Detailled semantic labeling (2D) result


Name Y. Sun
Affiliation Huazhong University of Science and Technology (HUST), Wuhan, China
Abbreviation HUSTW5
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
0.906
0.028
0.043
0.019
0.005
0.000
building
0.030
0.947
0.017
0.006
0.001
0.000
low_veg
0.040
0.021
0.823
0.116
0.000
0.000
tree
0.016
0.006
0.086
0.892
0.000
0.000
car
0.364
0.014
0.013
0.006
0.598
0.005
clutter
0.326
0.260
0.026
0.012
0.090
0.288
Precision/Correctness
0.901
0.938
0.832
0.864
0.775
0.927
Recall/Completeness
0.906
0.947
0.823
0.892
0.598
0.288
F1
0.903
0.942
0.827
0.878
0.675
0.439

Overall accuracy 0.886

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
0.935
0.020
0.033
0.009
0.002
0.000
building
0.024
0.963
0.010
0.003
0.000
0.000
low_veg
0.029
0.012
0.861
0.098
0.000
0.000
tree
0.007
0.002
0.070
0.921
0.000
0.000
car
0.281
0.013
0.009
0.003
0.688
0.006
clutter
0.281
0.279
0.020
0.007
0.093
0.320
Precision/Correctness
0.931
0.959
0.868
0.896
0.814
0.950
Recall/Completeness
0.935
0.963
0.861
0.921
0.688
0.320
F1
0.933
0.961
0.864
0.908
0.746
0.479

Overall accuracy 0.916
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9342
0.0122
0.0334
0.0141
0.0056
0.0005
building
0.0179
0.9552
0.0219
0.0049
0.0000
0.0000
low_veg
0.0484
0.0231
0.8156
0.1126
0.0002
0.0000
tree
0.0209
0.0069
0.0930
0.8781
0.0001
0.0010
car
0.4130
0.0018
0.0043
0.0021
0.5679
0.0110
clutter
0.0716
0.0021
0.0001
0.0124
0.0043
0.9095
Precision/Correctness
0.890
0.954
0.846
0.870
0.849
0.968
Recall/Completeness
0.934
0.955
0.816
0.878
0.568
0.910
F1
0.912
0.955
0.830
0.874
0.680
0.938

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_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9639
0.0069
0.0203
0.0049
0.0038
0.0004
building
0.0128
0.9696
0.0144
0.0031
0.0000
0.0000
low_veg
0.0355
0.0104
0.8507
0.1033
0.0002
0.0000
tree
0.0089
0.0025
0.0790
0.9093
0.0000
0.0004
car
0.3128
0.0001
0.0040
0.0009
0.6710
0.0112
clutter
0.0703
0.0012
0.0000
0.0018
0.0041
0.9225
Precision/Correctness
0.926
0.979
0.879
0.895
0.884
0.983
Recall/Completeness
0.964
0.970
0.851
0.909
0.671
0.923
F1
0.945
0.974
0.864
0.902
0.763
0.952

Overall accuracy 0.920

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
0.8964
0.0742
0.0189
0.0059
0.0045
0.0001
building
0.0384
0.9482
0.0103
0.0031
0.0000
0.0000
low_veg
0.1188
0.0708
0.5926
0.2171
0.0006
0.0000
tree
0.0475
0.0187
0.0723
0.8612
0.0002
0.0001
car
0.5390
0.0255
0.0071
0.0025
0.4220
0.0039
clutter
--
--
--
--
--
--
Precision/Correctness
0.876
0.953
0.640
0.759
0.817
--
Recall/Completeness
0.896
0.948
0.593
0.861
0.422
--
F1
0.886
0.951
0.615
0.807
0.556
--

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
0.9279
0.0506
0.0151
0.0034
0.0028
0.0001
building
0.0274
0.9613
0.0089
0.0023
0.0000
0.0000
low_veg
0.0868
0.0357
0.6434
0.2339
0.0001
0.0001
tree
0.0213
0.0060
0.0658
0.9068
0.0000
0.0000
car
0.4808
0.0176
0.0057
0.0024
0.4886
0.0050
clutter
--
--
--
--
--
--
Precision/Correctness
0.911
0.972
0.669
0.784
0.867
--
Recall/Completeness
0.928
0.961
0.643
0.907
0.489
--
F1
0.919
0.967
0.656
0.841
0.625
--

