Detailled semantic labeling (2D) result


Name B. Yu et al.
Affiliation Chinese Academy of Sciences, China
Abbreviation CAS_Y2
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
0.889
0.048
0.043
0.015
0.004
0.000
building
0.052
0.914
0.029
0.004
0.001
0.000
low_veg
0.050
0.027
0.784
0.138
0.000
0.000
tree
0.021
0.006
0.111
0.861
0.000
0.000
car
0.378
0.030
0.014
0.005
0.572
0.000
clutter
0.436
0.320
0.014
0.006
0.054
0.170
Precision/Correctness
0.867
0.909
0.790
0.847
0.794
0.974
Recall/Completeness
0.889
0.914
0.784
0.861
0.572
0.170
F1
0.878
0.912
0.787
0.854
0.665
0.290

Overall accuracy 0.856

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
0.916
0.040
0.034
0.007
0.003
0.000
building
0.045
0.931
0.022
0.002
0.001
0.000
low_veg
0.038
0.017
0.820
0.125
0.000
0.000
tree
0.010
0.002
0.093
0.895
0.000
0.000
car
0.277
0.032
0.010
0.002
0.678
0.000
clutter
0.403
0.338
0.010
0.002
0.058
0.190
Precision/Correctness
0.899
0.931
0.827
0.875
0.827
0.983
Recall/Completeness
0.916
0.931
0.820
0.895
0.678
0.190
F1
0.908
0.931
0.823
0.885
0.745
0.318

Overall accuracy 0.886
=============================================================

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
0.0258
0.0246
0.0106
0.0048
0.0000
building
0.0436
0.9304
0.0232
0.0026
0.0002
0.0000
low_veg
0.0680
0.0261
0.7346
0.1712
0.0000
0.0000
tree
0.0328
0.0045
0.1010
0.8601
0.0001
0.0015
car
0.3988
0.0013
0.0008
0.0025
0.5966
0.0000
clutter
0.1061
0.0000
0.0000
0.0133
0.0000
0.8806
Precision/Correctness
0.845
0.939
0.831
0.824
0.879
0.978
Recall/Completeness
0.934
0.930
0.735
0.860
0.597
0.881
F1
0.887
0.934
0.780
0.842
0.711
0.927

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_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9588
0.0206
0.0147
0.0031
0.0028
0.0000
building
0.0372
0.9488
0.0133
0.0004
0.0002
0.0000
low_veg
0.0510
0.0146
0.7685
0.1660
0.0000
0.0000
tree
0.0163
0.0016
0.0873
0.8939
0.0000
0.0007
car
0.2795
0.0000
0.0001
0.0015
0.7188
0.0000
clutter
0.1059
0.0000
0.0000
0.0026
0.0000
0.8915
Precision/Correctness
0.886
0.962
0.866
0.846
0.919
0.989
Recall/Completeness
0.959
0.949
0.769
0.894
0.719
0.891
F1
0.921
0.955
0.814
0.869
0.807
0.938

Overall accuracy 0.891

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
0.9188
0.0629
0.0111
0.0037
0.0034
0.0000
building
0.0579
0.9343
0.0064
0.0012
0.0002
0.0000
low_veg
0.1419
0.0649
0.5664
0.2267
0.0001
0.0000
tree
0.0504
0.0167
0.1082
0.8245
0.0001
0.0000
car
0.5221
0.0427
0.0002
0.0021
0.4329
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.846
0.959
0.677
0.769
0.847
--
Recall/Completeness
0.919
0.934
0.566
0.825
0.433
--
F1
0.881
0.946
0.617
0.796
0.573
--

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_area4_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9498
0.0388
0.0079
0.0013
0.0022
0.0000
building
0.0468
0.9473
0.0053
0.0004
0.0002
0.0000
low_veg
0.1031
0.0273
0.6192
0.2503
0.0001
0.0000
tree
0.0215
0.0055
0.1029
0.8701
0.0000
0.0000
car
0.4387
0.0355
0.0000
0.0005
0.5254
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.878
0.978
0.709
0.794
0.882
--
Recall/Completeness
0.950
0.947
0.619
0.870
0.525
--
F1
0.913
0.962
0.661
0.830
0.658
--

