Detailled semantic labeling (2D) result


Name W. Sun
Affiliation Univ. of Calgary, Canada
Abbreviation UCal5
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
0.904
0.032
0.042
0.018
0.005
0.000
building
0.041
0.931
0.023
0.005
0.000
0.000
low_veg
0.058
0.026
0.779
0.137
0.000
0.000
tree
0.022
0.006
0.091
0.880
0.000
0.000
car
0.230
0.030
0.009
0.005
0.724
0.002
clutter
0.313
0.307
0.012
0.007
0.016
0.345
Precision/Correctness
0.881
0.928
0.814
0.848
0.845
0.943
Recall/Completeness
0.904
0.931
0.779
0.880
0.724
0.345
F1
0.892
0.930
0.796
0.864
0.780
0.505

Overall accuracy 0.871

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
0.930
0.025
0.034
0.009
0.003
0.000
building
0.033
0.949
0.016
0.002
0.000
0.000
low_veg
0.046
0.017
0.815
0.121
0.000
0.000
tree
0.011
0.002
0.075
0.912
0.000
0.000
car
0.128
0.034
0.005
0.002
0.828
0.003
clutter
0.274
0.327
0.009
0.003
0.016
0.371
Precision/Correctness
0.913
0.948
0.849
0.878
0.888
0.969
Recall/Completeness
0.930
0.949
0.815
0.912
0.828
0.371
F1
0.922
0.948
0.832
0.895
0.857
0.537

Overall accuracy 0.901
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9429
0.0193
0.0204
0.0126
0.0049
0.0000
building
0.0342
0.9453
0.0170
0.0036
0.0000
0.0000
low_veg
0.0849
0.0197
0.7159
0.1793
0.0002
0.0000
tree
0.0309
0.0053
0.0833
0.8790
0.0003
0.0012
car
0.2470
0.0288
0.0002
0.0010
0.7230
0.0000
clutter
0.0220
0.0000
0.0029
0.0146
0.0000
0.9605
Precision/Correctness
0.854
0.950
0.855
0.819
0.894
0.984
Recall/Completeness
0.943
0.945
0.716
0.879
0.723
0.961
F1
0.896
0.948
0.779
0.848
0.799
0.972

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_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9652
0.0148
0.0126
0.0041
0.0034
0.0000
building
0.0257
0.9643
0.0093
0.0006
0.0000
0.0000
low_veg
0.0660
0.0117
0.7490
0.1732
0.0002
0.0000
tree
0.0153
0.0019
0.0706
0.9116
0.0002
0.0005
car
0.1145
0.0261
0.0000
0.0002
0.8592
0.0000
clutter
0.0227
0.0000
0.0026
0.0039
0.0000
0.9708
Precision/Correctness
0.896
0.969
0.887
0.842
0.917
0.994
Recall/Completeness
0.965
0.964
0.749
0.912
0.859
0.971
F1
0.929
0.967
0.812
0.875
0.887
0.982

Overall accuracy 0.899

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
0.9221
0.0562
0.0123
0.0047
0.0047
0.0000
building
0.0584
0.9325
0.0073
0.0013
0.0005
0.0000
low_veg
0.1442
0.0683
0.5627
0.2229
0.0018
0.0000
tree
0.0484
0.0143
0.0885
0.8485
0.0003
0.0000
car
0.3019
0.0109
0.0015
0.0028
0.6830
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.854
0.963
0.677
0.771
0.851
--
Recall/Completeness
0.922
0.932
0.563
0.849
0.683
--
F1
0.887
0.947
0.615
0.808
0.758
--

Overall accuracy 0.904

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
0.9502
0.0367
0.0085
0.0019
0.0027
0.0000
building
0.0454
0.9476
0.0060
0.0004
0.0005
0.0000
low_veg
0.1061
0.0434
0.6037
0.2457
0.0011
0.0000
tree
0.0215
0.0056
0.0790
0.8939
0.0000
0.0000
car
0.1841
0.0076
0.0002
0.0017
0.8064
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.888
0.978
0.714
0.798
0.889
--
Recall/Completeness
0.950
0.948
0.604
0.894
0.806
--
F1
0.918
0.963
0.654
0.843
0.846
--

