Detailled semantic labeling (2D) result


Name W. Sun
Affiliation Univ. of Calgary, Canada
Abbreviation UCal9
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
0.902
0.033
0.042
0.018
0.005
0.000
building
0.042
0.930
0.023
0.005
0.001
0.000
low_veg
0.059
0.025
0.779
0.137
0.000
0.000
tree
0.023
0.006
0.095
0.875
0.000
0.000
car
0.227
0.023
0.008
0.005
0.735
0.002
clutter
0.321
0.280
0.012
0.008
0.019
0.360
Precision/Correctness
0.879
0.928
0.811
0.847
0.838
0.950
Recall/Completeness
0.902
0.930
0.779
0.875
0.735
0.360
F1
0.891
0.929
0.795
0.861
0.783
0.522

Overall accuracy 0.870

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
0.929
0.026
0.034
0.009
0.003
0.000
building
0.033
0.948
0.017
0.002
0.000
0.000
low_veg
0.046
0.017
0.815
0.122
0.000
0.000
tree
0.011
0.003
0.079
0.907
0.000
0.000
car
0.125
0.025
0.005
0.003
0.839
0.003
clutter
0.283
0.299
0.009
0.003
0.018
0.388
Precision/Correctness
0.912
0.948
0.845
0.877
0.881
0.975
Recall/Completeness
0.929
0.948
0.815
0.907
0.839
0.388
F1
0.920
0.948
0.830
0.892
0.859
0.555

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
0.9462
0.0170
0.0195
0.0120
0.0053
0.0000
building
0.0388
0.9396
0.0182
0.0034
0.0000
0.0000
low_veg
0.0831
0.0208
0.7278
0.1680
0.0002
0.0000
tree
0.0317
0.0058
0.0906
0.8705
0.0004
0.0011
car
0.2612
0.0078
0.0007
0.0011
0.7292
0.0000
clutter
0.0081
0.0000
0.0009
0.0179
0.0000
0.9731
Precision/Correctness
0.852
0.952
0.850
0.826
0.886
0.985
Recall/Completeness
0.946
0.940
0.728
0.870
0.729
0.973
F1
0.896
0.946
0.784
0.848
0.800
0.979

Overall accuracy 0.870

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
0.9678
0.0130
0.0112
0.0044
0.0037
0.0000
building
0.0305
0.9587
0.0101
0.0006
0.0000
0.0000
low_veg
0.0642
0.0127
0.7607
0.1622
0.0002
0.0000
tree
0.0153
0.0022
0.0777
0.9042
0.0002
0.0005
car
0.1291
0.0063
0.0000
0.0001
0.8645
0.0000
clutter
0.0075
0.0000
0.0007
0.0057
0.0000
0.9861
Precision/Correctness
0.895
0.971
0.881
0.849
0.913
0.994
Recall/Completeness
0.968
0.959
0.761
0.904
0.864
0.986
F1
0.930
0.965
0.817
0.876
0.888
0.990

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_area4_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9194
0.0593
0.0118
0.0048
0.0046
0.0000
building
0.0545
0.9351
0.0081
0.0012
0.0010
0.0000
low_veg
0.1395
0.0778
0.5672
0.2137
0.0018
0.0000
tree
0.0464
0.0174
0.0899
0.8459
0.0004
0.0000
car
0.3017
0.0090
0.0010
0.0034
0.6850
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.861
0.960
0.672
0.777
0.830
--
Recall/Completeness
0.919
0.935
0.567
0.846
0.685
--
F1
0.889
0.948
0.615
0.810
0.750
--

Overall accuracy 0.905

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
0.9486
0.0389
0.0079
0.0019
0.0027
0.0000
building
0.0416
0.9501
0.0068
0.0004
0.0011
0.0000
low_veg
0.1024
0.0502
0.6092
0.2366
0.0015
0.0000
tree
0.0207
0.0067
0.0819
0.8906
0.0001
0.0000
car
0.1807
0.0057
0.0000
0.0018
0.8118
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.895
0.976
0.708
0.803
0.859
--
Recall/Completeness
0.949
0.950
0.609
0.891
0.812
--
F1
0.921
0.963
0.655
0.844
0.835
--

