Detailled semantic labeling (2D) result


Name W. Sun
Affiliation Univ. of Calgary, Canada
Abbreviation UCal6
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
0.894
0.043
0.041
0.018
0.005
0.000
building
0.032
0.942
0.020
0.006
0.000
0.000
low_veg
0.054
0.042
0.768
0.135
0.000
0.000
tree
0.022
0.013
0.088
0.877
0.000
0.000
car
0.243
0.018
0.009
0.005
0.723
0.002
clutter
0.343
0.283
0.011
0.007
0.015
0.341
Precision/Correctness
0.889
0.902
0.819
0.848
0.849
0.945
Recall/Completeness
0.894
0.942
0.768
0.877
0.723
0.341
F1
0.891
0.921
0.793
0.862
0.781
0.501

Overall accuracy 0.868

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
0.923
0.032
0.034
0.009
0.003
0.000
building
0.026
0.956
0.015
0.003
0.000
0.000
low_veg
0.042
0.030
0.808
0.120
0.000
0.000
tree
0.010
0.007
0.073
0.909
0.000
0.000
car
0.146
0.016
0.006
0.003
0.827
0.003
clutter
0.307
0.300
0.008
0.003
0.015
0.367
Precision/Correctness
0.920
0.929
0.852
0.878
0.893
0.971
Recall/Completeness
0.923
0.956
0.808
0.909
0.827
0.367
F1
0.921
0.943
0.829
0.893
0.859
0.533

Overall accuracy 0.899
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9414
0.0207
0.0204
0.0126
0.0049
0.0000
building
0.0338
0.9430
0.0187
0.0045
0.0000
0.0000
low_veg
0.0809
0.0354
0.7071
0.1765
0.0001
0.0000
tree
0.0301
0.0120
0.0797
0.8767
0.0003
0.0012
car
0.2563
0.0208
0.0002
0.0011
0.7216
0.0000
clutter
0.0220
0.0000
0.0029
0.0146
0.0000
0.9605
Precision/Correctness
0.857
0.927
0.856
0.820
0.895
0.984
Recall/Completeness
0.941
0.943
0.707
0.877
0.722
0.961
F1
0.897
0.935
0.774
0.847
0.799
0.972

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_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9643
0.0154
0.0127
0.0041
0.0034
0.0000
building
0.0263
0.9603
0.0122
0.0013
0.0000
0.0000
low_veg
0.0629
0.0229
0.7433
0.1709
0.0001
0.0000
tree
0.0146
0.0073
0.0679
0.9095
0.0002
0.0005
car
0.1225
0.0201
0.0000
0.0002
0.8573
0.0000
clutter
0.0227
0.0000
0.0026
0.0039
0.0000
0.9708
Precision/Correctness
0.898
0.952
0.886
0.843
0.919
0.994
Recall/Completeness
0.964
0.960
0.743
0.910
0.857
0.971
F1
0.930
0.956
0.808
0.875
0.887
0.982

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_area4_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8734
0.1070
0.0108
0.0044
0.0044
0.0000
building
0.0437
0.9507
0.0041
0.0013
0.0002
0.0000
low_veg
0.1223
0.1518
0.5228
0.2012
0.0018
0.0000
tree
0.0465
0.0394
0.0768
0.8369
0.0003
0.0000
car
0.2971
0.0166
0.0015
0.0028
0.6821
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.875
0.930
0.718
0.785
0.868
--
Recall/Completeness
0.873
0.951
0.523
0.837
0.682
--
F1
0.874
0.940
0.605
0.810
0.764
--

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_area4_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9133
0.0753
0.0074
0.0017
0.0023
0.0000
building
0.0351
0.9611
0.0030
0.0005
0.0002
0.0000
low_veg
0.0861
0.1175
0.5707
0.2247
0.0011
0.0000
tree
0.0206
0.0233
0.0708
0.8854
0.0000
0.0000
car
0.1832
0.0091
0.0002
0.0017
0.8058
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.906
0.954
0.760
0.809
0.913
--
Recall/Completeness
0.913
0.961
0.571
0.885
0.806
--
F1
0.910
0.957
0.652
0.846
0.856
--