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_area6_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8937
0.0505
0.0371
0.0139
0.0048
0.0001
building
0.0429
0.9404
0.0133
0.0034
0.0001
0.0000
low_veg
0.0950
0.0266
0.7365
0.1413
0.0005
0.0000
tree
0.0162
0.0046
0.0641
0.9150
0.0001
0.0000
car
0.3563
0.0243
0.0015
0.0014
0.6165
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.867
0.947
0.708
0.930
0.884
--
Recall/Completeness
0.894
0.940
0.737
0.915
0.617
--
F1
0.880
0.944
0.722
0.923
0.726
--

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_area6_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9264
0.0366
0.0283
0.0064
0.0023
0.0000
building
0.0327
0.9581
0.0083
0.0010
0.0000
0.0000
low_veg
0.0806
0.0103
0.7880
0.1209
0.0001
0.0000
tree
0.0061
0.0015
0.0507
0.9417
0.0000
0.0000
car
0.2573
0.0216
0.0004
0.0001
0.7206
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.906
0.968
0.754
0.953
0.939
--
Recall/Completeness
0.926
0.958
0.788
0.942
0.721
--
F1
0.916
0.963
0.771
0.947
0.815
--

Overall accuracy 0.926

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
0.8883
0.0341
0.0604
0.0126
0.0041
0.0005
building
0.0361
0.9464
0.0150
0.0024
0.0000
0.0000
low_veg
0.0459
0.0163
0.8857
0.0513
0.0008
0.0000
tree
0.0284
0.0065
0.0798
0.8850
0.0001
0.0003
car
0.2386
0.0078
0.0179
0.0050
0.7306
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.908
0.933
0.806
0.935
0.894
--
Recall/Completeness
0.888
0.946
0.886
0.885
0.731
--
F1
0.898
0.940
0.844
0.909
0.804
--

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
0.9166
0.0264
0.0504
0.0045
0.0017
0.0006
building
0.0274
0.9646
0.0074
0.0007
0.0000
0.0000
low_veg
0.0296
0.0080
0.9231
0.0389
0.0004
0.0000
tree
0.0124
0.0027
0.0615
0.9231
0.0000
0.0002
car
0.1347
0.0075
0.0115
0.0040
0.8423
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.944
0.956
0.847
0.960
0.947
--
Recall/Completeness
0.917
0.965
0.923
0.923
0.842
--
F1
0.930
0.960
0.883
0.941
0.891
--

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
0.8482
0.0603
0.0653
0.0205
0.0057
0.0000
building
0.0388
0.9351
0.0174
0.0082
0.0005
0.0000
low_veg
0.0870
0.0299
0.7293
0.1537
0.0000
0.0000
tree
0.0178
0.0083
0.0862
0.8876
0.0000
0.0000
car
0.1859
0.0289
0.0104
0.0019
0.7729
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.915
0.881
0.734
0.833
0.706
--
Recall/Completeness
0.848
0.935
0.729
0.888
0.773
--
F1
0.880
0.907
0.732
0.859
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_area10_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8768
0.0499
0.0593
0.0095
0.0045
0.0000
building
0.0324
0.9492
0.0128
0.0053
0.0003
0.0000
low_veg
0.0819
0.0171
0.7738
0.1272
0.0000
0.0000
tree
0.0082
0.0039
0.0673
0.9206
0.0000
0.0000
car
0.0995
0.0315
0.0057
0.0000
0.8633
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.934
0.909
0.769
0.875
0.714
--
Recall/Completeness
0.877
0.949
0.774
0.921
0.863
--
F1
0.905
0.928
0.771
0.897
0.781
--

