Detailled semantic labeling (2D) result


Name K. Takahashi
Affiliation Waseda University, Japan
Abbreviation WAS4
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
0.896
0.036
0.039
0.018
0.010
0.001
building
0.041
0.927
0.024
0.007
0.001
0.000
low_veg
0.055
0.033
0.764
0.148
0.000
0.000
tree
0.024
0.006
0.094
0.875
0.000
0.000
car
0.280
0.043
0.011
0.005
0.661
0.000
clutter
0.309
0.304
0.014
0.009
0.065
0.300
Precision/Correctness
0.878
0.917
0.810
0.836
0.703
0.901
Recall/Completeness
0.896
0.927
0.764
0.875
0.661
0.300
F1
0.887
0.922
0.787
0.855
0.681
0.450

Overall accuracy 0.863

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
0.924
0.029
0.032
0.009
0.006
0.001
building
0.032
0.948
0.017
0.003
0.001
0.000
low_veg
0.042
0.025
0.800
0.133
0.000
0.000
tree
0.012
0.003
0.078
0.908
0.000
0.000
car
0.198
0.048
0.007
0.002
0.745
0.000
clutter
0.274
0.318
0.011
0.005
0.067
0.325
Precision/Correctness
0.913
0.937
0.846
0.866
0.754
0.931
Recall/Completeness
0.924
0.948
0.800
0.908
0.745
0.325
F1
0.919
0.942
0.822
0.886
0.749
0.482

Overall accuracy 0.894
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9389
0.0128
0.0227
0.0143
0.0113
0.0000
building
0.0449
0.9193
0.0268
0.0088
0.0002
0.0000
low_veg
0.0631
0.0146
0.7084
0.2139
0.0000
0.0000
tree
0.0304
0.0041
0.0839
0.8790
0.0004
0.0022
car
0.2962
0.0001
0.0012
0.0024
0.6997
0.0004
clutter
0.0000
0.0000
0.0000
0.0080
0.0000
0.9919
Precision/Correctness
0.861
0.964
0.842
0.789
0.785
0.971
Recall/Completeness
0.939
0.919
0.708
0.879
0.700
0.992
F1
0.898
0.941
0.769
0.831
0.740
0.981

Overall accuracy 0.861

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
0.9665
0.0085
0.0127
0.0053
0.0070
0.0000
building
0.0369
0.9439
0.0155
0.0035
0.0002
0.0000
low_veg
0.0445
0.0064
0.7411
0.2081
0.0000
0.0000
tree
0.0138
0.0014
0.0709
0.9125
0.0003
0.0013
car
0.1898
0.0000
0.0001
0.0004
0.8092
0.0004
clutter
0.0000
0.0000
0.0000
0.0011
0.0000
0.9989
Precision/Correctness
0.905
0.983
0.879
0.814
0.841
0.984
Recall/Completeness
0.967
0.944
0.741
0.912
0.809
0.999
F1
0.935
0.963
0.804
0.860
0.825
0.991

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_area4_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9241
0.0545
0.0092
0.0040
0.0082
0.0000
building
0.0667
0.9232
0.0081
0.0018
0.0001
0.0000
low_veg
0.1707
0.0647
0.4953
0.2647
0.0046
0.0000
tree
0.0586
0.0192
0.0685
0.8536
0.0002
0.0000
car
0.3580
0.0153
0.0025
0.0013
0.6228
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.836
0.963
0.676
0.745
0.773
--
Recall/Completeness
0.924
0.923
0.495
0.854
0.623
--
F1
0.878
0.943
0.572
0.796
0.690
--

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: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9517
0.0353
0.0071
0.0014
0.0044
0.0000
building
0.0508
0.9416
0.0067
0.0009
0.0000
0.0000
low_veg
0.1268
0.0398
0.5368
0.2931
0.0034
0.0000
tree
0.0246
0.0086
0.0625
0.9043
0.0000
0.0000
car
0.2764
0.0099
0.0018
0.0002
0.7118
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.874
0.979
0.706
0.770
0.846
--
Recall/Completeness
0.952
0.942
0.537
0.904
0.712
--
F1
0.911
0.960
0.610
0.832
0.773
--

