Detailled semantic labeling (2D) result


Name T. Forbes et al.
Affiliation Concordia University, Canada
Abbreviation CONC_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
0.878
0.044
0.047
0.021
0.010
0.000
building
0.099
0.864
0.029
0.006
0.002
0.000
low_veg
0.054
0.041
0.718
0.187
0.001
0.000
tree
0.021
0.009
0.107
0.863
0.000
0.000
car
0.163
0.061
0.017
0.006
0.753
0.000
clutter
0.291
0.412
0.037
0.010
0.082
0.167
Precision/Correctness
0.839
0.891
0.774
0.803
0.695
0.900
Recall/Completeness
0.878
0.864
0.718
0.863
0.753
0.167
F1
0.858
0.877
0.745
0.832
0.723
0.282

Overall accuracy 0.828

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
0.906
0.037
0.039
0.011
0.006
0.000
building
0.094
0.879
0.023
0.003
0.002
0.000
low_veg
0.043
0.033
0.751
0.173
0.001
0.000
tree
0.010
0.005
0.092
0.894
0.000
0.000
car
0.104
0.069
0.013
0.003
0.811
0.000
clutter
0.256
0.437
0.035
0.005
0.081
0.187
Precision/Correctness
0.864
0.913
0.807
0.832
0.732
0.906
Recall/Completeness
0.906
0.879
0.751
0.894
0.811
0.187
F1
0.885
0.895
0.778
0.862
0.769
0.310

Overall accuracy 0.856
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8910
0.0535
0.0307
0.0152
0.0096
0.0000
building
0.0794
0.8871
0.0270
0.0053
0.0012
0.0000
low_veg
0.0615
0.0248
0.7086
0.2048
0.0004
0.0000
tree
0.0270
0.0078
0.1285
0.8356
0.0005
0.0006
car
0.1914
0.0200
0.0046
0.0013
0.7828
0.0000
clutter
0.0668
0.0000
0.0123
0.0325
0.0000
0.8884
Precision/Correctness
0.835
0.904
0.791
0.787
0.808
0.990
Recall/Completeness
0.891
0.887
0.709
0.836
0.783
0.888
F1
0.862
0.895
0.747
0.811
0.795
0.937

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_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9167
0.0510
0.0214
0.0053
0.0055
0.0000
building
0.0741
0.9052
0.0171
0.0024
0.0012
0.0000
low_veg
0.0462
0.0147
0.7408
0.1980
0.0003
0.0000
tree
0.0120
0.0035
0.1165
0.8675
0.0003
0.0002
car
0.1127
0.0205
0.0032
0.0001
0.8634
0.0000
clutter
0.0655
0.0000
0.0119
0.0140
0.0000
0.9087
Precision/Correctness
0.868
0.926
0.821
0.814
0.851
0.997
Recall/Completeness
0.917
0.905
0.741
0.867
0.863
0.909
F1
0.892
0.915
0.779
0.840
0.857
0.951

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_area4_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9003
0.0660
0.0146
0.0062
0.0129
0.0000
building
0.0674
0.9140
0.0135
0.0027
0.0024
0.0000
low_veg
0.1272
0.0640
0.4676
0.3315
0.0097
0.0000
tree
0.0592
0.0234
0.0865
0.8303
0.0005
0.0000
car
0.2360
0.0234
0.0021
0.0008
0.7377
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.841
0.956
0.565
0.688
0.658
--
Recall/Completeness
0.900
0.914
0.468
0.830
0.738
--
F1
0.869
0.935
0.512
0.752
0.695
--

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
0.9287
0.0463
0.0123
0.0033
0.0094
0.0000
building
0.0545
0.9290
0.0125
0.0017
0.0022
0.0000
low_veg
0.0915
0.0307
0.5113
0.3589
0.0076
0.0000
tree
0.0265
0.0116
0.0873
0.8745
0.0001
0.0000
car
0.1707
0.0186
0.0006
0.0001
0.8100
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.872
0.973
0.578
0.716
0.675
--
Recall/Completeness
0.929
0.929
0.511
0.874
0.810
--
F1
0.899
0.950
0.542
0.787
0.736
--

