Detailled semantic labeling (2D) result


Name T. Forbes et al.
Affiliation Concordia University, Canada
Abbreviation CONC_4
Strategy (u)nsupervised, (s)upervised, (h)ybrid s


Overall statistics, reference set: full_reference


Number of non processed tiles by this participant: 0
↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.911
0.031
0.039
0.016
0.003
0.000
building
0.055
0.916
0.023
0.005
0.000
0.000
low_veg
0.059
0.025
0.765
0.152
0.000
0.000
tree
0.021
0.006
0.092
0.880
0.000
0.000
car
0.312
0.050
0.011
0.006
0.621
0.000
clutter
0.415
0.323
0.018
0.008
0.052
0.183
Precision/Correctness
0.865
0.927
0.814
0.837
0.838
0.971
Recall/Completeness
0.911
0.916
0.765
0.880
0.621
0.183
F1
0.888
0.922
0.788
0.858
0.714
0.309

Overall accuracy 0.864

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
0.937
0.023
0.031
0.007
0.002
0.000
building
0.048
0.931
0.018
0.003
0.000
0.000
low_veg
0.047
0.015
0.800
0.138
0.000
0.000
tree
0.010
0.003
0.077
0.911
0.000
0.000
car
0.209
0.056
0.006
0.003
0.726
0.000
clutter
0.379
0.345
0.016
0.003
0.054
0.204
Precision/Correctness
0.896
0.949
0.847
0.865
0.862
0.979
Recall/Completeness
0.937
0.931
0.800
0.911
0.726
0.204
F1
0.916
0.940
0.823
0.887
0.788
0.338

Overall accuracy 0.892
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9496
0.0108
0.0251
0.0108
0.0037
0.0000
building
0.0356
0.9406
0.0193
0.0045
0.0000
0.0000
low_veg
0.0764
0.0216
0.7261
0.1756
0.0002
0.0000
tree
0.0313
0.0057
0.0981
0.8638
0.0001
0.0009
car
0.3489
0.0051
0.0008
0.0012
0.6439
0.0000
clutter
0.0177
0.0006
0.0001
0.0225
0.0000
0.9591
Precision/Correctness
0.855
0.958
0.836
0.819
0.910
0.987
Recall/Completeness
0.950
0.941
0.726
0.864
0.644
0.959
F1
0.900
0.949
0.777
0.841
0.754
0.973

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_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9727
0.0066
0.0151
0.0029
0.0026
0.0000
building
0.0281
0.9578
0.0118
0.0023
0.0000
0.0000
low_veg
0.0603
0.0112
0.7575
0.1708
0.0002
0.0000
tree
0.0152
0.0023
0.0844
0.8978
0.0000
0.0004
car
0.2215
0.0044
0.0000
0.0001
0.7740
0.0000
clutter
0.0179
0.0004
0.0000
0.0066
0.0000
0.9751
Precision/Correctness
0.896
0.979
0.868
0.841
0.930
0.995
Recall/Completeness
0.973
0.958
0.758
0.898
0.774
0.975
F1
0.933
0.968
0.809
0.868
0.845
0.985

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: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9230
0.0596
0.0093
0.0043
0.0038
0.0000
building
0.0685
0.9222
0.0072
0.0014
0.0007
0.0000
low_veg
0.1680
0.0545
0.4634
0.3135
0.0007
0.0000
tree
0.0503
0.0173
0.0582
0.8742
0.0000
0.0000
car
0.4605
0.0286
0.0036
0.0002
0.5071
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.830
0.961
0.682
0.724
0.826
--
Recall/Completeness
0.923
0.922
0.463
0.874
0.507
--
F1
0.874
0.941
0.552
0.792
0.628
--

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_area4_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9516
0.0375
0.0069
0.0012
0.0028
0.0000
building
0.0573
0.9350
0.0064
0.0006
0.0008
0.0000
low_veg
0.1301
0.0195
0.5044
0.3454
0.0007
0.0000
tree
0.0227
0.0075
0.0537
0.9161
0.0000
0.0000
car
0.3715
0.0253
0.0008
0.0000
0.6024
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.860
0.978
0.710
0.748
0.840
--
Recall/Completeness
0.952
0.935
0.504
0.916
0.602
--
F1
0.904
0.956
0.590
0.823
0.702
--