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_area6_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8801
0.0585
0.0420
0.0090
0.0104
0.0000
building
0.0331
0.9537
0.0081
0.0049
0.0003
0.0000
low_veg
0.1216
0.0270
0.7065
0.1445
0.0004
0.0000
tree
0.0238
0.0044
0.0711
0.9004
0.0003
0.0000
car
0.2964
0.0296
0.0007
0.0022
0.6711
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.863
0.942
0.690
0.931
0.793
--
Recall/Completeness
0.880
0.954
0.706
0.900
0.671
--
F1
0.871
0.948
0.698
0.915
0.727
--

Overall accuracy 0.888

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
0.9167
0.0424
0.0336
0.0022
0.0051
0.0000
building
0.0225
0.9718
0.0037
0.0019
0.0001
0.0000
low_veg
0.1046
0.0132
0.7519
0.1300
0.0001
0.0000
tree
0.0117
0.0010
0.0576
0.9296
0.0001
0.0000
car
0.2019
0.0286
0.0001
0.0004
0.7690
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.906
0.964
0.732
0.952
0.876
--
Recall/Completeness
0.917
0.972
0.752
0.930
0.769
--
F1
0.911
0.968
0.742
0.941
0.819
--

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_area8_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8727
0.0334
0.0705
0.0107
0.0100
0.0027
building
0.0359
0.9382
0.0219
0.0035
0.0005
0.0000
low_veg
0.0469
0.0121
0.8608
0.0793
0.0009
0.0000
tree
0.0289
0.0069
0.0707
0.8927
0.0000
0.0009
car
0.2937
0.0132
0.0385
0.0028
0.6518
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.903
0.936
0.791
0.915
0.762
--
Recall/Completeness
0.873
0.938
0.861
0.893
0.652
--
F1
0.888
0.937
0.824
0.904
0.703
--

Overall accuracy 0.887

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
0.9013
0.0265
0.0603
0.0037
0.0055
0.0026
building
0.0251
0.9600
0.0136
0.0008
0.0005
0.0000
low_veg
0.0279
0.0047
0.8980
0.0690
0.0004
0.0000
tree
0.0122
0.0029
0.0513
0.9330
0.0000
0.0006
car
0.2221
0.0108
0.0262
0.0009
0.7400
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.943
0.958
0.834
0.938
0.830
--
Recall/Completeness
0.901
0.960
0.898
0.933
0.740
--
F1
0.921
0.959
0.865
0.936
0.782
--

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_area10_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8469
0.0830
0.0461
0.0194
0.0046
0.0000
building
0.0381
0.9313
0.0171
0.0115
0.0020
0.0000
low_veg
0.0783
0.0349
0.7407
0.1461
0.0000
0.0000
tree
0.0188
0.0081
0.0994
0.8737
0.0000
0.0000
car
0.2475
0.0766
0.0048
0.0024
0.6688
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.918
0.848
0.757
0.834
0.682
--
Recall/Completeness
0.847
0.931
0.741
0.874
0.669
--
F1
0.881
0.888
0.749
0.853
0.675
--

Overall accuracy 0.852

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
0.8761
0.0737
0.0384
0.0091
0.0027
0.0000
building
0.0291
0.9497
0.0113
0.0081
0.0017
0.0000
low_veg
0.0744
0.0220
0.7828
0.1207
0.0000
0.0000
tree
0.0077
0.0036
0.0769
0.9118
0.0000
0.0000
car
0.1611
0.0895
0.0021
0.0003
0.7469
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.939
0.873
0.801
0.876
0.732
--
Recall/Completeness
0.876
0.950
0.783
0.912
0.747
--
F1
0.906
0.910
0.792
0.893
0.740
--

