Detailled semantic labeling (2D) result


Name W. Sun
Affiliation Univ. of Calgary, Canada
Abbreviation UCal10
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
0.892
0.044
0.040
0.018
0.005
0.000
building
0.034
0.940
0.020
0.006
0.000
0.000
low_veg
0.054
0.042
0.770
0.134
0.000
0.000
tree
0.022
0.013
0.090
0.875
0.000
0.000
car
0.231
0.014
0.008
0.006
0.739
0.002
clutter
0.346
0.262
0.013
0.008
0.017
0.355
Precision/Correctness
0.887
0.901
0.818
0.848
0.845
0.951
Recall/Completeness
0.892
0.940
0.770
0.875
0.739
0.355
F1
0.890
0.920
0.793
0.861
0.788
0.517

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
0.921
0.034
0.033
0.009
0.003
0.000
building
0.028
0.954
0.015
0.003
0.000
0.000
low_veg
0.042
0.030
0.809
0.119
0.000
0.000
tree
0.011
0.007
0.075
0.907
0.000
0.000
car
0.136
0.012
0.005
0.003
0.842
0.003
clutter
0.309
0.278
0.010
0.004
0.017
0.383
Precision/Correctness
0.918
0.928
0.850
0.878
0.888
0.976
Recall/Completeness
0.921
0.954
0.809
0.907
0.842
0.383
F1
0.920
0.941
0.829
0.893
0.864
0.550

Overall accuracy 0.898
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9445
0.0180
0.0201
0.0122
0.0052
0.0000
building
0.0344
0.9440
0.0172
0.0044
0.0000
0.0000
low_veg
0.0813
0.0363
0.7124
0.1698
0.0002
0.0000
tree
0.0319
0.0113
0.0831
0.8721
0.0004
0.0013
car
0.2577
0.0031
0.0005
0.0010
0.7376
0.0000
clutter
0.0015
0.0000
0.0027
0.0142
0.0000
0.9816
Precision/Correctness
0.856
0.930
0.855
0.824
0.890
0.983
Recall/Completeness
0.945
0.944
0.712
0.872
0.738
0.982
F1
0.898
0.937
0.777
0.848
0.807
0.982

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
0.9666
0.0131
0.0125
0.0042
0.0037
0.0000
building
0.0268
0.9613
0.0107
0.0013
0.0000
0.0000
low_veg
0.0629
0.0241
0.7487
0.1643
0.0001
0.0000
tree
0.0154
0.0066
0.0714
0.9058
0.0002
0.0005
car
0.1223
0.0026
0.0000
0.0001
0.8749
0.0000
clutter
0.0013
0.0000
0.0024
0.0043
0.0000
0.9920
Precision/Correctness
0.899
0.955
0.884
0.847
0.914
0.993
Recall/Completeness
0.967
0.961
0.749
0.906
0.875
0.992
F1
0.932
0.958
0.811
0.876
0.894
0.993

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: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8765
0.1034
0.0107
0.0048
0.0045
0.0000
building
0.0428
0.9520
0.0037
0.0012
0.0002
0.0000
low_veg
0.1241
0.1545
0.5204
0.1991
0.0019
0.0000
tree
0.0440
0.0371
0.0752
0.8434
0.0004
0.0000
car
0.2913
0.0157
0.0018
0.0036
0.6877
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.877
0.932
0.724
0.786
0.865
--
Recall/Completeness
0.877
0.952
0.520
0.843
0.688
--
F1
0.877
0.942
0.606
0.814
0.766
--

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: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9163
0.0718
0.0073
0.0020
0.0025
0.0000
building
0.0339
0.9627
0.0026
0.0005
0.0002
0.0000
low_veg
0.0876
0.1207
0.5687
0.2218
0.0012
0.0000
tree
0.0187
0.0211
0.0688
0.8914
0.0000
0.0000
car
0.1755
0.0082
0.0011
0.0022
0.8130
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.909
0.955
0.768
0.811
0.907
--
Recall/Completeness
0.916
0.963
0.569
0.891
0.813
--
F1
0.912
0.959
0.654
0.849
0.858
--