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
0.8916
0.0556
0.0375
0.0121
0.0031
0.0001
building
0.0268
0.9516
0.0160
0.0057
0.0000
0.0000
low_veg
0.0518
0.0442
0.7773
0.1267
0.0000
0.0000
tree
0.0114
0.0037
0.0508
0.9340
0.0000
0.0001
car
0.4522
0.0129
0.0096
0.0039
0.5191
0.0023
clutter
--
--
--
--
--
--
Precision/Correctness
0.901
0.940
0.737
0.935
0.913
--
Recall/Completeness
0.892
0.952
0.777
0.934
0.519
--
F1
0.896
0.946
0.756
0.935
0.662
--

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_area6_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9251
0.0407
0.0280
0.0049
0.0013
0.0000
building
0.0181
0.9681
0.0104
0.0035
0.0000
0.0000
low_veg
0.0361
0.0314
0.8324
0.1002
0.0000
0.0000
tree
0.0031
0.0009
0.0385
0.9574
0.0000
0.0000
car
0.3570
0.0043
0.0081
0.0029
0.6261
0.0016
clutter
--
--
--
--
--
--
Precision/Correctness
0.939
0.961
0.786
0.959
0.960
--
Recall/Completeness
0.925
0.968
0.832
0.957
0.626
--
F1
0.932
0.965
0.808
0.958
0.758
--

Overall accuracy 0.937

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
0.8808
0.0292
0.0739
0.0122
0.0039
0.0000
building
0.0308
0.9407
0.0229
0.0055
0.0000
0.0000
low_veg
0.0561
0.0131
0.8847
0.0461
0.0001
0.0000
tree
0.0197
0.0067
0.0938
0.8798
0.0000
0.0000
car
0.4283
0.0051
0.0281
0.0055
0.5328
0.0001
clutter
--
--
--
--
--
--
Precision/Correctness
0.902
0.942
0.772
0.937
0.878
--
Recall/Completeness
0.881
0.941
0.885
0.880
0.533
--
F1
0.891
0.941
0.824
0.907
0.663
--

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_area8_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9085
0.0239
0.0621
0.0037
0.0018
0.0000
building
0.0202
0.9629
0.0135
0.0034
0.0000
0.0000
low_veg
0.0414
0.0059
0.9181
0.0346
0.0001
0.0000
tree
0.0074
0.0028
0.0735
0.9163
0.0000
0.0000
car
0.3489
0.0035
0.0200
0.0044
0.6230
0.0001
clutter
--
--
--
--
--
--
Precision/Correctness
0.937
0.961
0.815
0.962
0.934
--
Recall/Completeness
0.909
0.963
0.918
0.916
0.623
--
F1
0.923
0.962
0.863
0.939
0.747
--

Overall accuracy 0.922

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
0.8793
0.0481
0.0466
0.0227
0.0032
0.0000
building
0.0138
0.9556
0.0184
0.0118
0.0005
0.0000
low_veg
0.0498
0.0278
0.7849
0.1374
0.0001
0.0000
tree
0.0134
0.0077
0.0736
0.9054
0.0000
0.0000
car
0.4105
0.0330
0.0125
0.0041
0.5396
0.0004
clutter
--
--
--
--
--
--
Precision/Correctness
0.949
0.901
0.788
0.840
0.740
--
Recall/Completeness
0.879
0.956
0.785
0.905
0.540
--
F1
0.913
0.928
0.787
0.871
0.624
--

Overall accuracy 0.884

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
0.9143
0.0350
0.0379
0.0105
0.0022
0.0000
building
0.0073
0.9724
0.0115
0.0084
0.0004
0.0000
low_veg
0.0442
0.0149
0.8360
0.1048
0.0000
0.0000
tree
0.0059
0.0034
0.0564
0.9343
0.0000
0.0000
car
0.3424
0.0357
0.0106
0.0021
0.6091
0.0001
clutter
--
--
--
--
--
--
Precision/Correctness
0.966
0.933
0.831
0.887
0.769
--
Recall/Completeness
0.914
0.972
0.836
0.934
0.609
--
F1
0.940
0.952
0.834
0.910
0.680
--

