
-nan

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_area22_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8992
0.0231
0.0448
0.0281
0.0049
0.0000
building
0.0328
0.9459
0.0158
0.0053
0.0002
0.0000
low_veg
0.0928
0.0398
0.6933
0.1739
0.0002
0.0000
tree
0.0242
0.0045
0.0583
0.9128
0.0001
0.0000
car
0.4133
0.0000
0.0237
0.0121
0.5509
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.888
0.910
0.804
0.854
0.785
--
Recall/Completeness
0.899
0.946
0.693
0.913
0.551
--
F1
0.894
0.928
0.744
0.882
0.648
--

Overall accuracy 0.866

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
0.9300
0.0160
0.0377
0.0132
0.0032
0.0000
building
0.0257
0.9635
0.0089
0.0018
0.0001
0.0000
low_veg
0.0901
0.0256
0.7383
0.1458
0.0002
0.0000
tree
0.0110
0.0018
0.0433
0.9439
0.0000
0.0000
car
0.3339
0.0000
0.0197
0.0055
0.6409
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.915
0.942
0.845
0.891
0.826
--
Recall/Completeness
0.930
0.964
0.738
0.944
0.641
--
F1
0.922
0.953
0.788
0.917
0.722
--

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_area24_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8103
0.0401
0.1063
0.0366
0.0068
0.0000
building
0.0711
0.8805
0.0293
0.0191
0.0000
0.0000
low_veg
0.0268
0.0203
0.8696
0.0833
0.0000
0.0000
tree
0.0169
0.0080
0.1366
0.8385
0.0000
0.0000
car
0.2932
0.0000
0.0110
0.0009
0.6948
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.798
0.911
0.865
0.831
0.723
--
Recall/Completeness
0.810
0.880
0.870
0.838
0.695
--
F1
0.804
0.895
0.867
0.835
0.708
--

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_area24_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8425
0.0310
0.0962
0.0256
0.0047
0.0000
building
0.0689
0.8925
0.0219
0.0167
0.0000
0.0000
low_veg
0.0236
0.0152
0.8903
0.0709
0.0001
0.0000
tree
0.0102
0.0042
0.1182
0.8674
0.0000
0.0000
car
0.1998
0.0000
0.0040
0.0000
0.7963
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.822
0.935
0.887
0.856
0.758
--
Recall/Completeness
0.842
0.892
0.890
0.867
0.796
--
F1
0.832
0.913
0.889
0.862
0.776
--

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_area27_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9355
0.0262
0.0219
0.0068
0.0096
0.0000
building
0.0707
0.9090
0.0137
0.0063
0.0003
0.0000
low_veg
0.1036
0.0261
0.6699
0.2002
0.0002
0.0000
tree
0.0176
0.0069
0.0328
0.9425
0.0002
0.0000
car
0.3861
0.0039
0.0096
0.0055
0.5950
0.0000
clutter
0.6482
0.1358
0.1175
0.0073
0.0912
0.0000
Precision/Correctness
0.831
0.956
0.893
0.683
0.849
-nan
Recall/Completeness
0.935
0.909
0.670
0.942
0.595
0.000
F1
0.880
0.932
0.766
0.792
0.700
-nan

Overall accuracy 0.862

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area27_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9617
0.0166
0.0151
0.0027
0.0039
0.0000
building
0.0583
0.9294
0.0081
0.0041
0.0002
0.0000
low_veg
0.0859
0.0135
0.7122
0.1883
0.0000
0.0000
tree
0.0093
0.0029
0.0208
0.9669
0.0001
0.0000
car
0.2902
0.0027
0.0069
0.0044
0.6959
0.0000
clutter
0.6603
0.1478
0.0915
0.0008
0.0997
0.0000
Precision/Correctness
0.867
0.976
0.930
0.713
0.917
-nan
Recall/Completeness
0.962
0.929
0.712
0.967
0.696
0.000
F1
0.912
0.952
0.807
0.821
0.791
-nan

Overall accuracy 0.895

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
0.9414
0.0178
0.0239
0.0129
0.0039
0.0000
building
0.0197
0.9635
0.0097
0.0071
0.0000
0.0000
low_veg
0.0752
0.0248
0.5700
0.3299
0.0001
0.0000
tree
0.0059
0.0056
0.0202
0.9682
0.0000
0.0000
car
0.3644
0.0081
0.0030
0.0121
0.6124
0.0000
clutter
0.5152
0.4055
0.0236
0.0114
0.0443
0.0000
Precision/Correctness
0.915
0.916
0.843
0.651
0.732
-nan
Recall/Completeness
0.941
0.963
0.570
0.968
0.612
0.000
F1
0.928
0.939
0.680
0.779
0.667
-nan

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_area29_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9641
0.0105
0.0172
0.0057
0.0024
0.0000
building
0.0144
0.9768
0.0051
0.0036
0.0000
0.0000
low_veg
0.0548
0.0111
0.6112
0.3228
0.0000
0.0000
tree
0.0018
0.0025
0.0146
0.9811
0.0000
0.0000
car
0.2729
0.0034
0.0024
0.0096
0.7117
0.0000
clutter
0.5004
0.4321
0.0178
0.0043
0.0454
0.0000
Precision/Correctness
0.937
0.938
0.885
0.685
0.761
-nan
Recall/Completeness
0.964
0.977
0.611
0.981
0.712
0.000
F1
0.950
0.957
0.723
0.807
0.736
-nan