Overall accuracy 0.931

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
0.8954
0.0511
0.0356
0.0118
0.0061
0.0000
building
0.0396
0.9412
0.0138
0.0052
0.0002
0.0000
low_veg
0.1008
0.0277
0.7308
0.1401
0.0005
0.0000
tree
0.0173
0.0050
0.0692
0.9083
0.0001
0.0000
car
0.3218
0.0214
0.0013
0.0017
0.6538
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.870
0.946
0.699
0.930
0.861
--
Recall/Completeness
0.895
0.941
0.731
0.908
0.654
--
F1
0.882
0.944
0.714
0.919
0.743
--

Overall accuracy 0.893

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
0.9295
0.0363
0.0265
0.0045
0.0031
0.0000
building
0.0296
0.9584
0.0091
0.0028
0.0001
0.0000
low_veg
0.0860
0.0116
0.7809
0.1214
0.0000
0.0000
tree
0.0065
0.0018
0.0556
0.9360
0.0000
0.0000
car
0.2312
0.0175
0.0006
0.0002
0.7505
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.909
0.968
0.743
0.952
0.919
--
Recall/Completeness
0.930
0.958
0.781
0.936
0.750
--
F1
0.919
0.963
0.762
0.944
0.826
--

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
0.8840
0.0363
0.0629
0.0123
0.0045
0.0002
building
0.0383
0.9427
0.0160
0.0029
0.0001
0.0000
low_veg
0.0478
0.0161
0.8766
0.0588
0.0006
0.0000
tree
0.0313
0.0063
0.0754
0.8867
0.0002
0.0001
car
0.2398
0.0077
0.0154
0.0047
0.7323
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.903
0.931
0.805
0.929
0.887
--
Recall/Completeness
0.884
0.943
0.877
0.887
0.732
--
F1
0.893
0.937
0.839
0.907
0.802
--

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_area8_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9119
0.0283
0.0532
0.0045
0.0020
0.0002
building
0.0295
0.9613
0.0082
0.0010
0.0001
0.0000
low_veg
0.0311
0.0077
0.9140
0.0468
0.0003
0.0000
tree
0.0151
0.0025
0.0572
0.9250
0.0000
0.0002
car
0.1342
0.0075
0.0098
0.0029
0.8456
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.939
0.954
0.845
0.954
0.939
--
Recall/Completeness
0.912
0.961
0.914
0.925
0.846
--
F1
0.925
0.958
0.878
0.939
0.890
--

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_area10_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8432
0.0729
0.0578
0.0204
0.0057
0.0000
building
0.0414
0.9323
0.0188
0.0071
0.0004
0.0000
low_veg
0.0866
0.0321
0.7218
0.1595
0.0000
0.0000
tree
0.0171
0.0086
0.0880
0.8863
0.0000
0.0000
car
0.1618
0.0356
0.0207
0.0013
0.7805
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.914
0.863
0.741
0.830
0.712
--
Recall/Completeness
0.843
0.932
0.722
0.886
0.781
--
F1
0.877
0.896
0.731
0.857
0.745
--

Overall accuracy 0.851

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area10_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8720
0.0631
0.0512
0.0093
0.0044
0.0000
building
0.0354
0.9465
0.0137
0.0041
0.0003
0.0000
low_veg
0.0815
0.0190
0.7661
0.1334
0.0000
0.0000
tree
0.0078
0.0042
0.0683
0.9197
0.0000
0.0000
car
0.0753
0.0400
0.0161
0.0000
0.8686
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.933
0.889
0.779
0.872
0.720
--
Recall/Completeness
0.872
0.946
0.766
0.920
0.869
--
F1
0.901
0.917
0.772
0.895
0.788
--