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_area6_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8819
0.0622
0.0369
0.0143
0.0047
0.0000
building
0.0318
0.9511
0.0117
0.0053
0.0000
0.0000
low_veg
0.0861
0.0477
0.7245
0.1411
0.0005
0.0000
tree
0.0155
0.0132
0.0613
0.9099
0.0001
0.0000
car
0.3469
0.0412
0.0014
0.0013
0.6092
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.883
0.925
0.714
0.928
0.886
--
Recall/Completeness
0.882
0.951
0.725
0.910
0.609
--
F1
0.882
0.938
0.719
0.919
0.722
--

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_area6_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9219
0.0405
0.0285
0.0068
0.0022
0.0000
building
0.0248
0.9647
0.0078
0.0028
0.0000
0.0000
low_veg
0.0718
0.0293
0.7782
0.1206
0.0001
0.0000
tree
0.0059
0.0076
0.0488
0.9377
0.0000
0.0000
car
0.2502
0.0369
0.0004
0.0001
0.7123
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.919
0.955
0.757
0.951
0.939
--
Recall/Completeness
0.922
0.965
0.778
0.938
0.712
--
F1
0.920
0.960
0.768
0.944
0.810
--

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_area8_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8775
0.0452
0.0600
0.0128
0.0040
0.0005
building
0.0235
0.9617
0.0123
0.0025
0.0000
0.0000
low_veg
0.0440
0.0214
0.8827
0.0511
0.0008
0.0000
tree
0.0277
0.0107
0.0776
0.8836
0.0001
0.0003
car
0.2439
0.0034
0.0177
0.0051
0.7299
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.917
0.914
0.811
0.935
0.894
--
Recall/Completeness
0.877
0.962
0.883
0.884
0.730
--
F1
0.897
0.937
0.845
0.909
0.804
--

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_area8_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9080
0.0350
0.0501
0.0047
0.0017
0.0006
building
0.0163
0.9773
0.0057
0.0007
0.0000
0.0000
low_veg
0.0285
0.0109
0.9213
0.0389
0.0004
0.0000
tree
0.0120
0.0057
0.0599
0.9221
0.0000
0.0002
car
0.1415
0.0011
0.0115
0.0041
0.8418
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.953
0.942
0.850
0.960
0.947
--
Recall/Completeness
0.908
0.977
0.921
0.922
0.842
--
F1
0.930
0.959
0.884
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
0.8336
0.0741
0.0661
0.0204
0.0057
0.0000
building
0.0352
0.9362
0.0182
0.0100
0.0005
0.0000
low_veg
0.0800
0.0472
0.7197
0.1531
0.0000
0.0000
tree
0.0176
0.0145
0.0839
0.8840
0.0000
0.0000
car
0.1908
0.0084
0.0100
0.0180
0.7729
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.920
0.850
0.732
0.831
0.706
--
Recall/Completeness
0.834
0.936
0.720
0.884
0.773
--
F1
0.875
0.891
0.726
0.856
0.738
--

Overall accuracy 0.848

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area10_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8657
0.0594
0.0609
0.0094
0.0045
0.0000
building
0.0290
0.9510
0.0136
0.0061
0.0003
0.0000
low_veg
0.0754
0.0327
0.7654
0.1264
0.0000
0.0000
tree
0.0080
0.0091
0.0657
0.9171
0.0000
0.0000
car
0.1065
0.0059
0.0057
0.0187
0.8633
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.938
0.884
0.764
0.873
0.714
--
Recall/Completeness
0.866
0.951
0.765
0.917
0.863
--
F1
0.901
0.916
0.765
0.895
0.781
--