Overall accuracy 0.917

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area6_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9143
0.0415
0.0344
0.0070
0.0028
0.0001
building
0.0656
0.9089
0.0224
0.0026
0.0005
0.0000
low_veg
0.0794
0.0262
0.7742
0.1198
0.0003
0.0000
tree
0.0209
0.0035
0.0754
0.9000
0.0003
0.0000
car
0.4435
0.0186
0.0055
0.0015
0.5308
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.843
0.953
0.685
0.944
0.898
--
Recall/Completeness
0.914
0.909
0.774
0.900
0.531
--
F1
0.877
0.931
0.727
0.921
0.667
--

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_area6_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9457
0.0274
0.0238
0.0016
0.0015
0.0001
building
0.0548
0.9271
0.0167
0.0009
0.0004
0.0000
low_veg
0.0645
0.0139
0.8178
0.1038
0.0000
0.0000
tree
0.0091
0.0008
0.0596
0.9302
0.0002
0.0000
car
0.3301
0.0154
0.0034
0.0000
0.6511
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.881
0.974
0.730
0.962
0.935
--
Recall/Completeness
0.946
0.927
0.818
0.930
0.651
--
F1
0.912
0.950
0.771
0.946
0.768
--

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_area8_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8949
0.0320
0.0607
0.0090
0.0034
0.0000
building
0.0279
0.9561
0.0110
0.0047
0.0004
0.0000
low_veg
0.0512
0.0184
0.8695
0.0608
0.0002
0.0000
tree
0.0229
0.0082
0.0815
0.8873
0.0001
0.0000
car
0.3087
0.0232
0.0228
0.0044
0.6410
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.912
0.932
0.805
0.930
0.900
--
Recall/Completeness
0.895
0.956
0.870
0.887
0.641
--
F1
0.903
0.944
0.836
0.908
0.749
--

Overall accuracy 0.898

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
0.9218
0.0248
0.0496
0.0019
0.0020
0.0000
building
0.0185
0.9733
0.0054
0.0025
0.0003
0.0000
low_veg
0.0375
0.0090
0.9051
0.0484
0.0000
0.0000
tree
0.0080
0.0040
0.0628
0.9252
0.0000
0.0000
car
0.1961
0.0265
0.0136
0.0027
0.7611
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.947
0.956
0.846
0.954
0.933
--
Recall/Completeness
0.922
0.973
0.905
0.925
0.761
--
F1
0.934
0.964
0.874
0.940
0.838
--

Overall accuracy 0.930

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
0.8611
0.0635
0.0543
0.0180
0.0031
0.0000
building
0.0312
0.9414
0.0160
0.0112
0.0002
0.0000
low_veg
0.0759
0.0286
0.7636
0.1316
0.0002
0.0000
tree
0.0143
0.0082
0.0831
0.8944
0.0000
0.0000
car
0.2574
0.0404
0.0070
0.0029
0.6923
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.927
0.878
0.765
0.850
0.797
--
Recall/Completeness
0.861
0.941
0.764
0.894
0.692
--
F1
0.893
0.909
0.764
0.871
0.741
--

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_area10_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8956
0.0501
0.0454
0.0069
0.0019
0.0000
building
0.0260
0.9542
0.0114
0.0082
0.0002
0.0000
low_veg
0.0733
0.0149
0.8080
0.1035
0.0002
0.0000
tree
0.0062
0.0041
0.0634
0.9263
0.0000
0.0000
car
0.1769
0.0440
0.0025
0.0010
0.7756
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.943
0.910
0.806
0.893
0.832
--
Recall/Completeness
0.896
0.954
0.808
0.926
0.776
--
F1
0.919
0.932
0.807
0.909
0.803
--

