Detailled semantic labeling (2D) result


Name Yansong Liu et al.
Affiliation Rochester Institute of Technology
Abbreviation RIT_L7
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
0.879
0.042
0.062
0.014
0.003
0.000
building
0.054
0.910
0.031
0.005
0.001
0.000
low_veg
0.047
0.028
0.822
0.102
0.000
0.000
tree
0.017
0.010
0.162
0.811
0.000
0.000
car
0.405
0.048
0.025
0.007
0.515
0.000
clutter
0.658
0.274
0.038
0.007
0.023
0.000
Precision/Correctness
0.862
0.912
0.739
0.871
0.822
-nan
Recall/Completeness
0.879
0.910
0.822
0.811
0.515
0.000
F1
0.870
0.911
0.778
0.840
0.634
-nan

Overall accuracy 0.847

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
0.912
0.031
0.048
0.006
0.002
0.000
building
0.047
0.927
0.023
0.002
0.001
0.000
low_veg
0.038
0.018
0.852
0.091
0.000
0.000
tree
0.008
0.006
0.139
0.846
0.000
0.000
car
0.317
0.044
0.017
0.003
0.618
0.000
clutter
0.646
0.292
0.034
0.002
0.025
0.000
Precision/Correctness
0.890
0.937
0.778
0.898
0.862
-nan
Recall/Completeness
0.912
0.927
0.852
0.846
0.618
0.000
F1
0.901
0.932
0.814
0.872
0.720
-nan

Overall accuracy 0.878
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9239
0.0141
0.0485
0.0104
0.0031
0.0000
building
0.0507
0.9176
0.0282
0.0034
0.0001
0.0000
low_veg
0.0664
0.0248
0.8238
0.0848
0.0002
0.0000
tree
0.0298
0.0186
0.1521
0.7994
0.0000
0.0000
car
0.4006
0.0126
0.0154
0.0031
0.5683
0.0000
clutter
0.9627
0.0234
0.0001
0.0136
0.0001
0.0000
Precision/Correctness
0.796
0.934
0.781
0.890
0.910
-nan
Recall/Completeness
0.924
0.918
0.824
0.799
0.568
0.000
F1
0.855
0.926
0.802
0.842
0.700
-nan

Overall accuracy 0.845

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
0.9567
0.0089
0.0298
0.0031
0.0014
0.0000
building
0.0434
0.9359
0.0190
0.0016
0.0001
0.0000
low_veg
0.0524
0.0154
0.8521
0.0798
0.0002
0.0000
tree
0.0170
0.0147
0.1340
0.8344
0.0000
0.0000
car
0.2825
0.0091
0.0096
0.0007
0.6980
0.0000
clutter
0.9763
0.0206
0.0001
0.0030
0.0001
0.0000
Precision/Correctness
0.826
0.956
0.818
0.911
0.951
-nan
Recall/Completeness
0.957
0.936
0.852
0.834
0.698
0.000
F1
0.887
0.946
0.835
0.871
0.805
-nan

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_area4_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8519
0.1234
0.0187
0.0027
0.0033
0.0000
building
0.0523
0.9353
0.0100
0.0016
0.0008
0.0000
low_veg
0.2282
0.1045
0.4673
0.1990
0.0010
0.0000
tree
0.0494
0.0286
0.1815
0.7398
0.0008
0.0000
car
0.4796
0.0365
0.0056
0.0015
0.4767
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.836
0.925
0.512
0.771
0.819
--
Recall/Completeness
0.852
0.935
0.467
0.740
0.477
--
F1
0.844
0.930
0.489
0.755
0.603
--

Overall accuracy 0.872

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
0.8890
0.0932
0.0153
0.0007
0.0018
0.0000
building
0.0434
0.9464
0.0087
0.0006
0.0009
0.0000
low_veg
0.2081
0.0730
0.4980
0.2201
0.0008
0.0000
tree
0.0230
0.0156
0.1805
0.7807
0.0002
0.0000
car
0.4044
0.0214
0.0022
0.0008
0.5712
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.865
0.948
0.526
0.796
0.858
--
Recall/Completeness
0.889
0.946
0.498
0.781
0.571
--
F1
0.877
0.947
0.512
0.788
0.686
--