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_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8870
0.0221
0.0544
0.0338
0.0027
0.0000
building
0.0947
0.8813
0.0175
0.0063
0.0002
0.0000
low_veg
0.0328
0.0221
0.7834
0.1617
0.0001
0.0000
tree
0.0074
0.0079
0.0934
0.8912
0.0000
0.0000
car
0.2551
0.0000
0.0089
0.0051
0.7309
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.799
0.931
0.833
0.862
0.888
--
Recall/Completeness
0.887
0.881
0.783
0.891
0.731
--
F1
0.841
0.905
0.807
0.876
0.802
--

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_area12_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9177
0.0185
0.0450
0.0180
0.0008
0.0000
building
0.0989
0.8900
0.0084
0.0025
0.0002
0.0000
low_veg
0.0302
0.0132
0.8210
0.1357
0.0001
0.0000
tree
0.0031
0.0031
0.0779
0.9158
0.0000
0.0000
car
0.1354
0.0000
0.0095
0.0014
0.8537
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.817
0.958
0.863
0.891
0.949
--
Recall/Completeness
0.918
0.890
0.821
0.916
0.854
--
F1
0.864
0.923
0.841
0.903
0.899
--

Overall accuracy 0.884

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
0.8730
0.0251
0.0648
0.0354
0.0018
0.0000
building
0.0130
0.9552
0.0242
0.0076
0.0000
0.0000
low_veg
0.0574
0.0397
0.7653
0.1376
0.0000
0.0000
tree
0.0220
0.0093
0.1101
0.8585
0.0000
0.0000
car
0.2401
0.0000
0.0018
0.0046
0.7530
0.0005
clutter
--
--
--
--
--
--
Precision/Correctness
0.889
0.898
0.776
0.866
0.827
--
Recall/Completeness
0.873
0.955
0.765
0.858
0.753
--
F1
0.881
0.926
0.771
0.862
0.788
--

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_area14_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8943
0.0212
0.0589
0.0246
0.0010
0.0000
building
0.0079
0.9780
0.0110
0.0031
0.0000
0.0000
low_veg
0.0508
0.0271
0.7985
0.1236
0.0000
0.0000
tree
0.0146
0.0042
0.0970
0.8842
0.0000
0.0000
car
0.1310
0.0000
0.0008
0.0023
0.8654
0.0004
clutter
--
--
--
--
--
--
Precision/Correctness
0.916
0.929
0.804
0.890
0.878
--
Recall/Completeness
0.894
0.978
0.798
0.884
0.865
--
F1
0.905
0.953
0.801
0.887
0.872
--

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_area16_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8178
0.0192
0.1005
0.0609
0.0015
0.0000
building
0.0166
0.9518
0.0177
0.0138
0.0000
0.0000
low_veg
0.0106
0.0133
0.8402
0.1356
0.0002
0.0000
tree
0.0160
0.0046
0.0776
0.9018
0.0000
0.0000
car
0.3127
0.0033
0.0270
0.0100
0.6471
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.909
0.952
0.841
0.864
0.827
--
Recall/Completeness
0.818
0.952
0.840
0.902
0.647
--
F1
0.861
0.952
0.840
0.882
0.726
--

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_area16_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8558
0.0135
0.0920
0.0382
0.0004
0.0000
building
0.0142
0.9714
0.0084
0.0059
0.0000
0.0000
low_veg
0.0077
0.0070
0.8681
0.1169
0.0002
0.0000
tree
0.0095
0.0013
0.0657
0.9235
0.0000
0.0000
car
0.2300
0.0006
0.0161
0.0039
0.7495
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.937
0.974
0.867
0.891
0.897
--
Recall/Completeness
0.856
0.971
0.868
0.923
0.750
--
F1
0.895
0.973
0.868
0.907
0.817
--