Overall accuracy 0.886

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8782
0.0335
0.0553
0.0301
0.0029
0.0000
building
0.0196
0.9577
0.0170
0.0057
0.0000
0.0000
low_veg
0.0393
0.0237
0.7822
0.1538
0.0001
0.0009
tree
0.0101
0.0057
0.1117
0.8725
0.0000
0.0000
car
0.1876
0.0000
0.0045
0.0102
0.7977
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.863
0.930
0.812
0.866
0.899
--
Recall/Completeness
0.878
0.958
0.782
0.873
0.798
--
F1
0.870
0.944
0.797
0.869
0.845
--

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_area12_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9061
0.0308
0.0470
0.0153
0.0007
0.0000
building
0.0175
0.9734
0.0079
0.0012
0.0000
0.0000
low_veg
0.0362
0.0146
0.8173
0.1308
0.0000
0.0010
tree
0.0046
0.0018
0.0931
0.9006
0.0000
0.0000
car
0.0791
0.0000
0.0029
0.0023
0.9156
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.892
0.954
0.844
0.894
0.968
--
Recall/Completeness
0.906
0.973
0.817
0.901
0.916
--
F1
0.899
0.963
0.830
0.897
0.941
--

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_area14_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8138
0.0404
0.1081
0.0317
0.0060
0.0000
building
0.0137
0.9643
0.0172
0.0045
0.0000
0.0003
low_veg
0.0681
0.0528
0.7193
0.1593
0.0005
0.0000
tree
0.0252
0.0147
0.1181
0.8420
0.0000
0.0000
car
0.1188
0.0000
0.0000
0.0033
0.8779
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.868
0.860
0.731
0.853
0.607
--
Recall/Completeness
0.814
0.964
0.719
0.842
0.878
--
F1
0.840
0.909
0.725
0.848
0.718
--

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: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8339
0.0354
0.1048
0.0208
0.0052
0.0000
building
0.0108
0.9799
0.0079
0.0012
0.0000
0.0003
low_veg
0.0631
0.0379
0.7500
0.1486
0.0005
0.0000
tree
0.0171
0.0077
0.1056
0.8696
0.0000
0.0000
car
0.0252
0.0000
0.0000
0.0000
0.9748
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.893
0.894
0.752
0.875
0.593
--
Recall/Completeness
0.834
0.980
0.750
0.870
0.975
--
F1
0.862
0.935
0.751
0.872
0.737
--

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_area16_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8303
0.0319
0.0866
0.0481
0.0031
0.0000
building
0.0190
0.9455
0.0252
0.0102
0.0001
0.0000
low_veg
0.0156
0.0165
0.8736
0.0940
0.0001
0.0001
tree
0.0233
0.0058
0.1251
0.8458
0.0000
0.0000
car
0.1262
0.0037
0.0417
0.0010
0.8274
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.884
0.934
0.802
0.893
0.770
--
Recall/Completeness
0.830
0.946
0.874
0.846
0.827
--
F1
0.856
0.940
0.836
0.869
0.798
--

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_area16_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8649
0.0277
0.0770
0.0289
0.0016
0.0000
building
0.0151
0.9701
0.0107
0.0041
0.0000
0.0000
low_veg
0.0113
0.0108
0.8983
0.0794
0.0001
0.0001
tree
0.0157
0.0025
0.1103
0.8715
0.0000
0.0000
car
0.0519
0.0004
0.0309
0.0000
0.9168
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.916
0.954
0.831
0.918
0.842
--
Recall/Completeness
0.865
0.970
0.898
0.871
0.917
--
F1
0.890
0.962
0.863
0.894
0.878
--