Overall accuracy 0.928

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
0.8829
0.0623
0.0353
0.0139
0.0056
0.0000
building
0.0302
0.9513
0.0124
0.0060
0.0001
0.0000
low_veg
0.0858
0.0501
0.7303
0.1333
0.0005
0.0000
tree
0.0161
0.0125
0.0629
0.9084
0.0001
0.0000
car
0.3081
0.0390
0.0008
0.0013
0.6507
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.886
0.925
0.714
0.930
0.874
--
Recall/Completeness
0.883
0.951
0.730
0.908
0.651
--
F1
0.885
0.938
0.722
0.919
0.746
--

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
0.9236
0.0403
0.0269
0.0066
0.0026
0.0000
building
0.0231
0.9650
0.0085
0.0034
0.0000
0.0000
low_veg
0.0704
0.0319
0.7837
0.1139
0.0001
0.0000
tree
0.0063
0.0070
0.0500
0.9367
0.0000
0.0000
car
0.2167
0.0348
0.0001
0.0001
0.7483
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.923
0.955
0.757
0.953
0.933
--
Recall/Completeness
0.924
0.965
0.784
0.937
0.748
--
F1
0.923
0.960
0.770
0.945
0.830
--

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
0.8766
0.0462
0.0602
0.0126
0.0043
0.0002
building
0.0243
0.9603
0.0128
0.0026
0.0000
0.0000
low_veg
0.0465
0.0212
0.8764
0.0551
0.0007
0.0000
tree
0.0293
0.0108
0.0743
0.8855
0.0002
0.0000
car
0.2424
0.0039
0.0151
0.0043
0.7341
0.0002
clutter
--
--
--
--
--
--
Precision/Correctness
0.914
0.912
0.812
0.932
0.891
--
Recall/Completeness
0.877
0.960
0.876
0.885
0.734
--
F1
0.895
0.936
0.843
0.908
0.805
--

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_area8_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9061
0.0361
0.0509
0.0050
0.0018
0.0002
building
0.0169
0.9762
0.0061
0.0007
0.0000
0.0000
low_veg
0.0304
0.0107
0.9154
0.0431
0.0004
0.0000
tree
0.0129
0.0058
0.0569
0.9243
0.0000
0.0000
car
0.1411
0.0024
0.0100
0.0028
0.8434
0.0003
clutter
--
--
--
--
--
--
Precision/Correctness
0.950
0.940
0.851
0.956
0.945
--
Recall/Completeness
0.906
0.976
0.915
0.924
0.843
--
F1
0.928
0.958
0.882
0.940
0.891
--

Overall accuracy 0.928

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
0.8125
0.1062
0.0555
0.0202
0.0057
0.0000
building
0.0402
0.9306
0.0192
0.0096
0.0004
0.0000
low_veg
0.0762
0.0447
0.7240
0.1551
0.0000
0.0000
tree
0.0170
0.0136
0.0870
0.8824
0.0000
0.0000
car
0.1718
0.0082
0.0144
0.0174
0.7882
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.917
0.813
0.746
0.830
0.714
--
Recall/Completeness
0.812
0.931
0.724
0.882
0.788
--
F1
0.862
0.868
0.735
0.855
0.749
--

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_area10_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8429
0.0943
0.0490
0.0093
0.0045
0.0000
building
0.0337
0.9458
0.0143
0.0059
0.0003
0.0000
low_veg
0.0704
0.0309
0.7700
0.1287
0.0000
0.0000
tree
0.0076
0.0085
0.0682
0.9157
0.0000
0.0000
car
0.0830
0.0056
0.0118
0.0174
0.8822
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.936
0.841
0.783
0.872
0.722
--
Recall/Completeness
0.843
0.946
0.770
0.916
0.882
--
F1
0.887
0.890
0.777
0.893
0.794
--