Overall accuracy 0.882

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8763
0.0324
0.0578
0.0304
0.0030
0.0000
building
0.0687
0.9080
0.0171
0.0062
0.0000
0.0001
low_veg
0.0435
0.0223
0.7818
0.1520
0.0001
0.0002
tree
0.0112
0.0058
0.1165
0.8664
0.0000
0.0000
car
0.1872
0.0000
0.0038
0.0084
0.8005
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.801
0.929
0.806
0.866
0.897
--
Recall/Completeness
0.876
0.908
0.782
0.866
0.801
--
F1
0.837
0.918
0.794
0.866
0.846
--

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_area12_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9037
0.0294
0.0497
0.0165
0.0007
0.0000
building
0.0692
0.9216
0.0078
0.0014
0.0000
0.0000
low_veg
0.0399
0.0131
0.8172
0.1295
0.0000
0.0003
tree
0.0053
0.0020
0.0985
0.8942
0.0000
0.0000
car
0.0829
0.0000
0.0010
0.0009
0.9152
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.827
0.954
0.837
0.894
0.971
--
Recall/Completeness
0.904
0.922
0.817
0.894
0.915
--
F1
0.864
0.937
0.827
0.894
0.942
--

Overall accuracy 0.879

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area14_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8153
0.0403
0.1078
0.0304
0.0062
0.0000
building
0.0166
0.9600
0.0184
0.0050
0.0000
0.0000
low_veg
0.0681
0.0543
0.7195
0.1578
0.0003
0.0000
tree
0.0266
0.0148
0.1211
0.8374
0.0000
0.0000
car
0.1252
0.0000
0.0000
0.0030
0.8719
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.864
0.858
0.727
0.854
0.606
--
Recall/Completeness
0.815
0.960
0.720
0.837
0.872
--
F1
0.839
0.906
0.723
0.846
0.715
--

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
0.8350
0.0351
0.1046
0.0199
0.0054
0.0000
building
0.0136
0.9760
0.0088
0.0017
0.0000
0.0000
low_veg
0.0627
0.0396
0.7497
0.1477
0.0003
0.0000
tree
0.0181
0.0080
0.1084
0.8655
0.0000
0.0000
car
0.0309
0.0000
0.0000
0.0003
0.9688
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.890
0.891
0.749
0.875
0.591
--
Recall/Completeness
0.835
0.976
0.750
0.865
0.969
--
F1
0.861
0.932
0.749
0.870
0.734
--

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
0.8263
0.0352
0.0881
0.0475
0.0029
0.0000
building
0.0162
0.9481
0.0251
0.0105
0.0001
0.0000
low_veg
0.0176
0.0154
0.8704
0.0966
0.0000
0.0000
tree
0.0251
0.0056
0.1246
0.8446
0.0000
0.0000
car
0.1536
0.0031
0.0572
0.0015
0.7846
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.879
0.933
0.802
0.891
0.786
--
Recall/Completeness
0.826
0.948
0.870
0.845
0.785
--
F1
0.852
0.941
0.835
0.867
0.785
--

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_area16_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8594
0.0314
0.0790
0.0288
0.0014
0.0000
building
0.0121
0.9732
0.0107
0.0040
0.0000
0.0000
low_veg
0.0131
0.0096
0.8961
0.0813
0.0000
0.0000
tree
0.0172
0.0025
0.1104
0.8700
0.0000
0.0000
car
0.0798
0.0000
0.0524
0.0000
0.8679
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.912
0.954
0.830
0.916
0.865
--
Recall/Completeness
0.859
0.973
0.896
0.870
0.868
--
F1
0.885
0.963
0.862
0.893
0.866
--

Overall accuracy 0.895

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area20_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8842
0.0381
0.0347
0.0401
0.0029
0.0000
building
0.0101
0.9733
0.0109
0.0058
0.0000
0.0000
low_veg
0.0684
0.0322
0.7302
0.1691
0.0000
0.0001
tree
0.0104
0.0023
0.0484
0.9389
0.0000
0.0000
car
0.1122
0.0042
0.0245
0.0050
0.8540
0.0000
clutter
0.0010
0.9982
0.0000
0.0008
0.0000
0.0000
Precision/Correctness
0.901
0.792
0.831
0.902
0.858
0.000
Recall/Completeness
0.884
0.973
0.730
0.939
0.854
0.000
F1
0.892
0.873
0.777
0.920
0.856
-nan