Overall accuracy 0.896

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
0.8741
0.0434
0.0367
0.0426
0.0030
0.0002
building
0.0069
0.9759
0.0114
0.0058
0.0000
0.0000
low_veg
0.0655
0.0304
0.7349
0.1691
0.0000
0.0001
tree
0.0087
0.0024
0.0466
0.9422
0.0000
0.0000
car
0.0899
0.0001
0.0165
0.0081
0.8854
0.0000
clutter
0.0024
0.9963
0.0000
0.0013
0.0000
0.0000
Precision/Correctness
0.908
0.789
0.833
0.901
0.859
0.000
Recall/Completeness
0.874
0.976
0.735
0.942
0.885
0.000
F1
0.891
0.873
0.781
0.921
0.872
-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_area20_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9077
0.0332
0.0340
0.0243
0.0008
0.0002
building
0.0048
0.9866
0.0073
0.0014
0.0000
0.0000
low_veg
0.0591
0.0193
0.7813
0.1401
0.0000
0.0001
tree
0.0035
0.0005
0.0348
0.9612
0.0000
0.0000
car
0.0148
0.0000
0.0031
0.0013
0.9808
0.0000
clutter
0.0001
0.9995
0.0000
0.0004
0.0000
0.0000
Precision/Correctness
0.932
0.810
0.865
0.928
0.950
0.000
Recall/Completeness
0.908
0.987
0.781
0.961
0.981
0.000
F1
0.920
0.889
0.821
0.944
0.965
-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_area22_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9040
0.0201
0.0391
0.0299
0.0069
0.0000
building
0.0171
0.9645
0.0114
0.0068
0.0002
0.0000
low_veg
0.0835
0.0347
0.7393
0.1418
0.0007
0.0000
tree
0.0248
0.0038
0.0604
0.9108
0.0001
0.0000
car
0.2032
0.0062
0.0045
0.0109
0.7644
0.0107
clutter
--
--
--
--
--
--
Precision/Correctness
0.908
0.922
0.824
0.869
0.778
--
Recall/Completeness
0.904
0.965
0.739
0.911
0.764
--
F1
0.906
0.943
0.779
0.890
0.771
--

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_area22_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9352
0.0128
0.0325
0.0151
0.0044
0.0000
building
0.0107
0.9822
0.0043
0.0026
0.0002
0.0000
low_veg
0.0799
0.0209
0.7859
0.1128
0.0005
0.0000
tree
0.0108
0.0011
0.0436
0.9444
0.0000
0.0000
car
0.1103
0.0076
0.0016
0.0035
0.8634
0.0136
clutter
--
--
--
--
--
--
Precision/Correctness
0.934
0.954
0.866
0.908
0.816
--
Recall/Completeness
0.935
0.982
0.786
0.944
0.863
--
F1
0.934
0.968
0.824
0.926
0.839
--

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_area24_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8299
0.0360
0.0934
0.0342
0.0065
0.0000
building
0.0602
0.8713
0.0604
0.0081
0.0000
0.0000
low_veg
0.0268
0.0133
0.8767
0.0832
0.0000
0.0000
tree
0.0173
0.0065
0.1502
0.8258
0.0002
0.0000
car
0.1620
0.0001
0.0163
0.0031
0.8185
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.815
0.930
0.851
0.837
0.757
--
Recall/Completeness
0.830
0.871
0.877
0.826
0.819
--
F1
0.823
0.900
0.864
0.832
0.787
--

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_area24_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8618
0.0269
0.0834
0.0233
0.0046
0.0000
building
0.0563
0.8855
0.0532
0.0050
0.0000
0.0000
low_veg
0.0236
0.0090
0.8959
0.0715
0.0000
0.0000
tree
0.0108
0.0033
0.1274
0.8585
0.0001
0.0000
car
0.0724
0.0000
0.0148
0.0011
0.9117
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.840
0.953
0.874
0.862
0.782
--
Recall/Completeness
0.862
0.886
0.896
0.858
0.912
--
F1
0.851
0.918
0.885
0.860
0.842
--

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_area27_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9365
0.0256
0.0242
0.0071
0.0066
0.0000
building
0.0614
0.9192
0.0158
0.0034
0.0002
0.0000
low_veg
0.0802
0.0340
0.6867
0.1986
0.0005
0.0000
tree
0.0110
0.0056
0.0569
0.9264
0.0001
0.0000
car
0.2603
0.0085
0.0055
0.0048
0.7209
0.0000
clutter
0.6453
0.2670
0.0633
0.0017
0.0210
0.0017
Precision/Correctness
0.861
0.952
0.874
0.686
0.909
0.750
Recall/Completeness
0.936
0.919
0.687
0.926
0.721
0.002
F1
0.897
0.935
0.769
0.788
0.804
0.003