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_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8793
0.0343
0.0520
0.0315
0.0029
0.0000
building
0.0671
0.9075
0.0160
0.0093
0.0000
0.0000
low_veg
0.0386
0.0378
0.7684
0.1546
0.0001
0.0005
tree
0.0105
0.0113
0.1066
0.8716
0.0000
0.0000
car
0.1792
0.0000
0.0032
0.0082
0.8094
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.812
0.897
0.817
0.863
0.900
--
Recall/Completeness
0.879
0.908
0.768
0.872
0.809
--
F1
0.845
0.902
0.792
0.867
0.852
--

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_area12_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9069
0.0305
0.0452
0.0168
0.0007
0.0000
building
0.0687
0.9189
0.0089
0.0035
0.0000
0.0000
low_veg
0.0359
0.0239
0.8084
0.1312
0.0000
0.0006
tree
0.0048
0.0058
0.0896
0.8998
0.0000
0.0000
car
0.0785
0.0000
0.0016
0.0012
0.9187
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.835
0.931
0.847
0.893
0.970
--
Recall/Completeness
0.907
0.919
0.808
0.900
0.919
--
F1
0.869
0.925
0.827
0.896
0.944
--

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
0.8091
0.0457
0.1084
0.0309
0.0059
0.0000
building
0.0134
0.9608
0.0161
0.0097
0.0000
0.0000
low_veg
0.0667
0.0678
0.7108
0.1543
0.0004
0.0000
tree
0.0258
0.0200
0.1118
0.8423
0.0000
0.0000
car
0.1309
0.0000
0.0000
0.0017
0.8674
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.868
0.831
0.735
0.855
0.610
--
Recall/Completeness
0.809
0.961
0.711
0.842
0.867
--
F1
0.837
0.891
0.723
0.848
0.716
--

Overall accuracy 0.822

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
0.8290
0.0400
0.1057
0.0201
0.0051
0.0000
building
0.0102
0.9764
0.0077
0.0057
0.0000
0.0000
low_veg
0.0617
0.0509
0.7429
0.1442
0.0004
0.0000
tree
0.0180
0.0119
0.1002
0.8700
0.0000
0.0000
car
0.0328
0.0000
0.0000
0.0000
0.9672
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.893
0.867
0.755
0.876
0.595
--
Recall/Completeness
0.829
0.976
0.743
0.870
0.967
--
F1
0.860
0.919
0.749
0.873
0.737
--

Overall accuracy 0.847

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
0.8229
0.0429
0.0813
0.0499
0.0030
0.0000
building
0.0199
0.9597
0.0113
0.0091
0.0000
0.0000
low_veg
0.0157
0.0242
0.8634
0.0966
0.0000
0.0000
tree
0.0228
0.0121
0.1198
0.8453
0.0000
0.0000
car
0.1485
0.0047
0.0402
0.0003
0.8063
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.883
0.903
0.814
0.891
0.787
--
Recall/Completeness
0.823
0.960
0.863
0.845
0.806
--
F1
0.852
0.931
0.838
0.867
0.796
--

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_area16_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8575
0.0371
0.0734
0.0304
0.0016
0.0000
building
0.0164
0.9759
0.0040
0.0037
0.0000
0.0000
low_veg
0.0118
0.0142
0.8921
0.0818
0.0000
0.0000
tree
0.0157
0.0066
0.1069
0.8708
0.0000
0.0000
car
0.0791
0.0011
0.0303
0.0000
0.8895
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.913
0.934
0.838
0.916
0.848
--
Recall/Completeness
0.858
0.976
0.892
0.871
0.890
--
F1
0.884
0.955
0.864
0.893
0.868
--

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_area20_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8689
0.0549
0.0331
0.0401
0.0029
0.0001
building
0.0034
0.9789
0.0094
0.0082
0.0000
0.0000
low_veg
0.0628
0.0490
0.7287
0.1594
0.0000
0.0000
tree
0.0097
0.0054
0.0477
0.9372
0.0000
0.0000
car
0.0914
0.0047
0.0088
0.0063
0.8887
0.0000
clutter
0.0000
0.9999
0.0000
0.0001
0.0000
0.0000
Precision/Correctness
0.911
0.763
0.835
0.905
0.862
0.000
Recall/Completeness
0.869
0.979
0.729
0.937
0.889
0.000
F1
0.889
0.857
0.778
0.921
0.875
-nan