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_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8789
0.0406
0.0490
0.0296
0.0019
0.0000
building
0.1164
0.8633
0.0158
0.0044
0.0000
0.0000
low_veg
0.0431
0.0256
0.7425
0.1885
0.0001
0.0002
tree
0.0090
0.0074
0.1121
0.8715
0.0000
0.0000
car
0.2256
0.0000
0.0136
0.0097
0.7510
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.761
0.912
0.807
0.844
0.923
--
Recall/Completeness
0.879
0.863
0.743
0.871
0.751
--
F1
0.816
0.887
0.773
0.857
0.828
--

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_area12_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9064
0.0378
0.0399
0.0157
0.0002
0.0000
building
0.1212
0.8694
0.0082
0.0011
0.0000
0.0000
low_veg
0.0402
0.0166
0.7754
0.1675
0.0001
0.0003
tree
0.0038
0.0029
0.0955
0.8978
0.0000
0.0000
car
0.1087
0.0000
0.0134
0.0022
0.8758
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.779
0.938
0.837
0.870
0.982
--
Recall/Completeness
0.906
0.869
0.775
0.898
0.876
--
F1
0.838
0.902
0.805
0.884
0.926
--

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_area14_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8429
0.0296
0.0912
0.0313
0.0050
0.0000
building
0.0093
0.9710
0.0130
0.0067
0.0000
0.0000
low_veg
0.0775
0.0578
0.7042
0.1598
0.0007
0.0000
tree
0.0263
0.0135
0.1176
0.8426
0.0000
0.0000
car
0.1761
0.0005
0.0000
0.0072
0.8162
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.863
0.868
0.741
0.852
0.620
--
Recall/Completeness
0.843
0.971
0.704
0.843
0.816
--
F1
0.853
0.917
0.722
0.847
0.704
--

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_area14_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8623
0.0250
0.0872
0.0210
0.0044
0.0000
building
0.0051
0.9862
0.0055
0.0032
0.0000
0.0000
low_veg
0.0726
0.0420
0.7359
0.1488
0.0007
0.0000
tree
0.0180
0.0066
0.1059
0.8695
0.0000
0.0000
car
0.0565
0.0000
0.0000
0.0025
0.9410
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.889
0.903
0.762
0.874
0.607
--
Recall/Completeness
0.862
0.986
0.736
0.870
0.941
--
F1
0.875
0.943
0.749
0.872
0.738
--

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_area16_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8337
0.0177
0.0961
0.0510
0.0014
0.0000
building
0.0360
0.9247
0.0283
0.0110
0.0000
0.0000
low_veg
0.0205
0.0166
0.7866
0.1752
0.0000
0.0011
tree
0.0222
0.0047
0.1215
0.8516
0.0000
0.0000
car
0.2079
0.0342
0.0502
0.0203
0.6875
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.859
0.946
0.783
0.835
0.874
--
Recall/Completeness
0.834
0.925
0.787
0.852
0.687
--
F1
0.846
0.935
0.785
0.843
0.769
--

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_area16_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8699
0.0120
0.0866
0.0312
0.0004
0.0000
building
0.0334
0.9432
0.0197
0.0038
0.0000
0.0000
low_veg
0.0170
0.0098
0.8089
0.1631
0.0000
0.0012
tree
0.0145
0.0015
0.1079
0.8761
0.0000
0.0000
car
0.1212
0.0428
0.0420
0.0139
0.7800
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.888
0.969
0.810
0.857
0.953
--
Recall/Completeness
0.870
0.943
0.809
0.876
0.780
--
F1
0.879
0.956
0.810
0.866
0.858
--