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_area27_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9626
0.0153
0.0175
0.0026
0.0020
0.0000
building
0.0505
0.9381
0.0103
0.0010
0.0001
0.0000
low_veg
0.0621
0.0204
0.7289
0.1884
0.0002
0.0000
tree
0.0042
0.0017
0.0405
0.9536
0.0000
0.0000
car
0.1486
0.0070
0.0040
0.0041
0.8363
0.0001
clutter
0.6416
0.2896
0.0428
0.0000
0.0236
0.0024
Precision/Correctness
0.896
0.973
0.911
0.716
0.965
0.750
Recall/Completeness
0.963
0.938
0.729
0.954
0.836
0.002
F1
0.928
0.955
0.810
0.818
0.896
0.005

Overall accuracy 0.903

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
0.9421
0.0193
0.0192
0.0134
0.0059
0.0001
building
0.0241
0.9584
0.0104
0.0070
0.0000
0.0000
low_veg
0.0778
0.0207
0.6087
0.2914
0.0014
0.0000
tree
0.0053
0.0012
0.0235
0.9700
0.0000
0.0000
car
0.1927
0.0083
0.0053
0.0111
0.7569
0.0256
clutter
0.5174
0.3722
0.0329
0.0078
0.0336
0.0360
Precision/Correctness
0.916
0.920
0.861
0.675
0.732
0.725
Recall/Completeness
0.942
0.958
0.609
0.970
0.757
0.036
F1
0.929
0.939
0.713
0.796
0.744
0.069

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: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9628
0.0138
0.0130
0.0060
0.0043
0.0000
building
0.0173
0.9734
0.0058
0.0035
0.0000
0.0000
low_veg
0.0542
0.0088
0.6541
0.2820
0.0009
0.0000
tree
0.0012
0.0001
0.0147
0.9840
0.0000
0.0000
car
0.1006
0.0086
0.0056
0.0079
0.8491
0.0281
clutter
0.4911
0.4037
0.0253
0.0035
0.0337
0.0427
Precision/Correctness
0.940
0.938
0.904
0.712
0.749
0.791
Recall/Completeness
0.963
0.973
0.654
0.984
0.849
0.043
F1
0.951
0.955
0.759
0.826
0.796
0.081

Overall accuracy 0.899

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
0.9664
0.0069
0.0136
0.0054
0.0072
0.0005
building
0.0639
0.9196
0.0125
0.0021
0.0019
0.0000
low_veg
0.0531
0.0019
0.9084
0.0355
0.0011
0.0001
tree
0.0426
0.0039
0.0793
0.8732
0.0010
0.0000
car
0.1755
0.1179
0.0068
0.0038
0.6960
0.0001
clutter
0.4820
0.3188
0.0172
0.0125
0.0345
0.1350
Precision/Correctness
0.876
0.933
0.879
0.921
0.841
0.956
Recall/Completeness
0.966
0.920
0.908
0.873
0.696
0.135
F1
0.919
0.926
0.894
0.896
0.761
0.237

Overall accuracy 0.896

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
0.9795
0.0050
0.0105
0.0016
0.0032
0.0001
building
0.0493
0.9419
0.0068
0.0005
0.0015
0.0000
low_veg
0.0353
0.0002
0.9357
0.0285
0.0003
0.0000
tree
0.0170
0.0009
0.0604
0.9216
0.0001
0.0000
car
0.0957
0.1346
0.0026
0.0012
0.7659
0.0000
clutter
0.4341
0.3585
0.0169
0.0058
0.0359
0.1488
Precision/Correctness
0.911
0.942
0.913
0.951
0.887
0.990
Recall/Completeness
0.980
0.942
0.936
0.922
0.766
0.149
F1
0.944
0.942
0.924
0.936
0.822
0.259