Overall accuracy 0.908

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area6_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8636
0.0666
0.0449
0.0125
0.0124
0.0000
building
0.0748
0.8885
0.0307
0.0028
0.0032
0.0000
low_veg
0.0659
0.0418
0.7688
0.1210
0.0024
0.0000
tree
0.0155
0.0061
0.1285
0.8494
0.0005
0.0000
car
0.2128
0.0218
0.0085
0.0021
0.7548
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.847
0.926
0.582
0.935
0.728
--
Recall/Completeness
0.864
0.888
0.769
0.849
0.755
--
F1
0.855
0.907
0.663
0.890
0.741
--

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_area6_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8998
0.0546
0.0333
0.0060
0.0063
0.0000
building
0.0633
0.9078
0.0250
0.0012
0.0027
0.0000
low_veg
0.0516
0.0282
0.8153
0.1030
0.0019
0.0000
tree
0.0056
0.0024
0.1139
0.8779
0.0002
0.0000
car
0.1573
0.0154
0.0062
0.0012
0.8199
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.881
0.948
0.610
0.956
0.785
--
Recall/Completeness
0.900
0.908
0.815
0.878
0.820
--
F1
0.890
0.927
0.698
0.915
0.802
--

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: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8780
0.0388
0.0621
0.0118
0.0079
0.0014
building
0.0628
0.9128
0.0182
0.0054
0.0008
0.0000
low_veg
0.0426
0.0205
0.8583
0.0773
0.0014
0.0000
tree
0.0254
0.0108
0.0988
0.8647
0.0004
0.0000
car
0.1691
0.0261
0.0125
0.0019
0.7905
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.897
0.916
0.780
0.911
0.815
--
Recall/Completeness
0.878
0.913
0.858
0.865
0.791
--
F1
0.887
0.915
0.817
0.887
0.803
--

Overall accuracy 0.877

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
0.9058
0.0333
0.0515
0.0044
0.0034
0.0016
building
0.0548
0.9302
0.0112
0.0032
0.0006
0.0000
low_veg
0.0275
0.0119
0.8958
0.0641
0.0007
0.0000
tree
0.0093
0.0057
0.0813
0.9036
0.0001
0.0000
car
0.1018
0.0255
0.0062
0.0013
0.8652
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.928
0.939
0.819
0.937
0.889
--
Recall/Completeness
0.906
0.930
0.896
0.904
0.865
--
F1
0.917
0.935
0.856
0.920
0.877
--

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_area10_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8148
0.0689
0.0856
0.0223
0.0084
0.0000
building
0.0461
0.9117
0.0292
0.0092
0.0037
0.0000
low_veg
0.0495
0.0422
0.7369
0.1710
0.0004
0.0000
tree
0.0124
0.0102
0.1063
0.8711
0.0000
0.0000
car
0.1042
0.0469
0.0310
0.0053
0.8126
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.930
0.858
0.680
0.815
0.582
--
Recall/Completeness
0.815
0.912
0.737
0.871
0.813
--
F1
0.869
0.884
0.707
0.842
0.678
--

Overall accuracy 0.836

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
0.8491
0.0565
0.0778
0.0107
0.0059
0.0000
building
0.0428
0.9240
0.0239
0.0061
0.0032
0.0000
low_veg
0.0461
0.0286
0.7806
0.1443
0.0003
0.0000
tree
0.0043
0.0051
0.0882
0.9024
0.0000
0.0000
car
0.0583
0.0472
0.0276
0.0018
0.8651
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.944
0.889
0.712
0.858
0.594
--
Recall/Completeness
0.849
0.924
0.781
0.902
0.865
--
F1
0.894
0.906
0.745
0.879
0.704
--