Overall accuracy 0.899

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
0.8548
0.0826
0.0490
0.0106
0.0031
0.0000
building
0.0572
0.9144
0.0252
0.0029
0.0002
0.0000
low_veg
0.0446
0.0355
0.7877
0.1319
0.0004
0.0000
tree
0.0091
0.0064
0.0831
0.9013
0.0001
0.0000
car
0.4265
0.0346
0.0193
0.0041
0.5154
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.867
0.917
0.651
0.936
0.904
--
Recall/Completeness
0.855
0.914
0.788
0.901
0.515
--
F1
0.861
0.916
0.713
0.918
0.656
--

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_area6_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9013
0.0605
0.0334
0.0037
0.0011
0.0000
building
0.0507
0.9299
0.0186
0.0008
0.0001
0.0000
low_veg
0.0379
0.0194
0.8290
0.1134
0.0003
0.0000
tree
0.0030
0.0026
0.0655
0.9289
0.0000
0.0000
car
0.3381
0.0208
0.0109
0.0015
0.6287
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.896
0.947
0.702
0.958
0.959
--
Recall/Completeness
0.901
0.930
0.829
0.929
0.629
--
F1
0.899
0.938
0.760
0.943
0.760
--

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_area8_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8575
0.0503
0.0801
0.0093
0.0028
0.0000
building
0.0374
0.9406
0.0189
0.0025
0.0006
0.0000
low_veg
0.0514
0.0183
0.8944
0.0355
0.0004
0.0000
tree
0.0194
0.0155
0.1466
0.8185
0.0000
0.0000
car
0.4377
0.0305
0.0341
0.0048
0.4928
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.897
0.902
0.730
0.949
0.884
--
Recall/Completeness
0.857
0.941
0.894
0.819
0.493
--
F1
0.877
0.921
0.804
0.879
0.633
--

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_area8_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8919
0.0407
0.0626
0.0033
0.0015
0.0000
building
0.0288
0.9584
0.0114
0.0008
0.0005
0.0000
low_veg
0.0404
0.0089
0.9224
0.0281
0.0002
0.0000
tree
0.0090
0.0092
0.1212
0.8605
0.0000
0.0000
car
0.3463
0.0253
0.0219
0.0036
0.6030
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.929
0.931
0.776
0.968
0.924
--
Recall/Completeness
0.892
0.958
0.922
0.861
0.603
--
F1
0.910
0.945
0.843
0.911
0.730
--

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_area10_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8189
0.0907
0.0742
0.0141
0.0021
0.0000
building
0.0336
0.9306
0.0255
0.0103
0.0000
0.0000
low_veg
0.0584
0.0518
0.7559
0.1332
0.0007
0.0000
tree
0.0113
0.0123
0.1572
0.8191
0.0000
0.0000
car
0.3784
0.0791
0.0454
0.0019
0.4952
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.930
0.826
0.667
0.844
0.795
--
Recall/Completeness
0.819
0.931
0.756
0.819
0.495
--
F1
0.871
0.875
0.708
0.831
0.610
--

Overall accuracy 0.832

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
0.8586
0.0747
0.0597
0.0056
0.0014
0.0000
building
0.0295
0.9440
0.0193
0.0073
0.0000
0.0000
low_veg
0.0577
0.0380
0.7907
0.1128
0.0008
0.0000
tree
0.0053
0.0074
0.1265
0.8608
0.0000
0.0000
car
0.3071
0.0630
0.0320
0.0001
0.5978
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.944
0.860
0.716
0.882
0.822
--
Recall/Completeness
0.859
0.944
0.791
0.861
0.598
--
F1
0.899
0.900
0.751
0.871
0.692
--