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_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8677
0.0409
0.0549
0.0283
0.0081
0.0000
building
0.0397
0.9317
0.0225
0.0061
0.0000
0.0000
low_veg
0.0343
0.0236
0.7931
0.1481
0.0001
0.0009
tree
0.0139
0.0084
0.1192
0.8586
0.0000
0.0000
car
0.2301
0.0009
0.0070
0.0051
0.7515
0.0054
clutter
--
--
--
--
--
--
Precision/Correctness
0.838
0.919
0.804
0.868
0.760
--
Recall/Completeness
0.868
0.932
0.793
0.859
0.752
--
F1
0.853
0.925
0.798
0.863
0.756
--

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_area12_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8946
0.0382
0.0466
0.0158
0.0047
0.0000
building
0.0371
0.9485
0.0130
0.0014
0.0000
0.0000
low_veg
0.0302
0.0136
0.8285
0.1266
0.0001
0.0010
tree
0.0078
0.0032
0.1020
0.8870
0.0000
0.0000
car
0.1274
0.0001
0.0023
0.0002
0.8645
0.0055
clutter
--
--
--
--
--
--
Precision/Correctness
0.870
0.946
0.833
0.896
0.822
--
Recall/Completeness
0.895
0.948
0.829
0.887
0.864
--
F1
0.882
0.947
0.831
0.891
0.843
--

Overall accuracy 0.883

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
0.8435
0.0356
0.0795
0.0343
0.0069
0.0001
building
0.0133
0.9580
0.0206
0.0081
0.0000
0.0000
low_veg
0.0790
0.0565
0.6854
0.1788
0.0002
0.0000
tree
0.0294
0.0140
0.1098
0.8468
0.0000
0.0000
car
0.1680
0.0000
0.0000
0.0075
0.8245
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.855
0.861
0.748
0.838
0.570
--
Recall/Completeness
0.844
0.958
0.685
0.847
0.824
--
F1
0.849
0.907
0.715
0.842
0.674
--

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
0.8630
0.0307
0.0751
0.0249
0.0061
0.0001
building
0.0071
0.9781
0.0118
0.0030
0.0000
0.0000
low_veg
0.0732
0.0425
0.7147
0.1694
0.0002
0.0000
tree
0.0210
0.0075
0.0975
0.8740
0.0000
0.0000
car
0.0725
0.0000
0.0000
0.0036
0.9240
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.883
0.894
0.772
0.859
0.552
--
Recall/Completeness
0.863
0.978
0.715
0.874
0.924
--
F1
0.873
0.934
0.742
0.867
0.691
--

Overall accuracy 0.850

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
0.8296
0.0330
0.0832
0.0507
0.0033
0.0002
building
0.0215
0.9315
0.0328
0.0141
0.0000
0.0000
low_veg
0.0202
0.0149
0.8479
0.1169
0.0000
0.0000
tree
0.0233
0.0053
0.1232
0.8482
0.0000
0.0000
car
0.2853
0.0071
0.0456
0.0024
0.6548
0.0049
clutter
--
--
--
--
--
--
Precision/Correctness
0.871
0.935
0.797
0.874
0.741
--
Recall/Completeness
0.830
0.932
0.848
0.848
0.655
--
F1
0.850
0.933
0.822
0.861
0.695
--

Overall accuracy 0.860

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
0.8615
0.0280
0.0758
0.0325
0.0020
0.0001
building
0.0169
0.9572
0.0203
0.0056
0.0000
0.0000
low_veg
0.0162
0.0096
0.8716
0.1027
0.0000
0.0000
tree
0.0153
0.0021
0.1095
0.8730
0.0000
0.0000
car
0.1940
0.0037
0.0316
0.0000
0.7663
0.0044
clutter
--
--
--
--
--
--
Precision/Correctness
0.904
0.956
0.824
0.898
0.802
--
Recall/Completeness
0.861
0.957
0.872
0.873
0.766
--
F1
0.882
0.957
0.847
0.885
0.784
--