Overall accuracy 0.864

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
0.9048
0.0406
0.0310
0.0227
0.0007
0.0002
building
0.0020
0.9898
0.0058
0.0025
0.0000
0.0000
low_veg
0.0568
0.0345
0.7773
0.1313
0.0000
0.0000
tree
0.0043
0.0025
0.0360
0.9572
0.0000
0.0000
car
0.0148
0.0015
0.0003
0.0011
0.9824
0.0000
clutter
0.0000
1.0000
0.0000
0.0000
0.0000
0.0000
Precision/Correctness
0.935
0.790
0.866
0.932
0.955
0.000
Recall/Completeness
0.905
0.990
0.777
0.957
0.982
0.000
F1
0.920
0.879
0.819
0.944
0.968
-nan

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_area22_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9022
0.0264
0.0351
0.0295
0.0069
0.0000
building
0.0155
0.9646
0.0095
0.0103
0.0001
0.0000
low_veg
0.0818
0.0533
0.7267
0.1377
0.0005
0.0000
tree
0.0261
0.0079
0.0644
0.9014
0.0001
0.0000
car
0.1988
0.0001
0.0021
0.0128
0.7740
0.0123
clutter
--
--
--
--
--
--
Precision/Correctness
0.909
0.889
0.823
0.869
0.782
--
Recall/Completeness
0.902
0.965
0.727
0.901
0.774
--
F1
0.905
0.925
0.772
0.885
0.778
--

Overall accuracy 0.876

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
0.9343
0.0166
0.0292
0.0154
0.0045
0.0000
building
0.0102
0.9800
0.0044
0.0054
0.0001
0.0000
low_veg
0.0789
0.0346
0.7763
0.1098
0.0004
0.0000
tree
0.0116
0.0039
0.0478
0.9367
0.0000
0.0000
car
0.1042
0.0000
0.0006
0.0051
0.8733
0.0167
clutter
--
--
--
--
--
--
Precision/Correctness
0.934
0.931
0.863
0.907
0.821
--
Recall/Completeness
0.934
0.980
0.776
0.937
0.873
--
F1
0.934
0.955
0.818
0.922
0.846
--

Overall accuracy 0.912

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
0.8178
0.0449
0.0959
0.0345
0.0069
0.0000
building
0.0496
0.8904
0.0511
0.0089
0.0000
0.0000
low_veg
0.0238
0.0161
0.8787
0.0815
0.0000
0.0000
tree
0.0170
0.0131
0.1494
0.8203
0.0001
0.0000
car
0.1537
0.0000
0.0119
0.0027
0.8317
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.832
0.911
0.854
0.838
0.749
--
Recall/Completeness
0.818
0.890
0.879
0.820
0.832
--
F1
0.825
0.900
0.866
0.829
0.788
--

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
0.8506
0.0350
0.0859
0.0237
0.0049
0.0000
building
0.0471
0.9022
0.0448
0.0059
0.0000
0.0000
low_veg
0.0207
0.0102
0.8988
0.0703
0.0000
0.0000
tree
0.0106
0.0085
0.1280
0.8529
0.0001
0.0000
car
0.0702
0.0000
0.0095
0.0007
0.9197
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.856
0.938
0.877
0.863
0.777
--
Recall/Completeness
0.851
0.902
0.899
0.853
0.920
--
F1
0.853
0.920
0.888
0.858
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_area27_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9210
0.0390
0.0258
0.0071
0.0071
0.0000
building
0.0423
0.9390
0.0138
0.0047
0.0002
0.0000
low_veg
0.0723
0.0629
0.6658
0.1984
0.0005
0.0000
tree
0.0104
0.0177
0.0551
0.9167
0.0001
0.0000
car
0.2447
0.0110
0.0043
0.0056
0.7344
0.0000
clutter
0.7027
0.2111
0.0563
0.0036
0.0264
0.0000
Precision/Correctness
0.881
0.923
0.874
0.681
0.905
0.000
Recall/Completeness
0.921
0.939
0.666
0.917
0.734
0.000
F1
0.901
0.931
0.756
0.782
0.811
-nan