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_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8465
0.0386
0.0827
0.0297
0.0025
0.0000
building
0.1197
0.8560
0.0178
0.0061
0.0004
0.0000
low_veg
0.0344
0.0401
0.7827
0.1417
0.0011
0.0000
tree
0.0065
0.0088
0.1607
0.8238
0.0001
0.0000
car
0.3022
0.1006
0.0151
0.0053
0.5768
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.766
0.887
0.752
0.868
0.785
--
Recall/Completeness
0.847
0.856
0.783
0.824
0.577
--
F1
0.804
0.871
0.767
0.845
0.665
--

Overall accuracy 0.820

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
0.8816
0.0333
0.0687
0.0155
0.0009
0.0000
building
0.1248
0.8628
0.0100
0.0021
0.0003
0.0000
low_veg
0.0327
0.0273
0.8176
0.1213
0.0010
0.0000
tree
0.0029
0.0042
0.1408
0.8520
0.0002
0.0000
car
0.1854
0.1195
0.0083
0.0018
0.6850
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.781
0.920
0.783
0.895
0.825
--
Recall/Completeness
0.882
0.863
0.818
0.852
0.685
--
F1
0.828
0.891
0.800
0.873
0.748
--

Overall accuracy 0.848

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area14_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8401
0.0266
0.1023
0.0273
0.0037
0.0000
building
0.0348
0.9241
0.0356
0.0051
0.0004
0.0000
low_veg
0.0724
0.0446
0.7771
0.1051
0.0009
0.0000
tree
0.0240
0.0122
0.1912
0.7726
0.0001
0.0000
car
0.3234
0.0008
0.0277
0.0111
0.6370
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.852
0.883
0.678
0.884
0.591
--
Recall/Completeness
0.840
0.924
0.777
0.773
0.637
--
F1
0.846
0.903
0.724
0.825
0.613
--

Overall accuracy 0.816

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
0.8625
0.0215
0.0945
0.0180
0.0035
0.0000
building
0.0294
0.9456
0.0229
0.0017
0.0004
0.0000
low_veg
0.0679
0.0304
0.8074
0.0934
0.0009
0.0000
tree
0.0166
0.0062
0.1777
0.7995
0.0000
0.0000
car
0.1961
0.0000
0.0171
0.0075
0.7793
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.878
0.918
0.700
0.907
0.578
--
Recall/Completeness
0.862
0.946
0.807
0.800
0.779
--
F1
0.870
0.932
0.750
0.850
0.664
--

Overall accuracy 0.842

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
0.7909
0.0434
0.1145
0.0490
0.0022
0.0000
building
0.0406
0.9094
0.0390
0.0108
0.0002
0.0000
low_veg
0.0181
0.0201
0.8432
0.1181
0.0005
0.0000
tree
0.0186
0.0079
0.1388
0.8346
0.0000
0.0000
car
0.2434
0.0322
0.0284
0.0070
0.6890
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.860
0.912
0.768
0.873
0.734
--
Recall/Completeness
0.791
0.909
0.843
0.835
0.689
--
F1
0.824
0.911
0.804
0.853
0.711
--

Overall accuracy 0.843

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
0.8302
0.0372
0.1015
0.0299
0.0012
0.0000
building
0.0387
0.9294
0.0275
0.0042
0.0002
0.0000
low_veg
0.0153
0.0127
0.8671
0.1044
0.0005
0.0000
tree
0.0125
0.0036
0.1234
0.8604
0.0000
0.0000
car
0.1221
0.0192
0.0103
0.0008
0.8476
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.885
0.939
0.797
0.897
0.773
--
Recall/Completeness
0.830
0.929
0.867
0.860
0.848
--
F1
0.857
0.934
0.830
0.878
0.808
--

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_area20_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.7908
0.0750
0.0928
0.0385
0.0029
0.0000
building
0.0153
0.9306
0.0460
0.0078
0.0003
0.0000
low_veg
0.0314
0.0353
0.7717
0.1611
0.0004
0.0000
tree
0.0050
0.0060
0.0769
0.9121
0.0000
0.0000
car
0.2504
0.0884
0.0277
0.0230
0.6104
0.0000
clutter
0.0320
0.8604
0.1065
0.0012
0.0000
0.0000
Precision/Correctness
0.927
0.760
0.711
0.903
0.774
-nan
Recall/Completeness
0.791
0.931
0.772
0.912
0.610
0.000
F1
0.854
0.837
0.740
0.907
0.683
-nan