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_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8466
0.0421
0.0638
0.0411
0.0064
0.0000
building
0.1684
0.8043
0.0203
0.0069
0.0002
0.0000
low_veg
0.0590
0.0338
0.6885
0.2173
0.0003
0.0011
tree
0.0094
0.0084
0.1146
0.8675
0.0002
0.0000
car
0.0812
0.0004
0.0045
0.0060
0.9078
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.694
0.891
0.783
0.821
0.805
--
Recall/Completeness
0.847
0.804
0.688
0.868
0.908
--
F1
0.762
0.845
0.733
0.843
0.853
--

Overall accuracy 0.801

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
0.8797
0.0398
0.0550
0.0240
0.0016
0.0000
building
0.1764
0.8095
0.0117
0.0022
0.0002
0.0000
low_veg
0.0578
0.0250
0.7206
0.1952
0.0002
0.0012
tree
0.0046
0.0036
0.0992
0.8926
0.0001
0.0000
car
0.0402
0.0000
0.0009
0.0017
0.9573
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.705
0.918
0.813
0.849
0.911
--
Recall/Completeness
0.880
0.810
0.721
0.893
0.957
--
F1
0.783
0.860
0.764
0.870
0.934
--

Overall accuracy 0.826

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
0.8346
0.0384
0.0807
0.0378
0.0085
0.0000
building
0.0211
0.9549
0.0171
0.0066
0.0003
0.0000
low_veg
0.0792
0.0576
0.6898
0.1725
0.0009
0.0000
tree
0.0278
0.0127
0.1280
0.8314
0.0001
0.0000
car
0.0814
0.0001
0.0006
0.0060
0.9119
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.852
0.858
0.732
0.838
0.516
--
Recall/Completeness
0.835
0.955
0.690
0.831
0.912
--
F1
0.843
0.904
0.710
0.835
0.659
--

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: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8551
0.0339
0.0763
0.0275
0.0073
0.0000
building
0.0150
0.9743
0.0083
0.0023
0.0002
0.0000
low_veg
0.0740
0.0431
0.7205
0.1614
0.0009
0.0000
tree
0.0192
0.0062
0.1155
0.8591
0.0001
0.0000
car
0.0155
0.0000
0.0000
0.0021
0.9824
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.879
0.891
0.755
0.861
0.496
--
Recall/Completeness
0.855
0.974
0.721
0.859
0.982
--
F1
0.867
0.931
0.737
0.860
0.659
--

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_area16_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.7905
0.0349
0.1045
0.0651
0.0051
0.0000
building
0.0718
0.8751
0.0416
0.0111
0.0004
0.0000
low_veg
0.0285
0.0493
0.7252
0.1955
0.0001
0.0014
tree
0.0176
0.0050
0.1221
0.8552
0.0001
0.0000
car
0.0660
0.0295
0.0205
0.0399
0.8441
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.815
0.877
0.759
0.817
0.671
--
Recall/Completeness
0.790
0.875
0.725
0.855
0.844
--
F1
0.802
0.876
0.742
0.836
0.747
--

Overall accuracy 0.810

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
0.8263
0.0310
0.0967
0.0434
0.0027
0.0000
building
0.0698
0.8929
0.0327
0.0043
0.0004
0.0000
low_veg
0.0253
0.0458
0.7429
0.1844
0.0000
0.0015
tree
0.0104
0.0015
0.1092
0.8788
0.0001
0.0000
car
0.0234
0.0371
0.0120
0.0316
0.8960
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.839
0.894
0.785
0.839
0.736
--
Recall/Completeness
0.826
0.893
0.743
0.879
0.896
--
F1
0.833
0.894
0.763
0.858
0.808
--