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_area20_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8682
0.0168
0.0715
0.0419
0.0016
0.0000
building
0.0117
0.9526
0.0300
0.0057
0.0000
0.0000
low_veg
0.0340
0.0135
0.8100
0.1424
0.0000
0.0000
tree
0.0069
0.0013
0.0434
0.9484
0.0000
0.0000
car
0.3760
0.0001
0.0419
0.0100
0.5680
0.0040
clutter
0.0623
0.8389
0.0971
0.0018
0.0000
0.0000
Precision/Correctness
0.923
0.842
0.797
0.913
0.877
0.000
Recall/Completeness
0.868
0.953
0.810
0.948
0.568
0.000
F1
0.895
0.894
0.804
0.930
0.689
-nan

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_area20_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9013
0.0099
0.0657
0.0225
0.0006
0.0000
building
0.0096
0.9681
0.0207
0.0017
0.0000
0.0000
low_veg
0.0267
0.0053
0.8589
0.1091
0.0000
0.0000
tree
0.0026
0.0002
0.0319
0.9653
0.0000
0.0000
car
0.2823
0.0002
0.0315
0.0029
0.6806
0.0026
clutter
0.0584
0.8635
0.0776
0.0005
0.0000
0.0000
Precision/Correctness
0.947
0.855
0.831
0.942
0.945
0.000
Recall/Completeness
0.901
0.968
0.859
0.965
0.681
0.000
F1
0.924
0.908
0.845
0.953
0.791
-nan

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_area22_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8993
0.0195
0.0442
0.0334
0.0036
0.0000
building
0.0253
0.9458
0.0199
0.0089
0.0001
0.0000
low_veg
0.0677
0.0278
0.7727
0.1318
0.0000
0.0000
tree
0.0190
0.0034
0.0568
0.9207
0.0001
0.0000
car
0.4283
0.0032
0.0295
0.0087
0.5296
0.0008
clutter
--
--
--
--
--
--
Precision/Correctness
0.910
0.929
0.820
0.872
0.829
--
Recall/Completeness
0.899
0.946
0.773
0.921
0.530
--
F1
0.905
0.937
0.795
0.896
0.646
--

Overall accuracy 0.884

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
0.9316
0.0130
0.0372
0.0161
0.0020
0.0000
building
0.0173
0.9674
0.0106
0.0047
0.0000
0.0000
low_veg
0.0624
0.0156
0.8218
0.1001
0.0000
0.0000
tree
0.0077
0.0010
0.0412
0.9501
0.0000
0.0000
car
0.3541
0.0034
0.0230
0.0026
0.6166
0.0003
clutter
--
--
--
--
--
--
Precision/Correctness
0.937
0.959
0.861
0.914
0.884
--
Recall/Completeness
0.932
0.967
0.822
0.950
0.617
--
F1
0.934
0.963
0.841
0.932
0.726
--

Overall accuracy 0.919

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area24_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8204
0.0373
0.1007
0.0394
0.0022
0.0000
building
0.0480
0.9175
0.0266
0.0078
0.0000
0.0000
low_veg
0.0163
0.0161
0.8986
0.0689
0.0001
0.0000
tree
0.0121
0.0086
0.1093
0.8700
0.0000
0.0000
car
0.5005
0.0000
0.0029
0.0043
0.4923
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.852
0.924
0.886
0.861
0.842
--
Recall/Completeness
0.820
0.918
0.899
0.870
0.492
--
F1
0.836
0.921
0.892
0.866
0.621
--

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_area24_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8553
0.0266
0.0906
0.0267
0.0008
0.0000
building
0.0474
0.9301
0.0183
0.0042
0.0000
0.0000
low_veg
0.0136
0.0116
0.9204
0.0543
0.0001
0.0000
tree
0.0065
0.0048
0.0902
0.8986
0.0000
0.0000
car
0.4123
0.0000
0.0003
0.0002
0.5871
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.875
0.948
0.908
0.891
0.912
--
Recall/Completeness
0.855
0.930
0.920
0.899
0.587
--
F1
0.865
0.939
0.914
0.895
0.714
--

Overall accuracy 0.907

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area27_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9278
0.0271
0.0247
0.0079
0.0124
0.0002
building
0.0459
0.9352
0.0138
0.0044
0.0005
0.0002
low_veg
0.0608
0.0256
0.7559
0.1573
0.0003
0.0000
tree
0.0096
0.0067
0.0462
0.9373
0.0002
0.0000
car
0.3578
0.0066
0.0051
0.0074
0.6210
0.0021
clutter
0.7310
0.0865
0.0845
0.0121
0.0859
0.0000
Precision/Correctness
0.875
0.957
0.893
0.728
0.820
0.000
Recall/Completeness
0.928
0.935
0.756
0.937
0.621
0.000
F1
0.901
0.946
0.819
0.819
0.707
-nan