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_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8777
0.0350
0.0542
0.0301
0.0029
0.0000
building
0.0159
0.9596
0.0148
0.0098
0.0000
0.0000
low_veg
0.0370
0.0385
0.7710
0.1525
0.0001
0.0009
tree
0.0100
0.0123
0.1080
0.8698
0.0000
0.0000
car
0.1876
0.0000
0.0045
0.0102
0.7977
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.872
0.899
0.816
0.865
0.899
--
Recall/Completeness
0.878
0.960
0.771
0.870
0.798
--
F1
0.875
0.928
0.793
0.867
0.845
--

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_area12_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9059
0.0312
0.0469
0.0154
0.0007
0.0000
building
0.0137
0.9744
0.0079
0.0040
0.0000
0.0000
low_veg
0.0343
0.0243
0.8106
0.1298
0.0000
0.0010
tree
0.0045
0.0065
0.0906
0.8984
0.0000
0.0000
car
0.0791
0.0000
0.0029
0.0023
0.9156
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.900
0.932
0.846
0.894
0.968
--
Recall/Completeness
0.906
0.974
0.811
0.898
0.916
--
F1
0.903
0.953
0.828
0.896
0.941
--

Overall accuracy 0.889

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
0.8185
0.0385
0.1055
0.0315
0.0060
0.0000
building
0.0116
0.9626
0.0161
0.0097
0.0000
0.0000
low_veg
0.0653
0.0700
0.7080
0.1564
0.0003
0.0000
tree
0.0247
0.0202
0.1130
0.8420
0.0000
0.0000
car
0.1188
0.0000
0.0000
0.0033
0.8779
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.873
0.835
0.735
0.853
0.614
--
Recall/Completeness
0.818
0.963
0.708
0.842
0.878
--
F1
0.845
0.894
0.721
0.847
0.723
--

Overall accuracy 0.824

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
0.8391
0.0324
0.1027
0.0206
0.0051
0.0000
building
0.0087
0.9775
0.0080
0.0059
0.0000
0.0000
low_veg
0.0602
0.0529
0.7406
0.1460
0.0003
0.0000
tree
0.0168
0.0121
0.1016
0.8695
0.0000
0.0000
car
0.0252
0.0000
0.0000
0.0000
0.9748
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.898
0.873
0.755
0.875
0.601
--
Recall/Completeness
0.839
0.977
0.741
0.869
0.975
--
F1
0.868
0.922
0.748
0.872
0.744
--

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_area16_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8278
0.0404
0.0804
0.0482
0.0031
0.0000
building
0.0164
0.9637
0.0117
0.0083
0.0000
0.0000
low_veg
0.0144
0.0252
0.8666
0.0936
0.0001
0.0001
tree
0.0226
0.0119
0.1215
0.8439
0.0000
0.0000
car
0.1260
0.0047
0.0417
0.0010
0.8266
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.890
0.904
0.813
0.894
0.779
--
Recall/Completeness
0.828
0.964
0.867
0.844
0.827
--
F1
0.858
0.933
0.839
0.868
0.802
--

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
0.8628
0.0345
0.0720
0.0292
0.0016
0.0000
building
0.0125
0.9799
0.0044
0.0032
0.0000
0.0000
low_veg
0.0105
0.0150
0.8951
0.0792
0.0001
0.0001
tree
0.0153
0.0064
0.1082
0.8702
0.0000
0.0000
car
0.0519
0.0012
0.0309
0.0000
0.9160
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.922
0.936
0.838
0.918
0.844
--
Recall/Completeness
0.863
0.980
0.895
0.870
0.916
--
F1
0.891
0.957
0.865
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
0.8595
0.0636
0.0330
0.0408
0.0029
0.0002
building
0.0033
0.9782
0.0101
0.0084
0.0000
0.0000
low_veg
0.0586
0.0517
0.7256
0.1641
0.0000
0.0001
tree
0.0084
0.0054
0.0463
0.9399
0.0000
0.0000
car
0.0893
0.0050
0.0165
0.0081
0.8811
0.0000
clutter
0.0001
0.9998
0.0000
0.0001
0.0000
0.0000
Precision/Correctness
0.917
0.754
0.837
0.903
0.860
0.000
Recall/Completeness
0.860
0.978
0.726
0.940
0.881
0.000
F1
0.887
0.852
0.777
0.921
0.870
-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_area20_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8956
0.0497
0.0306
0.0231
0.0008
0.0002
building
0.0019
0.9889
0.0068
0.0024
0.0000
0.0000
low_veg
0.0524
0.0375
0.7744
0.1355
0.0000
0.0001
tree
0.0034
0.0025
0.0345
0.9596
0.0000
0.0000
car
0.0147
0.0019
0.0031
0.0013
0.9791
0.0000
clutter
0.0000
1.0000
0.0000
0.0000
0.0000
0.0000
Precision/Correctness
0.940
0.781
0.868
0.930
0.949
0.000
Recall/Completeness
0.896
0.989
0.774
0.960
0.979
0.000
F1
0.917
0.873
0.819
0.945
0.964
-nan