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_area20_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.7542
0.0875
0.0901
0.0540
0.0142
0.0000
building
0.0278
0.9350
0.0250
0.0101
0.0021
0.0000
low_veg
0.0514
0.0375
0.7320
0.1782
0.0007
0.0002
tree
0.0091
0.0047
0.0837
0.9025
0.0000
0.0000
car
0.0737
0.0372
0.0601
0.0113
0.8177
0.0000
clutter
0.0052
0.9906
0.0017
0.0024
0.0000
0.0000
Precision/Correctness
0.890
0.740
0.714
0.887
0.503
0.000
Recall/Completeness
0.754
0.935
0.732
0.902
0.818
0.000
F1
0.817
0.826
0.723
0.895
0.623
-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_area20_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.7838
0.0798
0.0855
0.0392
0.0116
0.0000
building
0.0262
0.9448
0.0197
0.0071
0.0022
0.0000
low_veg
0.0466
0.0266
0.7732
0.1529
0.0006
0.0002
tree
0.0037
0.0026
0.0700
0.9236
0.0000
0.0000
car
0.0376
0.0313
0.0538
0.0060
0.8713
0.0000
clutter
0.0037
0.9948
0.0006
0.0009
0.0000
0.0000
Precision/Correctness
0.914
0.758
0.741
0.912
0.478
0.000
Recall/Completeness
0.784
0.945
0.773
0.924
0.871
0.000
F1
0.844
0.841
0.757
0.918
0.618
-nan

Overall accuracy 0.845

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
0.8757
0.0338
0.0438
0.0364
0.0102
0.0000
building
0.0475
0.9281
0.0165
0.0069
0.0010
0.0000
low_veg
0.0811
0.0563
0.6779
0.1837
0.0010
0.0000
tree
0.0230
0.0070
0.0740
0.8955
0.0005
0.0000
car
0.1774
0.0259
0.0358
0.0112
0.7496
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.893
0.871
0.780
0.838
0.685
--
Recall/Completeness
0.876
0.928
0.678
0.895
0.750
--
F1
0.884
0.899
0.725
0.866
0.716
--

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_area22_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9091
0.0263
0.0381
0.0198
0.0067
0.0000
building
0.0427
0.9443
0.0086
0.0036
0.0008
0.0000
low_veg
0.0777
0.0439
0.7208
0.1568
0.0008
0.0000
tree
0.0095
0.0033
0.0583
0.9286
0.0002
0.0000
car
0.1187
0.0244
0.0312
0.0059
0.8198
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.917
0.904
0.820
0.876
0.723
--
Recall/Completeness
0.909
0.944
0.721
0.929
0.820
--
F1
0.913
0.924
0.767
0.902
0.769
--

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_area24_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.7705
0.0543
0.1062
0.0499
0.0109
0.0082
building
0.0867
0.8470
0.0477
0.0177
0.0009
0.0000
low_veg
0.0304
0.0639
0.8023
0.1031
0.0004
0.0000
tree
0.0210
0.0119
0.1441
0.8228
0.0002
0.0000
car
0.1364
0.0346
0.0031
0.0015
0.8244
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.764
0.810
0.844
0.798
0.616
--
Recall/Completeness
0.770
0.847
0.802
0.823
0.824
--
F1
0.767
0.828
0.823
0.810
0.705
--

Overall accuracy 0.811

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
0.8034
0.0440
0.0984
0.0379
0.0074
0.0089
building
0.0848
0.8585
0.0406
0.0153
0.0009
0.0000
low_veg
0.0272
0.0623
0.8184
0.0917
0.0004
0.0000
tree
0.0149
0.0077
0.1223
0.8551
0.0001
0.0000
car
0.0943
0.0341
0.0000
0.0000
0.8717
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.785
0.827
0.867
0.821
0.624
--
Recall/Completeness
0.803
0.858
0.818
0.855
0.872
--
F1
0.794
0.842
0.842
0.837
0.727
--

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_area27_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9197
0.0331
0.0251
0.0072
0.0148
0.0001
building
0.1248
0.8504
0.0186
0.0039
0.0022
0.0000
low_veg
0.0827
0.0315
0.6714
0.2136
0.0008
0.0000
tree
0.0158
0.0102
0.0485
0.9249
0.0006
0.0000
car
0.1901
0.0258
0.0056
0.0046
0.7739
0.0000
clutter
0.5257
0.1759
0.1681
0.0091
0.1211
0.0000
Precision/Correctness
0.810
0.940
0.868
0.670
0.807
0.000
Recall/Completeness
0.920
0.850
0.671
0.925
0.774
0.000
F1
0.861
0.893
0.757
0.777
0.790
-nan