Overall accuracy 0.838

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area20_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8268
0.0649
0.0854
0.0212
0.0016
0.0000
building
0.0133
0.9426
0.0409
0.0029
0.0003
0.0000
low_veg
0.0263
0.0231
0.8135
0.1366
0.0005
0.0000
tree
0.0017
0.0038
0.0616
0.9329
0.0000
0.0000
car
0.1857
0.0809
0.0130
0.0124
0.7081
0.0000
clutter
0.0204
0.8799
0.0995
0.0002
0.0000
0.0000
Precision/Correctness
0.949
0.781
0.741
0.928
0.817
-nan
Recall/Completeness
0.827
0.943
0.813
0.933
0.708
0.000
F1
0.884
0.854
0.775
0.931
0.759
-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_area22_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8641
0.0293
0.0738
0.0279
0.0049
0.0000
building
0.0556
0.9121
0.0259
0.0059
0.0004
0.0000
low_veg
0.0674
0.0452
0.7832
0.1036
0.0007
0.0000
tree
0.0174
0.0046
0.1387
0.8393
0.0000
0.0000
car
0.4331
0.0131
0.0479
0.0212
0.4847
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.892
0.891
0.697
0.886
0.749
--
Recall/Completeness
0.864
0.912
0.783
0.839
0.485
--
F1
0.878
0.901
0.738
0.862
0.588
--

Overall accuracy 0.845

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
0.9021
0.0206
0.0602
0.0138
0.0034
0.0000
building
0.0514
0.9298
0.0156
0.0029
0.0004
0.0000
low_veg
0.0665
0.0316
0.8192
0.0822
0.0006
0.0000
tree
0.0077
0.0017
0.1128
0.8777
0.0000
0.0000
car
0.3568
0.0112
0.0358
0.0117
0.5845
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.914
0.926
0.744
0.923
0.785
--
Recall/Completeness
0.902
0.930
0.819
0.878
0.584
--
F1
0.908
0.928
0.780
0.900
0.670
--

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_area24_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.7764
0.0523
0.1421
0.0236
0.0056
0.0000
building
0.0719
0.8697
0.0450
0.0132
0.0003
0.0000
low_veg
0.0212
0.0246
0.9081
0.0459
0.0002
0.0000
tree
0.0134
0.0130
0.2585
0.7150
0.0001
0.0000
car
0.3620
0.0216
0.0159
0.0073
0.5932
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.807
0.886
0.797
0.880
0.702
--
Recall/Completeness
0.776
0.870
0.908
0.715
0.593
--
F1
0.791
0.878
0.849
0.789
0.643
--

Overall accuracy 0.832

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
0.8128
0.0400
0.1290
0.0144
0.0039
0.0000
building
0.0702
0.8839
0.0353
0.0104
0.0003
0.0000
low_veg
0.0186
0.0198
0.9233
0.0380
0.0002
0.0000
tree
0.0083
0.0098
0.2330
0.7488
0.0001
0.0000
car
0.2865
0.0139
0.0041
0.0026
0.6930
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.829
0.911
0.822
0.904
0.731
--
Recall/Completeness
0.813
0.884
0.923
0.749
0.693
--
F1
0.821
0.897
0.870
0.819
0.711
--

Overall accuracy 0.856

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
0.9141
0.0381
0.0356
0.0044
0.0078
0.0000
building
0.0757
0.8991
0.0219
0.0029
0.0004
0.0000
low_veg
0.0635
0.0323
0.7994
0.1045
0.0003
0.0000
tree
0.0106
0.0196
0.1484
0.8213
0.0001
0.0000
car
0.4342
0.0190
0.0204
0.0048
0.5216
0.0000
clutter
0.5155
0.2940
0.1892
0.0008
0.0005
0.0000
Precision/Correctness
0.841
0.935
0.817
0.781
0.862
-nan
Recall/Completeness
0.914
0.899
0.799
0.821
0.522
0.000
F1
0.876
0.917
0.808
0.801
0.650
-nan