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_area6_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9020
0.0505
0.0309
0.0094
0.0072
0.0000
building
0.0480
0.9369
0.0124
0.0026
0.0002
0.0000
low_veg
0.0775
0.0395
0.7328
0.1501
0.0003
0.0000
tree
0.0135
0.0037
0.0740
0.9087
0.0001
0.0000
car
0.4864
0.0382
0.0035
0.0031
0.4687
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.865
0.943
0.701
0.931
0.798
--
Recall/Completeness
0.902
0.937
0.733
0.909
0.469
--
F1
0.883
0.940
0.716
0.920
0.591
--

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_area6_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9366
0.0334
0.0212
0.0028
0.0059
0.0000
building
0.0391
0.9533
0.0067
0.0008
0.0001
0.0000
low_veg
0.0603
0.0241
0.7830
0.1326
0.0000
0.0000
tree
0.0036
0.0007
0.0600
0.9357
0.0000
0.0000
car
0.3977
0.0291
0.0031
0.0004
0.5698
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.902
0.967
0.749
0.952
0.824
--
Recall/Completeness
0.937
0.953
0.783
0.936
0.570
--
F1
0.919
0.960
0.766
0.944
0.674
--

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_area8_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8846
0.0343
0.0694
0.0083
0.0034
0.0000
building
0.0479
0.9290
0.0203
0.0027
0.0001
0.0000
low_veg
0.0505
0.0163
0.8584
0.0740
0.0008
0.0000
tree
0.0257
0.0081
0.1130
0.8532
0.0001
0.0000
car
0.4043
0.0140
0.0151
0.0033
0.5632
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.891
0.930
0.759
0.920
0.884
--
Recall/Completeness
0.885
0.929
0.858
0.853
0.563
--
F1
0.888
0.929
0.805
0.885
0.688
--

Overall accuracy 0.877

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
0.9118
0.0271
0.0565
0.0027
0.0019
0.0000
building
0.0387
0.9495
0.0109
0.0007
0.0001
0.0000
low_veg
0.0339
0.0079
0.8945
0.0636
0.0001
0.0000
tree
0.0107
0.0039
0.0910
0.8944
0.0000
0.0000
car
0.2992
0.0117
0.0088
0.0022
0.6780
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.928
0.953
0.804
0.941
0.931
--
Recall/Completeness
0.912
0.949
0.894
0.894
0.678
--
F1
0.920
0.951
0.847
0.917
0.785
--

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_area10_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.7839
0.1462
0.0514
0.0158
0.0028
0.0000
building
0.0421
0.9248
0.0208
0.0106
0.0016
0.0000
low_veg
0.0720
0.0389
0.7548
0.1340
0.0004
0.0000
tree
0.0156
0.0085
0.1117
0.8641
0.0001
0.0000
car
0.3403
0.0318
0.0123
0.0007
0.6149
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.912
0.774
0.738
0.847
0.743
--
Recall/Completeness
0.784
0.925
0.755
0.864
0.615
--
F1
0.843
0.843
0.746
0.856
0.673
--

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_area10_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8134
0.1376
0.0410
0.0064
0.0017
0.0000
building
0.0368
0.9389
0.0150
0.0078
0.0015
0.0000
low_veg
0.0697
0.0239
0.7945
0.1115
0.0004
0.0000
tree
0.0063
0.0041
0.0858
0.9038
0.0000
0.0000
car
0.2506
0.0351
0.0045
0.0000
0.7098
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.931
0.796
0.786
0.886
0.779
--
Recall/Completeness
0.813
0.939
0.794
0.904
0.710
--
F1
0.868
0.862
0.790
0.895
0.743
--

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_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8641
0.0392
0.0670
0.0283
0.0013
0.0000
building
0.1220
0.8557
0.0179
0.0044
0.0001
0.0000
low_veg
0.0321
0.0268
0.7701
0.1710
0.0000
0.0000
tree
0.0112
0.0079
0.1277
0.8532
0.0000
0.0000
car
0.3307
0.0018
0.0220
0.0065
0.6391
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.762
0.909
0.787
0.853
0.939
--
Recall/Completeness
0.864
0.856
0.770
0.853
0.639
--
F1
0.810
0.882
0.779
0.853
0.761
--

Overall accuracy 0.830

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
0.8906
0.0356
0.0593
0.0143
0.0002
0.0000
building
0.1273
0.8620
0.0094
0.0013
0.0001
0.0000
low_veg
0.0286
0.0140
0.8065
0.1508
0.0000
0.0000
tree
0.0058
0.0028
0.1097
0.8817
0.0000
0.0000
car
0.1847
0.0008
0.0184
0.0011
0.7950
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.781
0.943
0.817
0.879
0.983
--
Recall/Completeness
0.891
0.862
0.807
0.882
0.795
--
F1
0.832
0.901
0.812
0.880
0.879
--