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_area27_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9497
0.0235
0.0182
0.0028
0.0057
0.0000
building
0.1151
0.8688
0.0127
0.0016
0.0018
0.0000
low_veg
0.0658
0.0186
0.7117
0.2036
0.0003
0.0000
tree
0.0066
0.0052
0.0317
0.9564
0.0001
0.0000
car
0.1170
0.0261
0.0030
0.0031
0.8508
0.0000
clutter
0.5204
0.1844
0.1573
0.0059
0.1321
0.0000
Precision/Correctness
0.837
0.962
0.906
0.700
0.881
0.000
Recall/Completeness
0.950
0.869
0.712
0.956
0.851
0.000
F1
0.890
0.913
0.797
0.808
0.865
-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_area29_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9008
0.0414
0.0291
0.0176
0.0110
0.0001
building
0.0626
0.9187
0.0117
0.0069
0.0001
0.0000
low_veg
0.0563
0.0304
0.5602
0.3511
0.0020
0.0000
tree
0.0062
0.0045
0.0362
0.9531
0.0000
0.0000
car
0.1344
0.0509
0.0022
0.0059
0.8066
0.0000
clutter
0.3915
0.4863
0.0184
0.0142
0.0896
0.0000
Precision/Correctness
0.906
0.869
0.806
0.628
0.587
0.000
Recall/Completeness
0.901
0.919
0.560
0.953
0.807
0.000
F1
0.904
0.893
0.661
0.757
0.679
-nan

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_area29_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9251
0.0346
0.0228
0.0094
0.0080
0.0001
building
0.0575
0.9321
0.0072
0.0031
0.0000
0.0000
low_veg
0.0348
0.0164
0.6063
0.3410
0.0015
0.0000
tree
0.0019
0.0023
0.0285
0.9674
0.0000
0.0000
car
0.0768
0.0525
0.0012
0.0031
0.8664
0.0000
clutter
0.3697
0.5188
0.0143
0.0062
0.0910
0.0000
Precision/Correctness
0.926
0.891
0.844
0.665
0.592
0.000
Recall/Completeness
0.925
0.932
0.606
0.967
0.866
0.000
F1
0.926
0.911
0.706
0.788
0.703
-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_area31_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9373
0.0195
0.0217
0.0064
0.0148
0.0003
building
0.2933
0.6880
0.0137
0.0032
0.0017
0.0000
low_veg
0.0401
0.0130
0.8903
0.0557
0.0009
0.0000
tree
0.0435
0.0078
0.0825
0.8634
0.0028
0.0000
car
0.1069
0.2202
0.0332
0.0098
0.6300
0.0000
clutter
0.3331
0.3844
0.1262
0.0090
0.1333
0.0140
Precision/Correctness
0.773
0.859
0.831
0.888
0.671
0.814
Recall/Completeness
0.937
0.688
0.890
0.863
0.630
0.014
F1
0.847
0.764
0.860
0.876
0.650
0.028

Overall accuracy 0.811

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
0.9573
0.0159
0.0170
0.0020
0.0076
0.0003
building
0.2883
0.7006
0.0091
0.0009
0.0012
0.0000
low_veg
0.0228
0.0101
0.9199
0.0468
0.0003
0.0000
tree
0.0177
0.0027
0.0665
0.9121
0.0010
0.0000
car
0.0686
0.2504
0.0268
0.0051
0.6491
0.0000
clutter
0.2748
0.4368
0.1354
0.0041
0.1339
0.0150
Precision/Correctness
0.790
0.878
0.865
0.923
0.713
0.820
Recall/Completeness
0.957
0.701
0.920
0.912
0.649
0.015
F1
0.866
0.779
0.892
0.918
0.680
0.029