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_area22_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8986
0.0279
0.0364
0.0302
0.0069
0.0000
building
0.0111
0.9693
0.0097
0.0098
0.0001
0.0000
low_veg
0.0799
0.0535
0.7247
0.1413
0.0007
0.0000
tree
0.0247
0.0078
0.0590
0.9084
0.0001
0.0000
car
0.2081
0.0000
0.0045
0.0122
0.7644
0.0107
clutter
--
--
--
--
--
--
Precision/Correctness
0.913
0.887
0.828
0.867
0.779
--
Recall/Completeness
0.899
0.969
0.725
0.908
0.764
--
F1
0.906
0.926
0.773
0.887
0.771
--

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_area22_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9313
0.0182
0.0305
0.0155
0.0044
0.0000
building
0.0060
0.9844
0.0044
0.0051
0.0001
0.0000
low_veg
0.0770
0.0349
0.7751
0.1124
0.0005
0.0000
tree
0.0108
0.0037
0.0428
0.9427
0.0000
0.0000
car
0.1165
0.0000
0.0016
0.0049
0.8634
0.0136
clutter
--
--
--
--
--
--
Precision/Correctness
0.937
0.928
0.868
0.906
0.817
--
Recall/Completeness
0.931
0.984
0.775
0.943
0.863
--
F1
0.934
0.956
0.819
0.924
0.840
--

Overall accuracy 0.913

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
0.8185
0.0467
0.0945
0.0339
0.0064
0.0000
building
0.0498
0.8911
0.0511
0.0080
0.0000
0.0000
low_veg
0.0252
0.0161
0.8760
0.0826
0.0000
0.0000
tree
0.0165
0.0129
0.1465
0.8240
0.0002
0.0000
car
0.1620
0.0000
0.0164
0.0031
0.8185
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.829
0.909
0.856
0.838
0.761
--
Recall/Completeness
0.818
0.891
0.876
0.824
0.819
--
F1
0.824
0.900
0.866
0.831
0.789
--

Overall accuracy 0.857

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
0.8510
0.0370
0.0844
0.0231
0.0045
0.0000
building
0.0471
0.9031
0.0445
0.0053
0.0000
0.0000
low_veg
0.0224
0.0102
0.8963
0.0711
0.0000
0.0000
tree
0.0101
0.0083
0.1247
0.8568
0.0001
0.0000
car
0.0724
0.0000
0.0148
0.0011
0.9117
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.852
0.937
0.879
0.863
0.787
--
Recall/Completeness
0.851
0.903
0.896
0.857
0.912
--
F1
0.852
0.920
0.887
0.860
0.845
--

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_area27_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9220
0.0396
0.0245
0.0073
0.0066
0.0000
building
0.0447
0.9380
0.0127
0.0044
0.0002
0.0000
low_veg
0.0725
0.0663
0.6656
0.1951
0.0005
0.0000
tree
0.0102
0.0190
0.0523
0.9184
0.0001
0.0000
car
0.2596
0.0111
0.0056
0.0051
0.7185
0.0000
clutter
0.6728
0.2396
0.0633
0.0017
0.0210
0.0017
Precision/Correctness
0.878
0.920
0.880
0.686
0.909
0.750
Recall/Completeness
0.922
0.938
0.666
0.918
0.719
0.002
F1
0.899
0.929
0.758
0.785
0.802
0.003