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_area31_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9611
0.0186
0.0105
0.0039
0.0059
0.0000
building
0.1623
0.8162
0.0160
0.0032
0.0023
0.0000
low_veg
0.0398
0.0041
0.9138
0.0423
0.0000
0.0000
tree
0.0405
0.0044
0.0581
0.8968
0.0002
0.0000
car
0.2827
0.2420
0.0145
0.0067
0.4541
0.0000
clutter
0.4742
0.3664
0.1095
0.0092
0.0407
0.0000
Precision/Correctness
0.821
0.885
0.876
0.917
0.790
-nan
Recall/Completeness
0.961
0.816
0.914
0.897
0.454
0.000
F1
0.885
0.849
0.894
0.907
0.577
-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
0.9763
0.0131
0.0069
0.0007
0.0029
0.0000
building
0.1544
0.8318
0.0115
0.0004
0.0019
0.0000
low_veg
0.0224
0.0016
0.9412
0.0348
0.0000
0.0000
tree
0.0150
0.0009
0.0432
0.9410
0.0000
0.0000
car
0.2057
0.2652
0.0092
0.0020
0.5179
0.0000
clutter
0.4247
0.4090
0.1182
0.0034
0.0448
0.0000
Precision/Correctness
0.847
0.905
0.906
0.947
0.830
-nan
Recall/Completeness
0.976
0.832
0.941
0.941
0.518
0.000
F1
0.907
0.867
0.923
0.944
0.638
-nan

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_area33_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9756
0.0114
0.0085
0.0021
0.0025
0.0000
building
0.1633
0.7741
0.0205
0.0400
0.0021
0.0000
low_veg
0.0734
0.0108
0.8460
0.0690
0.0007
0.0000
tree
0.0466
0.0095
0.1461
0.7978
0.0000
0.0000
car
0.4250
0.0192
0.0114
0.0032
0.5412
0.0000
clutter
0.7624
0.1496
0.0030
0.0019
0.0831
0.0000
Precision/Correctness
0.773
0.936
0.840
0.783
0.529
-nan
Recall/Completeness
0.976
0.774
0.846
0.798
0.541
0.000
F1
0.863
0.847
0.843
0.790
0.535
-nan

Overall accuracy 0.820

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
0.9861
0.0084
0.0038
0.0004
0.0014
0.0000
building
0.1574
0.7851
0.0159
0.0397
0.0019
0.0000
low_veg
0.0436
0.0075
0.8800
0.0682
0.0007
0.0000
tree
0.0206
0.0056
0.1342
0.8396
0.0000
0.0000
car
0.3261
0.0234
0.0091
0.0014
0.6399
0.0000
clutter
0.7437
0.1609
0.0022
0.0009
0.0924
0.0000
Precision/Correctness
0.797
0.947
0.868
0.793
0.521
-nan
Recall/Completeness
0.986
0.785
0.880
0.840
0.640
0.000
F1
0.882
0.858
0.874
0.816
0.575
-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_area35_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8769
0.0336
0.0754
0.0125
0.0016
0.0000
building
0.0664
0.9060
0.0236
0.0038
0.0003
0.0000
low_veg
0.0547
0.0125
0.7223
0.2104
0.0002
0.0000
tree
0.0388
0.0059
0.1233
0.8320
0.0001
0.0000
car
0.3808
0.0262
0.0018
0.0081
0.5831
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.836
0.949
0.768
0.776
0.893
--
Recall/Completeness
0.877
0.906
0.722
0.832
0.583
--
F1
0.856
0.927
0.745
0.803
0.706
--

Overall accuracy 0.834

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
0.9172
0.0275
0.0521
0.0026
0.0007
0.0000
building
0.0558
0.9301
0.0132
0.0007
0.0002
0.0000
low_veg
0.0392
0.0056
0.7502
0.2049
0.0002
0.0000
tree
0.0144
0.0016
0.0967
0.8873
0.0000
0.0000
car
0.2780
0.0256
0.0000
0.0030
0.6934
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.882
0.968
0.826
0.799
0.936
--
Recall/Completeness
0.917
0.930
0.750
0.887
0.693
--
F1
0.899
0.949
0.786
0.841
0.797
--

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
0.8999
0.0349
0.0503
0.0118
0.0031
0.0000
building
0.0229
0.9370
0.0339
0.0057
0.0004
0.0000
low_veg
0.0434
0.0145
0.8429
0.0992
0.0001
0.0000
tree
0.0344
0.0072
0.1089
0.8495
0.0000
0.0000
car
0.4132
0.0392
0.0340
0.0062
0.5074
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.894
0.940
0.844
0.836
0.835
--
Recall/Completeness
0.900
0.937
0.843
0.849
0.507
--
F1
0.897
0.938
0.843
0.843
0.631
--

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_area38_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9269
0.0316
0.0358
0.0035
0.0021
0.0000
building
0.0161
0.9609
0.0199
0.0027
0.0004
0.0000
low_veg
0.0281
0.0076
0.8810
0.0832
0.0000
0.0000
tree
0.0188
0.0040
0.0865
0.8907
0.0001
0.0000
car
0.3242
0.0402
0.0228
0.0011
0.6117
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.933
0.956
0.886
0.873
0.864
--
Recall/Completeness
0.927
0.961
0.881
0.891
0.612
--
F1
0.930
0.959
0.883
0.882
0.716
--

Overall accuracy 0.914

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image