Overall accuracy 0.835

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
0.9504
0.0325
0.0075
0.0039
0.0054
0.0003
building
0.2159
0.6934
0.0813
0.0050
0.0042
0.0003
low_veg
0.0716
0.0198
0.5442
0.3625
0.0017
0.0002
tree
0.0419
0.0291
0.1254
0.8033
0.0002
0.0000
car
0.2029
0.0736
0.0133
0.0033
0.7069
0.0000
clutter
0.4561
0.3261
0.0030
0.0000
0.1249
0.0898
Precision/Correctness
0.777
0.844
0.677
0.589
0.467
0.956
Recall/Completeness
0.950
0.693
0.544
0.803
0.707
0.090
F1
0.855
0.761
0.603
0.679
0.563
0.164

Overall accuracy 0.748

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
0.9646
0.0283
0.0033
0.0014
0.0024
0.0000
building
0.2127
0.6995
0.0808
0.0030
0.0038
0.0003
low_veg
0.0428
0.0120
0.5559
0.3878
0.0012
0.0003
tree
0.0175
0.0244
0.1158
0.8423
0.0001
0.0000
car
0.1375
0.0919
0.0105
0.0013
0.7587
0.0000
clutter
0.4251
0.3419
0.0019
0.0000
0.1326
0.0985
Precision/Correctness
0.796
0.864
0.691
0.589
0.459
0.974
Recall/Completeness
0.965
0.699
0.556
0.842
0.759
0.099
F1
0.872
0.773
0.616
0.693
0.572
0.179

Overall accuracy 0.765

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
0.8670
0.0429
0.0553
0.0317
0.0029
0.0001
building
0.1109
0.8560
0.0231
0.0064
0.0035
0.0000
low_veg
0.0575
0.0164
0.6389
0.2869
0.0003
0.0000
tree
0.0313
0.0079
0.1021
0.8581
0.0006
0.0000
car
0.2079
0.0509
0.0241
0.0104
0.7067
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.805
0.930
0.782
0.713
0.740
--
Recall/Completeness
0.867
0.856
0.639
0.858
0.707
--
F1
0.835
0.892
0.703
0.779
0.723
--

Overall accuracy 0.805

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
0.9122
0.0375
0.0379
0.0114
0.0008
0.0002
building
0.1033
0.8776
0.0143
0.0015
0.0034
0.0000
low_veg
0.0438
0.0075
0.6717
0.2768
0.0002
0.0000
tree
0.0108
0.0037
0.0832
0.9021
0.0003
0.0000
car
0.1378
0.0521
0.0227
0.0034
0.7839
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.839
0.953
0.835
0.744
0.787
--
Recall/Completeness
0.912
0.878
0.672
0.902
0.784
--
F1
0.874
0.914
0.745
0.815
0.785
--

Overall accuracy 0.841

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
0.8966
0.0298
0.0475
0.0188
0.0073
0.0000
building
0.0855
0.8475
0.0573
0.0074
0.0024
0.0000
low_veg
0.0352
0.0580
0.7432
0.1626
0.0009
0.0000
tree
0.0248
0.0081
0.1045
0.8624
0.0002
0.0000
car
0.1381
0.0399
0.0350
0.0120
0.7750
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.865
0.891
0.813
0.762
0.723
--
Recall/Completeness
0.897
0.847
0.743
0.862
0.775
--
F1
0.880
0.869
0.776
0.809
0.748
--

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_area38_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9274
0.0265
0.0347
0.0075
0.0039
0.0000
building
0.0800
0.8683
0.0466
0.0029
0.0021
0.0000
low_veg
0.0208
0.0555
0.7766
0.1465
0.0007
0.0000
tree
0.0088
0.0049
0.0865
0.8997
0.0000
0.0000
car
0.0908
0.0422
0.0240
0.0066
0.8364
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.895
0.906
0.849
0.798
0.773
--
Recall/Completeness
0.927
0.868
0.777
0.900
0.836
--
F1
0.911
0.887
0.811
0.846
0.804
--

Overall accuracy 0.865

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image