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_area20_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8207
0.0725
0.0569
0.0469
0.0030
0.0000
building
0.0392
0.9306
0.0239
0.0062
0.0001
0.0000
low_veg
0.0523
0.0268
0.7728
0.1479
0.0001
0.0000
tree
0.0074
0.0022
0.0510
0.9393
0.0000
0.0000
car
0.1937
0.0093
0.0486
0.0170
0.7314
0.0000
clutter
0.1089
0.8871
0.0039
0.0002
0.0000
0.0000
Precision/Correctness
0.876
0.773
0.803
0.908
0.824
-nan
Recall/Completeness
0.821
0.931
0.773
0.939
0.731
0.000
F1
0.848
0.844
0.788
0.923
0.775
-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_area20_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8511
0.0645
0.0536
0.0292
0.0016
0.0000
building
0.0380
0.9406
0.0194
0.0019
0.0001
0.0000
low_veg
0.0465
0.0139
0.8206
0.1189
0.0001
0.0000
tree
0.0028
0.0006
0.0389
0.9577
0.0000
0.0000
car
0.1160
0.0047
0.0387
0.0120
0.8287
0.0000
clutter
0.1003
0.8970
0.0026
0.0000
0.0000
0.0000
Precision/Correctness
0.899
0.792
0.833
0.934
0.872
-nan
Recall/Completeness
0.851
0.941
0.821
0.958
0.829
0.000
F1
0.874
0.860
0.827
0.946
0.850
-nan

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_area22_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8927
0.0283
0.0413
0.0338
0.0039
0.0000
building
0.0208
0.9622
0.0112
0.0058
0.0001
0.0000
low_veg
0.0967
0.0454
0.7087
0.1492
0.0000
0.0000
tree
0.0203
0.0045
0.0529
0.9221
0.0001
0.0000
car
0.3749
0.0155
0.0229
0.0109
0.5758
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.896
0.897
0.823
0.863
0.828
--
Recall/Completeness
0.893
0.962
0.709
0.922
0.576
--
F1
0.894
0.929
0.762
0.892
0.679
--

Overall accuracy 0.873

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
0.9253
0.0204
0.0352
0.0166
0.0026
0.0000
building
0.0158
0.9762
0.0054
0.0026
0.0000
0.0000
low_veg
0.0936
0.0311
0.7574
0.1179
0.0000
0.0000
tree
0.0089
0.0014
0.0386
0.9511
0.0000
0.0000
car
0.2874
0.0182
0.0185
0.0036
0.6722
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.920
0.931
0.862
0.904
0.865
--
Recall/Completeness
0.925
0.976
0.757
0.951
0.672
--
F1
0.923
0.953
0.806
0.927
0.757
--

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_area24_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8227
0.0385
0.0967
0.0390
0.0031
0.0000
building
0.0581
0.8934
0.0351
0.0133
0.0002
0.0000
low_veg
0.0327
0.0184
0.8562
0.0924
0.0002
0.0000
tree
0.0184
0.0084
0.1494
0.8237
0.0000
0.0000
car
0.2799
0.0001
0.0068
0.0084
0.7049
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.799
0.917
0.857
0.819
0.826
--
Recall/Completeness
0.823
0.893
0.856
0.824
0.705
--
F1
0.811
0.905
0.857
0.821
0.760
--

Overall accuracy 0.850

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
0.8553
0.0273
0.0878
0.0279
0.0018
0.0000
building
0.0580
0.9022
0.0288
0.0108
0.0002
0.0000
low_veg
0.0300
0.0127
0.8753
0.0818
0.0002
0.0000
tree
0.0119
0.0043
0.1291
0.8547
0.0000
0.0000
car
0.1900
0.0000
0.0000
0.0058
0.8043
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.819
0.944
0.879
0.841
0.855
--
Recall/Completeness
0.855
0.902
0.875
0.855
0.804
--
F1
0.837
0.922
0.877
0.848
0.829
--