Overall accuracy 0.886

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area20_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8554
0.0524
0.0261
0.0595
0.0066
0.0000
building
0.0201
0.9485
0.0241
0.0074
0.0000
0.0000
low_veg
0.0418
0.0292
0.7623
0.1666
0.0001
0.0000
tree
0.0092
0.0024
0.0571
0.9314
0.0000
0.0000
car
0.1390
0.0130
0.0144
0.0157
0.8178
0.0000
clutter
0.0937
0.9060
0.0002
0.0002
0.0000
0.0000
Precision/Correctness
0.904
0.788
0.819
0.894
0.717
-nan
Recall/Completeness
0.855
0.948
0.762
0.931
0.818
0.000
F1
0.879
0.861
0.789
0.912
0.764
-nan

Overall accuracy 0.860

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
0.8889
0.0415
0.0224
0.0431
0.0041
0.0000
building
0.0176
0.9609
0.0196
0.0019
0.0000
0.0000
low_veg
0.0359
0.0168
0.8058
0.1414
0.0000
0.0000
tree
0.0038
0.0006
0.0442
0.9515
0.0000
0.0000
car
0.0629
0.0149
0.0064
0.0075
0.9083
0.0000
clutter
0.0959
0.9040
0.0000
0.0000
0.0000
0.0000
Precision/Correctness
0.927
0.811
0.850
0.919
0.766
-nan
Recall/Completeness
0.889
0.961
0.806
0.951
0.908
0.000
F1
0.908
0.880
0.827
0.935
0.831
-nan

Overall accuracy 0.887

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
0.8959
0.0283
0.0351
0.0305
0.0103
0.0000
building
0.0286
0.9428
0.0201
0.0068
0.0016
0.0000
low_veg
0.0857
0.0381
0.6952
0.1803
0.0007
0.0000
tree
0.0258
0.0042
0.0572
0.9124
0.0003
0.0000
car
0.2402
0.0121
0.0153
0.0061
0.7263
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.898
0.903
0.817
0.847
0.676
--
Recall/Completeness
0.896
0.943
0.695
0.912
0.726
--
F1
0.897
0.922
0.751
0.879
0.701
--

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_area22_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9265
0.0213
0.0292
0.0159
0.0070
0.0000
building
0.0200
0.9644
0.0115
0.0028
0.0013
0.0000
low_veg
0.0835
0.0251
0.7392
0.1519
0.0004
0.0000
tree
0.0112
0.0013
0.0417
0.9456
0.0002
0.0000
car
0.1488
0.0151
0.0102
0.0011
0.8249
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.925
0.934
0.859
0.885
0.717
--
Recall/Completeness
0.927
0.964
0.739
0.946
0.825
--
F1
0.926
0.949
0.795
0.914
0.767
--

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_area24_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.7981
0.0479
0.1044
0.0379
0.0117
0.0000
building
0.0558
0.8710
0.0603
0.0129
0.0000
0.0000
low_veg
0.0197
0.0133
0.8846
0.0824
0.0001
0.0000
tree
0.0183
0.0069
0.1512
0.8236
0.0000
0.0000
car
0.2224
0.0114
0.0220
0.0054
0.7388
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.828
0.920
0.848
0.833
0.619
--
Recall/Completeness
0.798
0.871
0.885
0.824
0.739
--
F1
0.813
0.895
0.866
0.828
0.674
--

Overall accuracy 0.853

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
0.8329
0.0371
0.0949
0.0270
0.0081
0.0000
building
0.0531
0.8843
0.0532
0.0095
0.0000
0.0000
low_veg
0.0166
0.0082
0.9040
0.0711
0.0000
0.0000
tree
0.0114
0.0035
0.1301
0.8550
0.0000
0.0000
car
0.1550
0.0116
0.0105
0.0017
0.8212
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.854
0.946
0.870
0.858
0.656
--
Recall/Completeness
0.833
0.884
0.904
0.855
0.821
--
F1
0.843
0.914
0.887
0.856
0.729
--