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_area27_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9506
0.0255
0.0189
0.0027
0.0023
0.0000
building
0.0334
0.9548
0.0094
0.0023
0.0001
0.0000
low_veg
0.0565
0.0448
0.7094
0.1892
0.0001
0.0000
tree
0.0036
0.0109
0.0392
0.9463
0.0000
0.0000
car
0.1358
0.0075
0.0026
0.0046
0.8495
0.0000
clutter
0.7311
0.2020
0.0360
0.0002
0.0307
0.0000
Precision/Correctness
0.915
0.950
0.909
0.711
0.961
-nan
Recall/Completeness
0.951
0.955
0.709
0.946
0.849
0.000
F1
0.933
0.952
0.797
0.812
0.902
-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
0.9348
0.0269
0.0176
0.0144
0.0062
0.0001
building
0.0162
0.9700
0.0080
0.0058
0.0000
0.0000
low_veg
0.0684
0.0426
0.5983
0.2898
0.0010
0.0000
tree
0.0055
0.0113
0.0240
0.9591
0.0000
0.0000
car
0.1820
0.0102
0.0003
0.0142
0.7692
0.0241
clutter
0.6287
0.2646
0.0311
0.0121
0.0352
0.0282
Precision/Correctness
0.916
0.907
0.870
0.673
0.730
0.694
Recall/Completeness
0.935
0.970
0.598
0.959
0.769
0.028
F1
0.925
0.938
0.709
0.791
0.749
0.054

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
0.9583
0.0182
0.0119
0.0070
0.0045
0.0000
building
0.0115
0.9810
0.0045
0.0030
0.0000
0.0000
low_veg
0.0468
0.0250
0.6470
0.2806
0.0006
0.0000
tree
0.0012
0.0064
0.0159
0.9765
0.0000
0.0000
car
0.0968
0.0045
0.0001
0.0112
0.8605
0.0270
clutter
0.6128
0.2888
0.0234
0.0073
0.0344
0.0333
Precision/Correctness
0.938
0.933
0.911
0.709
0.749
0.755
Recall/Completeness
0.958
0.981
0.647
0.977
0.860
0.033
F1
0.948
0.956
0.757
0.822
0.801
0.064

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
0.9574
0.0166
0.0118
0.0059
0.0078
0.0005
building
0.0397
0.9488
0.0076
0.0018
0.0021
0.0000
low_veg
0.0519
0.0108
0.8999
0.0357
0.0016
0.0001
tree
0.0400
0.0164
0.0762
0.8665
0.0009
0.0000
car
0.2332
0.0258
0.0092
0.0034
0.7284
0.0000
clutter
0.5095
0.2295
0.0231
0.0151
0.0340
0.1889
Precision/Correctness
0.884
0.934
0.891
0.918
0.837
0.969
Recall/Completeness
0.957
0.949
0.900
0.866
0.728
0.189
F1
0.919
0.941
0.895
0.892
0.779
0.316

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_area31_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9752
0.0105
0.0089
0.0020
0.0033
0.0001
building
0.0321
0.9606
0.0052
0.0004
0.0017
0.0000
low_veg
0.0351
0.0050
0.9308
0.0286
0.0006
0.0000
tree
0.0160
0.0096
0.0607
0.9137
0.0001
0.0000
car
0.1684
0.0294
0.0050
0.0005
0.7967
0.0000
clutter
0.4602
0.2603
0.0236
0.0074
0.0362
0.2123
Precision/Correctness
0.916
0.950
0.918
0.949
0.885
0.992
Recall/Completeness
0.975
0.961
0.931
0.914
0.797
0.212
F1
0.944
0.955
0.924
0.931
0.838
0.350