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_area27_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9513
0.0261
0.0178
0.0028
0.0020
0.0000
building
0.0358
0.9536
0.0082
0.0022
0.0001
0.0000
low_veg
0.0560
0.0484
0.7098
0.1857
0.0002
0.0000
tree
0.0035
0.0122
0.0373
0.9470
0.0000
0.0000
car
0.1502
0.0078
0.0041
0.0044
0.8335
0.0001
clutter
0.6994
0.2318
0.0428
0.0000
0.0236
0.0024
Precision/Correctness
0.912
0.947
0.915
0.715
0.965
0.750
Recall/Completeness
0.951
0.954
0.710
0.947
0.834
0.002
F1
0.931
0.950
0.799
0.815
0.894
0.005

Overall accuracy 0.901

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
0.9347
0.0282
0.0173
0.0137
0.0059
0.0001
building
0.0162
0.9705
0.0076
0.0056
0.0000
0.0000
low_veg
0.0710
0.0442
0.5972
0.2864
0.0012
0.0000
tree
0.0053
0.0121
0.0227
0.9599
0.0000
0.0000
car
0.1946
0.0093
0.0053
0.0111
0.7540
0.0256
clutter
0.6244
0.2686
0.0293
0.0117
0.0326
0.0334
Precision/Correctness
0.915
0.904
0.873
0.677
0.735
0.711
Recall/Completeness
0.935
0.970
0.597
0.960
0.754
0.033
F1
0.925
0.936
0.709
0.794
0.744
0.064

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_area29_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9578
0.0195
0.0117
0.0066
0.0043
0.0000
building
0.0114
0.9813
0.0043
0.0029
0.0000
0.0000
low_veg
0.0493
0.0262
0.6462
0.2775
0.0007
0.0000
tree
0.0012
0.0070
0.0143
0.9774
0.0000
0.0000
car
0.1074
0.0043
0.0056
0.0079
0.8466
0.0281
clutter
0.6055
0.2940
0.0213
0.0070
0.0326
0.0396
Precision/Correctness
0.938
0.930
0.913
0.713
0.752
0.778
Recall/Completeness
0.958
0.981
0.646
0.977
0.847
0.040
F1
0.948
0.955
0.757
0.824
0.797
0.075

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_area31_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9564
0.0171
0.0134
0.0054
0.0072
0.0004
building
0.0491
0.9398
0.0075
0.0021
0.0015
0.0000
low_veg
0.0509
0.0122
0.9001
0.0355
0.0012
0.0001
tree
0.0407
0.0182
0.0713
0.8689
0.0010
0.0000
car
0.2450
0.0379
0.0098
0.0040
0.7032
0.0001
clutter
0.5091
0.3181
0.0173
0.0123
0.0307
0.1124
Precision/Correctness
0.878
0.920
0.892
0.921
0.848
0.953
Recall/Completeness
0.956
0.940
0.900
0.869
0.703
0.112
F1
0.915
0.930
0.896
0.894
0.769
0.201

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
0.9738
0.0109
0.0104
0.0017
0.0032
0.0001
building
0.0418
0.9514
0.0051
0.0005
0.0012
0.0000
low_veg
0.0341
0.0058
0.9313
0.0285
0.0003
0.0000
tree
0.0161
0.0114
0.0547
0.9177
0.0001
0.0000
car
0.1760
0.0437
0.0054
0.0012
0.7737
0.0000
clutter
0.4638
0.3572
0.0169
0.0061
0.0320
0.1239
Precision/Correctness
0.909
0.938
0.920
0.950
0.895
0.990
Recall/Completeness
0.974
0.951
0.931
0.918
0.774
0.124
F1
0.940
0.944
0.925
0.934
0.830
0.220