Overall accuracy 0.885

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
0.9582
0.0172
0.0161
0.0033
0.0050
0.0001
building
0.0355
0.9537
0.0078
0.0024
0.0004
0.0002
low_veg
0.0468
0.0119
0.7986
0.1425
0.0003
0.0000
tree
0.0037
0.0022
0.0319
0.9621
0.0001
0.0000
car
0.2840
0.0051
0.0021
0.0064
0.7011
0.0014
clutter
0.7508
0.0812
0.0591
0.0100
0.0989
0.0000
Precision/Correctness
0.909
0.977
0.931
0.764
0.897
0.000
Recall/Completeness
0.958
0.954
0.799
0.962
0.701
0.000
F1
0.933
0.965
0.860
0.851
0.787
-nan

Overall accuracy 0.918

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area29_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9383
0.0162
0.0268
0.0140
0.0046
0.0001
building
0.0158
0.9619
0.0144
0.0079
0.0000
0.0000
low_veg
0.0451
0.0245
0.6711
0.2592
0.0001
0.0000
tree
0.0040
0.0028
0.0201
0.9731
0.0000
0.0000
car
0.2817
0.0064
0.0043
0.0095
0.6746
0.0234
clutter
0.4667
0.3017
0.0189
0.0127
0.1080
0.0920
Precision/Correctness
0.932
0.929
0.846
0.694
0.636
0.880
Recall/Completeness
0.938
0.962
0.671
0.973
0.675
0.092
F1
0.935
0.945
0.749
0.810
0.655
0.167

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_area29_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9623
0.0091
0.0196
0.0065
0.0024
0.0001
building
0.0118
0.9730
0.0101
0.0051
0.0000
0.0000
low_veg
0.0267
0.0090
0.7212
0.2431
0.0000
0.0000
tree
0.0012
0.0008
0.0149
0.9831
0.0000
0.0000
car
0.2058
0.0024
0.0043
0.0064
0.7526
0.0286
clutter
0.4385
0.3182
0.0122
0.0059
0.1169
0.1083
Precision/Correctness
0.952
0.952
0.882
0.735
0.647
0.902
Recall/Completeness
0.962
0.973
0.721
0.983
0.753
0.108
F1
0.957
0.962
0.793
0.841
0.696
0.193

Overall accuracy 0.909

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
0.9663
0.0078
0.0110
0.0054
0.0092
0.0003
building
0.0574
0.9268
0.0074
0.0033
0.0042
0.0009
low_veg
0.0320
0.0054
0.9405
0.0216
0.0005
0.0000
tree
0.0284
0.0040
0.0894
0.8777
0.0003
0.0001
car
0.2033
0.0277
0.0068
0.0050
0.7512
0.0061
clutter
0.4713
0.2689
0.0260
0.0192
0.1298
0.0847
Precision/Correctness
0.889
0.947
0.888
0.934
0.745
0.825
Recall/Completeness
0.966
0.927
0.940
0.878
0.751
0.085
F1
0.926
0.937
0.914
0.905
0.748
0.154

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_area31_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9818
0.0053
0.0079
0.0014
0.0034
0.0002
building
0.0469
0.9442
0.0028
0.0017
0.0035
0.0008
low_veg
0.0160
0.0032
0.9675
0.0133
0.0001
0.0000
tree
0.0094
0.0010
0.0745
0.9151
0.0000
0.0000
car
0.1315
0.0291
0.0032
0.0016
0.8287
0.0059
clutter
0.4167
0.3079
0.0211
0.0126
0.1411
0.1005
Precision/Correctness
0.920
0.955
0.919
0.967
0.782
0.859
Recall/Completeness
0.982
0.944
0.967
0.915
0.829
0.101
F1
0.950
0.950
0.943
0.940
0.805
0.180