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: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9167
0.0278
0.0323
0.0224
0.0007
0.0000
building
0.0077
0.9842
0.0065
0.0016
0.0000
0.0000
low_veg
0.0616
0.0210
0.7764
0.1409
0.0000
0.0002
tree
0.0047
0.0005
0.0368
0.9581
0.0000
0.0000
car
0.0372
0.0044
0.0087
0.0006
0.9491
0.0000
clutter
0.0000
0.9999
0.0000
0.0001
0.0000
0.0000
Precision/Correctness
0.926
0.812
0.862
0.929
0.952
0.000
Recall/Completeness
0.917
0.984
0.776
0.958
0.949
0.000
F1
0.921
0.890
0.817
0.943
0.951
-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
0.9031
0.0217
0.0377
0.0306
0.0069
0.0000
building
0.0243
0.9592
0.0096
0.0069
0.0000
0.0000
low_veg
0.0816
0.0342
0.7450
0.1387
0.0004
0.0000
tree
0.0260
0.0038
0.0647
0.9053
0.0001
0.0000
car
0.1856
0.0006
0.0047
0.0118
0.7867
0.0107
clutter
--
--
--
--
--
--
Precision/Correctness
0.905
0.920
0.822
0.870
0.787
--
Recall/Completeness
0.903
0.959
0.745
0.905
0.787
--
F1
0.904
0.939
0.782
0.887
0.787
--

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: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9340
0.0143
0.0313
0.0161
0.0043
0.0000
building
0.0175
0.9767
0.0031
0.0028
0.0000
0.0000
low_veg
0.0783
0.0204
0.7911
0.1101
0.0002
0.0000
tree
0.0115
0.0010
0.0483
0.9391
0.0001
0.0000
car
0.0935
0.0006
0.0014
0.0045
0.8852
0.0148
clutter
--
--
--
--
--
--
Precision/Correctness
0.931
0.952
0.863
0.908
0.833
--
Recall/Completeness
0.934
0.977
0.791
0.939
0.885
--
F1
0.932
0.964
0.825
0.923
0.859
--

Overall accuracy 0.915

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
0.8250
0.0372
0.0954
0.0355
0.0069
0.0000
building
0.0598
0.8728
0.0584
0.0091
0.0000
0.0000
low_veg
0.0250
0.0138
0.8787
0.0823
0.0000
0.0000
tree
0.0179
0.0067
0.1564
0.8189
0.0001
0.0000
car
0.1674
0.0028
0.0115
0.0029
0.8154
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.818
0.928
0.848
0.836
0.750
--
Recall/Completeness
0.825
0.873
0.879
0.819
0.815
--
F1
0.821
0.899
0.863
0.827
0.781
--

Overall accuracy 0.854

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area24_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8566
0.0284
0.0853
0.0248
0.0048
0.0000
building
0.0556
0.8876
0.0507
0.0060
0.0000
0.0000
low_veg
0.0215
0.0098
0.8976
0.0711
0.0000
0.0000
tree
0.0114
0.0034
0.1335
0.8517
0.0000
0.0000
car
0.0826
0.0025
0.0107
0.0010
0.9032
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.844
0.950
0.872
0.861
0.778
--
Recall/Completeness
0.857
0.888
0.898
0.852
0.903
--
F1
0.850
0.918
0.884
0.856
0.836
--

Overall accuracy 0.878

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area27_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9332
0.0261
0.0267
0.0070
0.0070
0.0000
building
0.0564
0.9243
0.0155
0.0036
0.0002
0.0000
low_veg
0.0805
0.0350
0.6812
0.2028
0.0005
0.0000
tree
0.0131
0.0057
0.0644
0.9167
0.0001
0.0000
car
0.2579
0.0051
0.0044
0.0053
0.7273
0.0000
clutter
0.6672
0.2175
0.0592
0.0031
0.0530
0.0000
Precision/Correctness
0.864
0.952
0.866
0.679
0.903
-nan
Recall/Completeness
0.933
0.924
0.681
0.917
0.727
0.000
F1
0.897
0.938
0.762
0.780
0.806
-nan