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_area33_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9718
0.0108
0.0060
0.0051
0.0024
0.0040
building
0.0903
0.8203
0.0832
0.0052
0.0007
0.0003
low_veg
0.0649
0.0151
0.8855
0.0342
0.0003
0.0000
tree
0.0398
0.0056
0.1226
0.8320
0.0000
0.0000
car
0.2364
0.0422
0.0032
0.0024
0.7083
0.0075
clutter
0.3527
0.0624
0.0015
0.0002
0.0078
0.5754
Precision/Correctness
0.857
0.956
0.776
0.909
0.851
0.948
Recall/Completeness
0.972
0.820
0.886
0.832
0.708
0.575
F1
0.911
0.883
0.827
0.869
0.773
0.716

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_area33_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9867
0.0074
0.0022
0.0017
0.0011
0.0009
building
0.0835
0.8310
0.0820
0.0027
0.0006
0.0002
low_veg
0.0343
0.0088
0.9270
0.0297
0.0001
0.0000
tree
0.0178
0.0012
0.1129
0.8681
0.0000
0.0000
car
0.1308
0.0543
0.0011
0.0009
0.8064
0.0065
clutter
0.3164
0.0602
0.0006
0.0000
0.0079
0.6149
Precision/Correctness
0.885
0.970
0.791
0.937
0.885
0.985
Recall/Completeness
0.987
0.831
0.927
0.868
0.806
0.615
F1
0.933
0.895
0.854
0.901
0.844
0.757

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_area35_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8616
0.0446
0.0707
0.0216
0.0015
0.0000
building
0.0293
0.9434
0.0198
0.0071
0.0003
0.0000
low_veg
0.0512
0.0123
0.7026
0.2339
0.0001
0.0000
tree
0.0388
0.0052
0.1000
0.8560
0.0001
0.0000
car
0.2325
0.0112
0.0023
0.0120
0.7419
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.873
0.942
0.790
0.754
0.918
--
Recall/Completeness
0.862
0.943
0.703
0.856
0.742
--
F1
0.867
0.943
0.744
0.802
0.821
--

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: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8998
0.0404
0.0516
0.0077
0.0005
0.0000
building
0.0192
0.9691
0.0097
0.0017
0.0003
0.0000
low_veg
0.0351
0.0046
0.7343
0.2259
0.0000
0.0000
tree
0.0155
0.0012
0.0767
0.9066
0.0000
0.0000
car
0.1180
0.0115
0.0005
0.0042
0.8659
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.924
0.960
0.845
0.782
0.957
--
Recall/Completeness
0.900
0.969
0.734
0.907
0.866
--
F1
0.912
0.964
0.786
0.840
0.909
--

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: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8954
0.0319
0.0502
0.0190
0.0032
0.0003
building
0.0219
0.9265
0.0458
0.0046
0.0013
0.0000
low_veg
0.0504
0.0394
0.8152
0.0948
0.0002
0.0001
tree
0.0233
0.0046
0.1033
0.8686
0.0001
0.0000
car
0.2099
0.0097
0.0360
0.0054
0.7390
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.902
0.919
0.834
0.838
0.848
--
Recall/Completeness
0.895
0.926
0.815
0.869
0.739
--
F1
0.898
0.923
0.824
0.853
0.790
--

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_area38_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9247
0.0297
0.0365
0.0077
0.0012
0.0003
building
0.0148
0.9507
0.0318
0.0015
0.0012
0.0000
low_veg
0.0362
0.0369
0.8489
0.0779
0.0001
0.0000
tree
0.0094
0.0014
0.0814
0.9079
0.0000
0.0000
car
0.1135
0.0088
0.0231
0.0023
0.8523
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.938
0.931
0.874
0.878
0.905
--
Recall/Completeness
0.925
0.951
0.849
0.908
0.852
--
F1
0.931
0.941
0.861
0.893
0.878
--

Overall accuracy 0.907

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image