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
0.9083
0.0348
0.0266
0.0073
0.0231
0.0000
building
0.0669
0.9092
0.0193
0.0042
0.0003
0.0000
low_veg
0.0792
0.0264
0.6820
0.2116
0.0007
0.0000
tree
0.0145
0.0045
0.0624
0.9186
0.0000
0.0000
car
0.3200
0.0113
0.0030
0.0047
0.6609
0.0000
clutter
0.4482
0.4263
0.0201
0.0109
0.0945
0.0000
Precision/Correctness
0.848
0.946
0.860
0.670
0.733
-nan
Recall/Completeness
0.908
0.909
0.682
0.919
0.661
0.000
F1
0.877
0.927
0.761
0.775
0.695
-nan

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_area27_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9406
0.0237
0.0199
0.0030
0.0127
0.0000
building
0.0552
0.9302
0.0129
0.0014
0.0003
0.0000
low_veg
0.0584
0.0149
0.7246
0.2019
0.0002
0.0000
tree
0.0054
0.0015
0.0475
0.9456
0.0000
0.0000
car
0.2379
0.0101
0.0009
0.0029
0.7482
0.0000
clutter
0.4202
0.4539
0.0138
0.0053
0.1069
0.0000
Precision/Correctness
0.886
0.967
0.897
0.699
0.807
-nan
Recall/Completeness
0.941
0.930
0.725
0.946
0.748
0.000
F1
0.913
0.948
0.802
0.804
0.776
-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_area29_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9324
0.0216
0.0236
0.0134
0.0090
0.0000
building
0.0360
0.9448
0.0113
0.0078
0.0001
0.0000
low_veg
0.0648
0.0259
0.6217
0.2872
0.0004
0.0000
tree
0.0066
0.0022
0.0336
0.9577
0.0000
0.0000
car
0.2555
0.0230
0.0009
0.0102
0.7104
0.0000
clutter
0.3411
0.5300
0.0179
0.0139
0.0710
0.0261
Precision/Correctness
0.922
0.898
0.842
0.673
0.614
1.000
Recall/Completeness
0.932
0.945
0.622
0.958
0.710
0.026
F1
0.927
0.921
0.715
0.791
0.658
0.051

Overall accuracy 0.862

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
0.9560
0.0143
0.0173
0.0063
0.0061
0.0000
building
0.0293
0.9602
0.0066
0.0039
0.0000
0.0000
low_veg
0.0408
0.0119
0.6667
0.2804
0.0002
0.0000
tree
0.0019
0.0008
0.0245
0.9729
0.0000
0.0000
car
0.1705
0.0258
0.0001
0.0064
0.7973
0.0000
clutter
0.3090
0.5649
0.0102
0.0086
0.0759
0.0313
Precision/Correctness
0.945
0.920
0.882
0.709
0.632
1.000
Recall/Completeness
0.956
0.960
0.667
0.973
0.797
0.031
F1
0.950
0.940
0.759
0.820
0.705
0.061

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_area31_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9579
0.0168
0.0058
0.0046
0.0146
0.0003
building
0.0346
0.9479
0.0120
0.0039
0.0015
0.0000
low_veg
0.0514
0.0047
0.9013
0.0415
0.0010
0.0002
tree
0.0484
0.0045
0.1023
0.8440
0.0008
0.0000
car
0.2518
0.1739
0.0084
0.0053
0.5602
0.0004
clutter
0.5007
0.2038
0.0452
0.0206
0.0830
0.1466
Precision/Correctness
0.884
0.926
0.876
0.906
0.689
0.971
Recall/Completeness
0.958
0.948
0.901
0.844
0.560
0.147
F1
0.920
0.937
0.888
0.874
0.618
0.255

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_area31_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9774
0.0100
0.0032
0.0015
0.0078
0.0001
building
0.0246
0.9661
0.0071
0.0010
0.0012
0.0000
low_veg
0.0303
0.0017
0.9325
0.0352
0.0002
0.0000
tree
0.0183
0.0011
0.0871
0.8933
0.0001
0.0000
car
0.1942
0.1903
0.0044
0.0012
0.6096
0.0004
clutter
0.4581
0.2242
0.0429
0.0156
0.0881
0.1711
Precision/Correctness
0.920
0.944
0.907
0.936
0.742
0.987
Recall/Completeness
0.977
0.966
0.933
0.893
0.610
0.171
F1
0.948
0.955
0.920
0.914
0.669
0.292