Overall accuracy 0.870

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
0.9596
0.0160
0.0195
0.0026
0.0023
0.0000
building
0.0452
0.9434
0.0101
0.0011
0.0001
0.0000
low_veg
0.0631
0.0211
0.7224
0.1933
0.0001
0.0000
tree
0.0055
0.0021
0.0486
0.9439
0.0000
0.0000
car
0.1457
0.0026
0.0023
0.0045
0.8449
0.0000
clutter
0.6509
0.2379
0.0425
0.0005
0.0681
0.0000
Precision/Correctness
0.900
0.972
0.903
0.709
0.956
-nan
Recall/Completeness
0.960
0.943
0.722
0.944
0.845
0.000
F1
0.929
0.958
0.803
0.809
0.897
-nan

Overall accuracy 0.902

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
0.9399
0.0194
0.0209
0.0139
0.0059
0.0001
building
0.0245
0.9565
0.0108
0.0082
0.0000
0.0000
low_veg
0.0714
0.0206
0.6098
0.2975
0.0008
0.0000
tree
0.0045
0.0013
0.0254
0.9687
0.0000
0.0000
car
0.1969
0.0071
0.0025
0.0135
0.7555
0.0246
clutter
0.5447
0.3471
0.0335
0.0104
0.0366
0.0277
Precision/Correctness
0.916
0.923
0.853
0.668
0.733
0.691
Recall/Completeness
0.940
0.956
0.610
0.969
0.756
0.028
F1
0.928
0.939
0.711
0.791
0.744
0.053

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_area29_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9612
0.0140
0.0144
0.0062
0.0042
0.0000
building
0.0176
0.9719
0.0061
0.0044
0.0000
0.0000
low_veg
0.0480
0.0086
0.6551
0.2880
0.0003
0.0000
tree
0.0010
0.0002
0.0168
0.9820
0.0000
0.0000
car
0.1068
0.0076
0.0025
0.0105
0.8448
0.0278
clutter
0.5257
0.3747
0.0262
0.0053
0.0360
0.0321
Precision/Correctness
0.939
0.940
0.896
0.706
0.753
0.749
Recall/Completeness
0.961
0.972
0.655
0.982
0.845
0.032
F1
0.950
0.956
0.757
0.821
0.796
0.062

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
0.9681
0.0068
0.0107
0.0058
0.0078
0.0008
building
0.0517
0.9311
0.0123
0.0022
0.0027
0.0000
low_veg
0.0562
0.0012
0.9070
0.0344
0.0011
0.0000
tree
0.0427
0.0036
0.0876
0.8652
0.0009
0.0000
car
0.1699
0.0883
0.0062
0.0033
0.7323
0.0000
clutter
0.4887
0.2239
0.0165
0.0147
0.0408
0.2155
Precision/Correctness
0.883
0.949
0.881
0.919
0.829
0.960
Recall/Completeness
0.968
0.931
0.907
0.865
0.732
0.215
F1
0.923
0.940
0.894
0.892
0.778
0.352

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_area31_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9811
0.0052
0.0077
0.0022
0.0036
0.0003
building
0.0371
0.9535
0.0067
0.0005
0.0023
0.0000
low_veg
0.0367
0.0001
0.9355
0.0274
0.0003
0.0000
tree
0.0173
0.0007
0.0702
0.9117
0.0001
0.0000
car
0.0870
0.1003
0.0028
0.0005
0.8095
0.0000
clutter
0.4407
0.2518
0.0154
0.0064
0.0431
0.2425
Precision/Correctness
0.918
0.956
0.914
0.950
0.871
0.985
Recall/Completeness
0.981
0.953
0.936
0.912
0.809
0.243
F1
0.949
0.955
0.925
0.930
0.839
0.389