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_area27_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9466
0.0250
0.0238
0.0016
0.0030
0.0000
building
0.0665
0.9176
0.0144
0.0011
0.0004
0.0000
low_veg
0.0499
0.0195
0.8363
0.0943
0.0001
0.0000
tree
0.0043
0.0140
0.1225
0.8592
0.0000
0.0000
car
0.3464
0.0120
0.0155
0.0036
0.6225
0.0000
clutter
0.5230
0.3073
0.1691
0.0000
0.0007
0.0000
Precision/Correctness
0.873
0.960
0.861
0.817
0.933
-nan
Recall/Completeness
0.947
0.918
0.836
0.859
0.623
0.000
F1
0.909
0.938
0.849
0.837
0.747
-nan

Overall accuracy 0.897

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area29_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9221
0.0262
0.0362
0.0123
0.0032
0.0000
building
0.0168
0.9674
0.0101
0.0054
0.0003
0.0000
low_veg
0.0529
0.0272
0.7092
0.2104
0.0003
0.0000
tree
0.0051
0.0108
0.0562
0.9279
0.0000
0.0000
car
0.3801
0.0389
0.0185
0.0150
0.5474
0.0000
clutter
0.6892
0.2437
0.0422
0.0072
0.0176
0.0000
Precision/Correctness
0.910
0.916
0.803
0.727
0.786
-nan
Recall/Completeness
0.922
0.967
0.709
0.928
0.547
0.000
F1
0.916
0.941
0.753
0.815
0.645
-nan

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_area29_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9483
0.0180
0.0258
0.0058
0.0021
0.0000
building
0.0117
0.9805
0.0051
0.0025
0.0003
0.0000
low_veg
0.0383
0.0126
0.7530
0.1958
0.0003
0.0000
tree
0.0021
0.0082
0.0433
0.9464
0.0000
0.0000
car
0.2928
0.0292
0.0124
0.0123
0.6533
0.0000
clutter
0.6869
0.2587
0.0320
0.0028
0.0197
0.0000
Precision/Correctness
0.931
0.940
0.850
0.769
0.811
-nan
Recall/Completeness
0.948
0.980
0.753
0.946
0.653
0.000
F1
0.940
0.960
0.799
0.849
0.724
-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_area31_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9545
0.0193
0.0184
0.0036
0.0041
0.0000
building
0.0390
0.9477
0.0082
0.0032
0.0020
0.0000
low_veg
0.0571
0.0059
0.9112
0.0255
0.0004
0.0000
tree
0.0279
0.0074
0.1121
0.8524
0.0002
0.0000
car
0.3432
0.1520
0.0162
0.0074
0.4812
0.0000
clutter
0.6183
0.2863
0.0394
0.0144
0.0416
0.0000
Precision/Correctness
0.870
0.915
0.850
0.934
0.826
-nan
Recall/Completeness
0.955
0.948
0.911
0.852
0.481
0.000
F1
0.910
0.931
0.879
0.892
0.608
-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_area31_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9721
0.0133
0.0125
0.0006
0.0015
0.0000
building
0.0291
0.9645
0.0040
0.0006
0.0018
0.0000
low_veg
0.0377
0.0031
0.9394
0.0197
0.0001
0.0000
tree
0.0091
0.0028
0.0885
0.8996
0.0000
0.0000
car
0.2754
0.1583
0.0078
0.0021
0.5565
0.0000
clutter
0.5906
0.3160
0.0405
0.0060
0.0468
0.0000
Precision/Correctness
0.903
0.933
0.891
0.965
0.863
-nan
Recall/Completeness
0.972
0.964
0.939
0.900
0.557
0.000
F1
0.936
0.949
0.915
0.931
0.677
-nan