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
0.9650
0.0066
0.0095
0.0035
0.0064
0.0090
building
0.0460
0.8807
0.0616
0.0064
0.0051
0.0000
low_veg
0.0730
0.2541
0.6149
0.0559
0.0022
0.0000
tree
0.0557
0.0035
0.1156
0.8252
0.0001
0.0000
car
0.3003
0.0351
0.0037
0.0063
0.6546
0.0000
clutter
0.4199
0.0727
0.0007
0.0009
0.1157
0.3900
Precision/Correctness
0.867
0.846
0.737
0.879
0.443
0.859
Recall/Completeness
0.965
0.881
0.615
0.825
0.655
0.390
F1
0.913
0.863
0.671
0.851
0.529
0.536

Overall accuracy 0.837

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
0.9816
0.0030
0.0051
0.0012
0.0035
0.0056
building
0.0369
0.8981
0.0569
0.0036
0.0045
0.0000
low_veg
0.0411
0.2755
0.6299
0.0514
0.0021
0.0000
tree
0.0258
0.0005
0.1079
0.8657
0.0000
0.0000
car
0.2052
0.0429
0.0011
0.0040
0.7469
0.0000
clutter
0.3882
0.0697
0.0001
0.0004
0.1249
0.4168
Precision/Correctness
0.901
0.852
0.760
0.904
0.445
0.906
Recall/Completeness
0.982
0.898
0.630
0.866
0.747
0.417
F1
0.940
0.875
0.689
0.885
0.557
0.571

Overall accuracy 0.861

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
0.8190
0.0586
0.0927
0.0251
0.0046
0.0000
building
0.0280
0.9291
0.0314
0.0108
0.0005
0.0000
low_veg
0.0409
0.0107
0.7017
0.2467
0.0000
0.0000
tree
0.0367
0.0054
0.1033
0.8542
0.0001
0.0002
car
0.2696
0.0145
0.0012
0.0093
0.7054
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.879
0.930
0.757
0.740
0.800
--
Recall/Completeness
0.819
0.929
0.702
0.854
0.705
--
F1
0.848
0.929
0.728
0.793
0.750
--

Overall accuracy 0.827

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
0.8651
0.0546
0.0703
0.0082
0.0018
0.0000
building
0.0190
0.9606
0.0166
0.0032
0.0005
0.0000
low_veg
0.0276
0.0041
0.7312
0.2371
0.0000
0.0000
tree
0.0138
0.0014
0.0792
0.9053
0.0000
0.0002
car
0.1708
0.0125
0.0001
0.0018
0.8146
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.929
0.948
0.817
0.772
0.889
--
Recall/Completeness
0.865
0.961
0.731
0.905
0.815
--
F1
0.896
0.954
0.772
0.834
0.850
--

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_area38_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9078
0.0321
0.0373
0.0160
0.0069
0.0000
building
0.0317
0.9227
0.0383
0.0061
0.0012
0.0000
low_veg
0.0480
0.0376
0.8213
0.0925
0.0006
0.0000
tree
0.0262
0.0059
0.1088
0.8588
0.0001
0.0001
car
0.2555
0.0352
0.0449
0.0077
0.6567
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.894
0.919
0.848
0.840
0.729
--
Recall/Completeness
0.908
0.923
0.821
0.859
0.657
--
F1
0.901
0.921
0.834
0.850
0.691
--

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_area38_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9359
0.0294
0.0254
0.0055
0.0038
0.0000
building
0.0223
0.9501
0.0242
0.0023
0.0010
0.0000
low_veg
0.0309
0.0343
0.8586
0.0758
0.0003
0.0000
tree
0.0098
0.0029
0.0864
0.9007
0.0001
0.0001
car
0.1748
0.0393
0.0376
0.0037
0.7445
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.935
0.932
0.888
0.881
0.794
--
Recall/Completeness
0.936
0.950
0.859
0.901
0.744
--
F1
0.935
0.941
0.873
0.891
0.768
--

Overall accuracy 0.910

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image