Overall accuracy 0.931

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
0.9689
0.0118
0.0079
0.0046
0.0024
0.0044
building
0.0889
0.8117
0.0943
0.0042
0.0008
0.0002
low_veg
0.0616
0.0197
0.8831
0.0351
0.0005
0.0000
tree
0.0395
0.0089
0.1263
0.8252
0.0000
0.0000
car
0.2334
0.0473
0.0032
0.0023
0.7068
0.0069
clutter
0.3646
0.0596
0.0023
0.0000
0.0080
0.5655
Precision/Correctness
0.857
0.950
0.756
0.911
0.845
0.944
Recall/Completeness
0.969
0.812
0.883
0.825
0.707
0.566
F1
0.910
0.875
0.815
0.866
0.770
0.707

Overall accuracy 0.870

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
0.9850
0.0078
0.0035
0.0014
0.0012
0.0011
building
0.0824
0.8223
0.0927
0.0018
0.0007
0.0001
low_veg
0.0324
0.0135
0.9232
0.0305
0.0004
0.0000
tree
0.0171
0.0031
0.1171
0.8627
0.0000
0.0000
car
0.1308
0.0599
0.0010
0.0008
0.8011
0.0064
clutter
0.3317
0.0558
0.0009
0.0000
0.0079
0.6036
Precision/Correctness
0.885
0.966
0.772
0.939
0.876
0.983
Recall/Completeness
0.985
0.822
0.923
0.863
0.801
0.604
F1
0.932
0.888
0.841
0.899
0.837
0.748

Overall accuracy 0.893

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
0.8570
0.0488
0.0729
0.0198
0.0015
0.0001
building
0.0273
0.9447
0.0202
0.0074
0.0005
0.0000
low_veg
0.0512
0.0137
0.7044
0.2306
0.0001
0.0000
tree
0.0387
0.0056
0.1085
0.8471
0.0001
0.0000
car
0.2326
0.0075
0.0063
0.0147
0.7390
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.875
0.937
0.781
0.755
0.910
--
Recall/Completeness
0.857
0.945
0.704
0.847
0.739
--
F1
0.866
0.941
0.741
0.799
0.816
--

Overall accuracy 0.839

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
0.8953
0.0444
0.0530
0.0068
0.0005
0.0001
building
0.0178
0.9700
0.0099
0.0019
0.0005
0.0000
low_veg
0.0350
0.0059
0.7353
0.2238
0.0000
0.0000
tree
0.0153
0.0015
0.0838
0.8994
0.0000
0.0000
car
0.1173
0.0060
0.0055
0.0063
0.8650
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.926
0.955
0.837
0.783
0.949
--
Recall/Completeness
0.895
0.970
0.735
0.899
0.865
--
F1
0.910
0.963
0.783
0.837
0.905
--

Overall accuracy 0.878

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area38_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8911
0.0328
0.0507
0.0214
0.0038
0.0003
building
0.0225
0.9277
0.0437
0.0047
0.0014
0.0000
low_veg
0.0527
0.0310
0.8188
0.0972
0.0002
0.0000
tree
0.0221
0.0053
0.1075
0.8650
0.0001
0.0000
car
0.2081
0.0082
0.0354
0.0056
0.7428
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.899
0.927
0.833
0.832
0.830
--
Recall/Completeness
0.891
0.928
0.819
0.865
0.743
--
F1
0.895
0.927
0.826
0.848
0.784
--

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
0.9209
0.0307
0.0368
0.0098
0.0016
0.0003
building
0.0154
0.9526
0.0293
0.0015
0.0012
0.0000
low_veg
0.0394
0.0275
0.8527
0.0803
0.0000
0.0000
tree
0.0084
0.0019
0.0862
0.9036
0.0000
0.0000
car
0.1197
0.0068
0.0257
0.0025
0.8453
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.934
0.939
0.873
0.872
0.893
--
Recall/Completeness
0.921
0.953
0.853
0.904
0.845
--
F1
0.928
0.946
0.863
0.887
0.868
--

Overall accuracy 0.907

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image