Overall accuracy 0.872

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area27_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9372
0.0295
0.0213
0.0069
0.0051
0.0000
building
0.0810
0.8989
0.0136
0.0061
0.0004
0.0000
low_veg
0.0956
0.0300
0.6825
0.1919
0.0001
0.0000
tree
0.0147
0.0056
0.0390
0.9407
0.0000
0.0000
car
0.2949
0.0247
0.0065
0.0063
0.6676
0.0000
clutter
0.6439
0.2162
0.0714
0.0232
0.0452
0.0000
Precision/Correctness
0.834
0.948
0.894
0.691
0.920
-nan
Recall/Completeness
0.937
0.899
0.682
0.941
0.668
0.000
F1
0.883
0.923
0.774
0.797
0.774
-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_area27_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9616
0.0199
0.0150
0.0022
0.0014
0.0000
building
0.0706
0.9163
0.0087
0.0040
0.0003
0.0000
low_veg
0.0792
0.0155
0.7248
0.1806
0.0000
0.0000
tree
0.0066
0.0016
0.0236
0.9682
0.0000
0.0000
car
0.1854
0.0269
0.0043
0.0052
0.7782
0.0000
clutter
0.6613
0.2265
0.0534
0.0124
0.0464
0.0000
Precision/Correctness
0.866
0.969
0.929
0.722
0.967
-nan
Recall/Completeness
0.962
0.916
0.725
0.968
0.778
0.000
F1
0.911
0.942
0.814
0.827
0.862
-nan

Overall accuracy 0.894

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
0.9459
0.0158
0.0220
0.0125
0.0037
0.0000
building
0.0694
0.9161
0.0088
0.0057
0.0000
0.0000
low_veg
0.0645
0.0255
0.6192
0.2902
0.0007
0.0000
tree
0.0050
0.0024
0.0257
0.9668
0.0000
0.0000
car
0.3173
0.0029
0.0018
0.0076
0.6704
0.0000
clutter
0.5953
0.2993
0.0126
0.0115
0.0811
0.0001
Precision/Correctness
0.887
0.927
0.860
0.678
0.687
1.000
Recall/Completeness
0.946
0.916
0.619
0.967
0.670
0.000
F1
0.916
0.921
0.720
0.797
0.679
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_area29_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9665
0.0094
0.0162
0.0052
0.0028
0.0000
building
0.0656
0.9267
0.0049
0.0027
0.0000
0.0000
low_veg
0.0427
0.0111
0.6680
0.2776
0.0006
0.0000
tree
0.0014
0.0008
0.0191
0.9786
0.0000
0.0000
car
0.2245
0.0007
0.0011
0.0045
0.7693
0.0000
clutter
0.5814
0.3174
0.0082
0.0038
0.0890
0.0001
Precision/Correctness
0.908
0.948
0.896
0.717
0.681
1.000
Recall/Completeness
0.966
0.927
0.668
0.979
0.769
0.000
F1
0.936
0.937
0.765
0.827
0.723
0.000

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_area31_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9725
0.0113
0.0089
0.0036
0.0037
0.0001
building
0.0710
0.9146
0.0090
0.0028
0.0025
0.0001
low_veg
0.0418
0.0052
0.9204
0.0324
0.0002
0.0000
tree
0.0441
0.0035
0.0750
0.8771
0.0002
0.0000
car
0.2023
0.2184
0.0090
0.0072
0.5623
0.0008
clutter
0.4924
0.3213
0.0627
0.0072
0.0835
0.0328
Precision/Correctness
0.874
0.913
0.890
0.930
0.802
0.926
Recall/Completeness
0.972
0.915
0.920
0.877
0.562
0.033
F1
0.920
0.914
0.905
0.903
0.661
0.063

Overall accuracy 0.891

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
0.9846
0.0070
0.0061
0.0005
0.0017
0.0000
building
0.0615
0.9310
0.0050
0.0005
0.0020
0.0000
low_veg
0.0232
0.0030
0.9491
0.0246
0.0001
0.0000
tree
0.0166
0.0013
0.0602
0.9218
0.0000
0.0000
car
0.1124
0.2436
0.0039
0.0029
0.6364
0.0009
clutter
0.4420
0.3680
0.0644
0.0022
0.0879
0.0354
Precision/Correctness
0.906
0.927
0.919
0.960
0.823
0.954
Recall/Completeness
0.985
0.931
0.949
0.922
0.636
0.035
F1
0.944
0.929
0.934
0.941
0.718
0.068