Overall accuracy 0.916

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
0.9702
0.0109
0.0159
0.0021
0.0009
0.0000
building
0.0330
0.8828
0.0782
0.0032
0.0027
0.0000
low_veg
0.0832
0.0191
0.6624
0.2344
0.0008
0.0000
tree
0.0368
0.0093
0.2259
0.7279
0.0000
0.0000
car
0.4892
0.0122
0.0091
0.0028
0.4866
0.0000
clutter
0.8409
0.1121
0.0081
0.0000
0.0389
0.0000
Precision/Correctness
0.827
0.947
0.658
0.668
0.649
-nan
Recall/Completeness
0.970
0.883
0.662
0.728
0.487
0.000
F1
0.893
0.914
0.660
0.697
0.556
-nan

Overall accuracy 0.814

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
0.9842
0.0063
0.0088
0.0004
0.0003
0.0000
building
0.0235
0.8967
0.0759
0.0013
0.0025
0.0000
low_veg
0.0558
0.0134
0.6753
0.2546
0.0008
0.0000
tree
0.0157
0.0049
0.2064
0.7730
0.0000
0.0000
car
0.3855
0.0059
0.0066
0.0008
0.6012
0.0000
clutter
0.8344
0.1159
0.0058
0.0000
0.0440
0.0000
Precision/Correctness
0.858
0.962
0.682
0.669
0.652
-nan
Recall/Completeness
0.984
0.897
0.675
0.773
0.601
0.000
F1
0.917
0.928
0.678
0.717
0.626
-nan

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: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8447
0.0161
0.1271
0.0106
0.0014
0.0000
building
0.1250
0.8295
0.0415
0.0035
0.0005
0.0000
low_veg
0.0297
0.0114
0.8404
0.1184
0.0001
0.0000
tree
0.0244
0.0056
0.2719
0.6979
0.0001
0.0000
car
0.4795
0.0205
0.0084
0.0078
0.4839
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.809
0.964
0.662
0.832
0.870
--
Recall/Completeness
0.845
0.829
0.840
0.698
0.484
--
F1
0.827
0.892
0.740
0.759
0.622
--

Overall accuracy 0.803

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
0.9000
0.0106
0.0862
0.0027
0.0006
0.0000
building
0.1140
0.8603
0.0245
0.0006
0.0005
0.0000
low_veg
0.0205
0.0056
0.8585
0.1152
0.0001
0.0000
tree
0.0093
0.0033
0.2283
0.7592
0.0000
0.0000
car
0.3752
0.0208
0.0040
0.0017
0.5982
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.842
0.980
0.724
0.856
0.916
--
Recall/Completeness
0.900
0.860
0.859
0.759
0.598
--
F1
0.870
0.916
0.785
0.805
0.724
--

Overall accuracy 0.845

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
0.8919
0.0168
0.0781
0.0107
0.0025
0.0000
building
0.0417
0.8869
0.0665
0.0040
0.0010
0.0000
low_veg
0.0326
0.0157
0.8933
0.0581
0.0003
0.0000
tree
0.0164
0.0059
0.2390
0.7385
0.0001
0.0000
car
0.3856
0.0276
0.0759
0.0079
0.5030
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.900
0.956
0.746
0.877
0.828
--
Recall/Completeness
0.892
0.887
0.893
0.739
0.503
--
F1
0.896
0.920
0.813
0.802
0.626
--

Overall accuracy 0.858

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
0.9303
0.0111
0.0539
0.0034
0.0012
0.0000
building
0.0339
0.9115
0.0522
0.0014
0.0010
0.0000
low_veg
0.0209
0.0087
0.9231
0.0470
0.0003
0.0000
tree
0.0061
0.0031
0.2056
0.7852
0.0000
0.0000
car
0.3068
0.0164
0.0616
0.0024
0.6127
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.932
0.975
0.790
0.912
0.869
--
Recall/Completeness
0.930
0.911
0.923
0.785
0.613
--
F1
0.931
0.942
0.852
0.844
0.719
--

Overall accuracy 0.894

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image