Overall accuracy 0.929

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
0.9612
0.0196
0.0074
0.0051
0.0026
0.0041
building
0.0786
0.8266
0.0909
0.0039
0.0000
0.0000
low_veg
0.0577
0.0245
0.8820
0.0354
0.0004
0.0000
tree
0.0396
0.0187
0.1178
0.8239
0.0000
0.0000
car
0.2520
0.0072
0.0031
0.0017
0.7289
0.0071
clutter
0.3838
0.0430
0.0014
0.0002
0.0099
0.5617
Precision/Correctness
0.861
0.938
0.765
0.910
0.855
0.948
Recall/Completeness
0.961
0.827
0.882
0.824
0.729
0.562
F1
0.908
0.879
0.819
0.865
0.787
0.705

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_area33_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9803
0.0127
0.0031
0.0016
0.0013
0.0010
building
0.0740
0.8345
0.0897
0.0019
0.0000
0.0000
low_veg
0.0291
0.0172
0.9226
0.0310
0.0001
0.0000
tree
0.0171
0.0114
0.1096
0.8618
0.0000
0.0000
car
0.1643
0.0021
0.0009
0.0006
0.8256
0.0065
clutter
0.3546
0.0324
0.0003
0.0000
0.0101
0.6025
Precision/Correctness
0.888
0.961
0.780
0.937
0.887
0.986
Recall/Completeness
0.980
0.834
0.923
0.862
0.826
0.603
F1
0.932
0.893
0.845
0.898
0.855
0.748

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_area35_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8559
0.0494
0.0731
0.0200
0.0016
0.0000
building
0.0265
0.9449
0.0219
0.0063
0.0004
0.0000
low_veg
0.0499
0.0294
0.6999
0.2208
0.0000
0.0000
tree
0.0400
0.0137
0.1083
0.8380
0.0001
0.0000
car
0.2183
0.0138
0.0025
0.0158
0.7497
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.876
0.916
0.778
0.761
0.911
--
Recall/Completeness
0.856
0.945
0.700
0.838
0.750
--
F1
0.866
0.930
0.737
0.798
0.822
--

Overall accuracy 0.836

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area35_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8955
0.0422
0.0547
0.0071
0.0006
0.0000
building
0.0177
0.9668
0.0132
0.0019
0.0004
0.0000
low_veg
0.0355
0.0170
0.7330
0.2144
0.0000
0.0000
tree
0.0160
0.0072
0.0847
0.8921
0.0000
0.0000
car
0.1079
0.0120
0.0020
0.0083
0.8698
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.925
0.944
0.831
0.788
0.951
--
Recall/Completeness
0.895
0.967
0.733
0.892
0.870
--
F1
0.910
0.955
0.779
0.837
0.909
--

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_area38_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8898
0.0358
0.0508
0.0200
0.0033
0.0003
building
0.0176
0.9358
0.0392
0.0061
0.0014
0.0000
low_veg
0.0410
0.0613
0.8040
0.0934
0.0002
0.0000
tree
0.0221
0.0113
0.1056
0.8609
0.0001
0.0000
car
0.1970
0.0199
0.0339
0.0055
0.7436
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.915
0.890
0.835
0.835
0.844
--
Recall/Completeness
0.890
0.936
0.804
0.861
0.744
--
F1
0.902
0.913
0.819
0.848
0.791
--

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_area38_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9220
0.0304
0.0374
0.0087
0.0011
0.0003
building
0.0121
0.9567
0.0271
0.0029
0.0012
0.0000
low_veg
0.0273
0.0551
0.8402
0.0773
0.0001
0.0000
tree
0.0086
0.0057
0.0852
0.9004
0.0000
0.0000
car
0.1061
0.0171
0.0248
0.0021
0.8499
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.949
0.911
0.874
0.875
0.907
--
Recall/Completeness
0.922
0.957
0.840
0.900
0.850
--
F1
0.936
0.933
0.857
0.887
0.878
--

Overall accuracy 0.904

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image