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_area33_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9714
0.0099
0.0110
0.0044
0.0020
0.0013
building
0.0192
0.9700
0.0052
0.0028
0.0018
0.0010
low_veg
0.0481
0.0119
0.9117
0.0256
0.0006
0.0021
tree
0.0339
0.0079
0.1337
0.8245
0.0000
0.0000
car
0.3817
0.0143
0.0075
0.0026
0.5798
0.0141
clutter
0.3742
0.0730
0.0021
0.0098
0.1424
0.3985
Precision/Correctness
0.900
0.964
0.875
0.925
0.451
0.943
Recall/Completeness
0.971
0.970
0.912
0.825
0.580
0.399
F1
0.934
0.967
0.893
0.872
0.507
0.560

Overall accuracy 0.910

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
0.9858
0.0055
0.0058
0.0020
0.0006
0.0004
building
0.0140
0.9797
0.0026
0.0012
0.0015
0.0009
low_veg
0.0235
0.0043
0.9485
0.0211
0.0005
0.0021
tree
0.0128
0.0015
0.1252
0.8604
0.0000
0.0000
car
0.2801
0.0172
0.0041
0.0021
0.6824
0.0142
clutter
0.3174
0.0681
0.0015
0.0091
0.1546
0.4493
Precision/Correctness
0.932
0.978
0.900
0.948
0.445
0.962
Recall/Completeness
0.986
0.980
0.948
0.860
0.682
0.449
F1
0.958
0.979
0.924
0.902
0.539
0.613

Overall accuracy 0.936

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
0.8772
0.0330
0.0656
0.0224
0.0017
0.0001
building
0.0217
0.9571
0.0169
0.0041
0.0002
0.0000
low_veg
0.0299
0.0171
0.7728
0.1800
0.0002
0.0000
tree
0.0208
0.0064
0.1219
0.8508
0.0001
0.0000
car
0.4361
0.0071
0.0121
0.0125
0.5220
0.0103
clutter
--
--
--
--
--
--
Precision/Correctness
0.912
0.948
0.795
0.795
0.877
--
Recall/Completeness
0.877
0.957
0.773
0.851
0.522
--
F1
0.894
0.952
0.784
0.822
0.655
--

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_area35_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9264
0.0240
0.0420
0.0070
0.0005
0.0000
building
0.0134
0.9779
0.0071
0.0014
0.0002
0.0000
low_veg
0.0184
0.0070
0.8034
0.1710
0.0002
0.0000
tree
0.0058
0.0015
0.0946
0.8982
0.0000
0.0000
car
0.3523
0.0063
0.0087
0.0074
0.6108
0.0145
clutter
--
--
--
--
--
--
Precision/Correctness
0.951
0.972
0.853
0.823
0.939
--
Recall/Completeness
0.926
0.978
0.803
0.898
0.611
--
F1
0.939
0.975
0.827
0.859
0.740
--

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_area38_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9035
0.0324
0.0459
0.0145
0.0035
0.0001
building
0.0138
0.9628
0.0186
0.0038
0.0009
0.0001
low_veg
0.0310
0.0173
0.8912
0.0605
0.0001
0.0000
tree
0.0138
0.0070
0.1283
0.8509
0.0000
0.0000
car
0.3559
0.0423
0.0395
0.0077
0.5526
0.0021
clutter
--
--
--
--
--
--
Precision/Correctness
0.930
0.941
0.855
0.884
0.818
--
Recall/Completeness
0.904
0.963
0.891
0.851
0.553
--
F1
0.916
0.952
0.873
0.867
0.660
--

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_area38_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9352
0.0287
0.0295
0.0045
0.0019
0.0001
building
0.0082
0.9823
0.0071
0.0015
0.0008
0.0001
low_veg
0.0184
0.0094
0.9276
0.0445
0.0000
0.0000
tree
0.0039
0.0026
0.1036
0.8899
0.0000
0.0000
car
0.2716
0.0468
0.0292
0.0029
0.6473
0.0022
clutter
--
--
--
--
--
--
Precision/Correctness
0.962
0.959
0.896
0.924
0.866
--
Recall/Completeness
0.935
0.982
0.928
0.890
0.647
--
F1
0.948
0.970
0.912
0.906
0.741
--

Overall accuracy 0.935

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image