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_area33_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9826
0.0083
0.0049
0.0030
0.0012
0.0001
building
0.0633
0.8356
0.0971
0.0036
0.0003
0.0000
low_veg
0.0830
0.0109
0.6811
0.2250
0.0000
0.0000
tree
0.0462
0.0090
0.1294
0.8154
0.0000
0.0000
car
0.4089
0.0029
0.0034
0.0025
0.5823
0.0000
clutter
0.6087
0.2302
0.0010
0.0010
0.0652
0.0940
Precision/Correctness
0.836
0.930
0.706
0.698
0.646
0.993
Recall/Completeness
0.983
0.836
0.681
0.815
0.582
0.094
F1
0.904
0.880
0.693
0.752
0.612
0.172

Overall accuracy 0.823

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area33_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9924
0.0047
0.0017
0.0005
0.0007
0.0000
building
0.0561
0.8437
0.0976
0.0022
0.0003
0.0000
low_veg
0.0511
0.0041
0.7066
0.2382
0.0000
0.0000
tree
0.0216
0.0039
0.1223
0.8522
0.0000
0.0000
car
0.3027
0.0016
0.0010
0.0011
0.6936
0.0000
clutter
0.5824
0.2397
0.0006
0.0007
0.0724
0.1043
Precision/Correctness
0.866
0.945
0.715
0.703
0.632
0.999
Recall/Completeness
0.992
0.844
0.707
0.852
0.694
0.104
F1
0.925
0.891
0.711
0.770
0.661
0.189

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_area35_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8860
0.0415
0.0516
0.0201
0.0009
0.0000
building
0.0500
0.9274
0.0175
0.0045
0.0005
0.0000
low_veg
0.0601
0.0163
0.6875
0.2361
0.0000
0.0000
tree
0.0286
0.0057
0.0876
0.8781
0.0001
0.0000
car
0.2950
0.0627
0.0035
0.0091
0.6296
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.857
0.938
0.817
0.760
0.921
--
Recall/Completeness
0.886
0.927
0.688
0.878
0.630
--
F1
0.871
0.933
0.747
0.815
0.748
--

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_area35_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9282
0.0341
0.0328
0.0046
0.0003
0.0000
building
0.0404
0.9480
0.0100
0.0011
0.0005
0.0000
low_veg
0.0439
0.0078
0.7189
0.2294
0.0000
0.0000
tree
0.0090
0.0014
0.0652
0.9243
0.0000
0.0000
car
0.1702
0.0689
0.0013
0.0047
0.7550
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.901
0.960
0.872
0.786
0.951
--
Recall/Completeness
0.928
0.948
0.719
0.924
0.755
--
F1
0.914
0.954
0.788
0.849
0.842
--

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: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9268
0.0211
0.0387
0.0106
0.0028
0.0000
building
0.0369
0.9043
0.0521
0.0060
0.0007
0.0000
low_veg
0.0394
0.0188
0.8428
0.0987
0.0002
0.0000
tree
0.0244
0.0058
0.1117
0.8581
0.0001
0.0000
car
0.3169
0.0123
0.0293
0.0069
0.6345
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.898
0.949
0.838
0.839
0.861
--
Recall/Completeness
0.927
0.904
0.843
0.858
0.634
--
F1
0.912
0.926
0.840
0.849
0.731
--

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_area38_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9528
0.0183
0.0244
0.0028
0.0018
0.0000
building
0.0293
0.9274
0.0397
0.0031
0.0005
0.0000
low_veg
0.0250
0.0129
0.8784
0.0836
0.0001
0.0000
tree
0.0084
0.0029
0.0900
0.8986
0.0000
0.0000
car
0.2254
0.0110
0.0135
0.0014
0.7487
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.935
0.964
0.877
0.874
0.890
--
Recall/Completeness
0.953
0.927
0.878
0.899
0.749
--
F1
0.944
0.945
0.877
0.886
0.813
--

Overall accuracy 0.914

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image