Overall accuracy 0.923

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
0.9625
0.0203
0.0061
0.0049
0.0023
0.0039
building
0.0807
0.8309
0.0841
0.0042
0.0000
0.0000
low_veg
0.0600
0.0244
0.8816
0.0337
0.0003
0.0000
tree
0.0387
0.0201
0.1169
0.8242
0.0000
0.0000
car
0.2720
0.0068
0.0032
0.0024
0.7081
0.0075
clutter
0.3681
0.0446
0.0009
0.0002
0.0078
0.5785
Precision/Correctness
0.861
0.937
0.776
0.912
0.871
0.951
Recall/Completeness
0.962
0.831
0.882
0.824
0.708
0.578
F1
0.909
0.881
0.826
0.866
0.781
0.719

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_area33_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9808
0.0135
0.0022
0.0016
0.0011
0.0008
building
0.0758
0.8391
0.0830
0.0021
0.0000
0.0000
low_veg
0.0301
0.0170
0.9234
0.0294
0.0001
0.0000
tree
0.0171
0.0125
0.1082
0.8623
0.0000
0.0000
car
0.1832
0.0022
0.0011
0.0009
0.8061
0.0065
clutter
0.3384
0.0341
0.0003
0.0000
0.0079
0.6194
Precision/Correctness
0.887
0.959
0.791
0.940
0.903
0.988
Recall/Completeness
0.981
0.839
0.923
0.862
0.806
0.619
F1
0.932
0.895
0.852
0.899
0.852
0.761

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_area35_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8571
0.0487
0.0710
0.0217
0.0015
0.0000
building
0.0261
0.9468
0.0201
0.0067
0.0003
0.0000
low_veg
0.0476
0.0303
0.6914
0.2307
0.0001
0.0000
tree
0.0385
0.0128
0.0977
0.8508
0.0001
0.0000
car
0.2336
0.0179
0.0019
0.0126
0.7340
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.879
0.917
0.788
0.755
0.918
--
Recall/Completeness
0.857
0.947
0.691
0.851
0.734
--
F1
0.868
0.932
0.737
0.800
0.816
--

Overall accuracy 0.838

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
0.8973
0.0412
0.0530
0.0080
0.0005
0.0000
building
0.0169
0.9689
0.0118
0.0021
0.0003
0.0000
low_veg
0.0326
0.0181
0.7263
0.2230
0.0000
0.0000
tree
0.0153
0.0065
0.0754
0.9028
0.0000
0.0000
car
0.1233
0.0160
0.0004
0.0042
0.8560
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.929
0.944
0.841
0.783
0.957
--
Recall/Completeness
0.897
0.969
0.726
0.903
0.856
--
F1
0.913
0.956
0.779
0.839
0.904
--

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_area38_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8917
0.0366
0.0490
0.0194
0.0030
0.0003
building
0.0186
0.9351
0.0389
0.0060
0.0013
0.0000
low_veg
0.0458
0.0601
0.8003
0.0935
0.0002
0.0001
tree
0.0225
0.0114
0.1006
0.8654
0.0001
0.0000
car
0.2051
0.0211
0.0357
0.0054
0.7327
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.909
0.891
0.839
0.837
0.853
--
Recall/Completeness
0.892
0.935
0.800
0.865
0.733
--
F1
0.900
0.912
0.819
0.851
0.788
--

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_area38_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9233
0.0313
0.0360
0.0081
0.0010
0.0003
building
0.0130
0.9555
0.0275
0.0029
0.0012
0.0000
low_veg
0.0322
0.0533
0.8372
0.0772
0.0001
0.0000
tree
0.0090
0.0057
0.0798
0.9055
0.0000
0.0000
car
0.1108
0.0189
0.0231
0.0023
0.8449
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.943
0.912
0.878
0.876
0.911
--
Recall/Completeness
0.923
0.956
0.837
0.905
0.845
--
F1
0.933
0.933
0.857
0.891
0.877
--

Overall accuracy 0.904

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image