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_area14_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8210
0.0683
0.0771
0.0300
0.0037
0.0000
building
0.0122
0.9590
0.0243
0.0044
0.0001
0.0000
low_veg
0.0670
0.0494
0.7539
0.1294
0.0004
0.0000
tree
0.0242
0.0116
0.1555
0.8087
0.0001
0.0000
car
0.2146
0.0000
0.0004
0.0030
0.7820
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.871
0.840
0.721
0.870
0.682
--
Recall/Completeness
0.821
0.959
0.754
0.809
0.782
--
F1
0.845
0.896
0.737
0.838
0.729
--

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
0.8415
0.0647
0.0711
0.0199
0.0029
0.0000
building
0.0086
0.9775
0.0125
0.0014
0.0001
0.0000
low_veg
0.0618
0.0333
0.7852
0.1194
0.0004
0.0000
tree
0.0167
0.0054
0.1408
0.8371
0.0000
0.0000
car
0.0960
0.0000
0.0000
0.0000
0.9040
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.896
0.871
0.746
0.891
0.690
--
Recall/Completeness
0.841
0.977
0.785
0.837
0.904
--
F1
0.868
0.921
0.765
0.863
0.782
--

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
0.8154
0.0349
0.0991
0.0485
0.0021
0.0000
building
0.0259
0.9175
0.0484
0.0081
0.0001
0.0000
low_veg
0.0158
0.0160
0.8413
0.1263
0.0000
0.0006
tree
0.0228
0.0054
0.1154
0.8565
0.0000
0.0000
car
0.2375
0.0005
0.0299
0.0156
0.7166
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.874
0.931
0.790
0.871
0.828
--
Recall/Completeness
0.815
0.918
0.841
0.856
0.717
--
F1
0.844
0.924
0.815
0.864
0.768
--

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_area16_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8495
0.0306
0.0895
0.0295
0.0009
0.0000
building
0.0217
0.9400
0.0353
0.0030
0.0001
0.0000
low_veg
0.0120
0.0099
0.8651
0.1124
0.0000
0.0006
tree
0.0152
0.0016
0.0996
0.8836
0.0000
0.0000
car
0.1649
0.0000
0.0259
0.0091
0.8001
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.906
0.954
0.820
0.894
0.899
--
Recall/Completeness
0.849
0.940
0.865
0.884
0.800
--
F1
0.877
0.947
0.842
0.889
0.847
--

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_area20_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8525
0.0556
0.0489
0.0384
0.0047
0.0000
building
0.0148
0.9519
0.0281
0.0047
0.0005
0.0000
low_veg
0.0443
0.0396
0.7425
0.1733
0.0003
0.0000
tree
0.0084
0.0032
0.0593
0.9291
0.0000
0.0000
car
0.1961
0.0025
0.0684
0.0061
0.7253
0.0016
clutter
0.0042
0.9956
0.0001
0.0000
0.0000
0.0000
Precision/Correctness
0.918
0.768
0.786
0.901
0.734
0.000
Recall/Completeness
0.852
0.952
0.742
0.929
0.725
0.000
F1
0.884
0.850
0.764
0.915
0.730
-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_area20_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8862
0.0438
0.0454
0.0214
0.0031
0.0000
building
0.0127
0.9609
0.0243
0.0015
0.0005
0.0000
low_veg
0.0392
0.0250
0.7885
0.1469
0.0004
0.0000
tree
0.0038
0.0006
0.0464
0.9492
0.0000
0.0000
car
0.1188
0.0000
0.0494
0.0026
0.8267
0.0025
clutter
0.0017
0.9983
0.0000
0.0000
0.0000
0.0000
Precision/Correctness
0.940
0.793
0.817
0.926
0.760
0.000
Recall/Completeness
0.886
0.961
0.789
0.949
0.827
0.000
F1
0.912
0.869
0.802
0.937
0.792
-nan

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_area22_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8998
0.0278
0.0377
0.0300
0.0046
0.0000
building
0.0554
0.9230
0.0153
0.0059
0.0004
0.0000
low_veg
0.0786
0.0519
0.7461
0.1233
0.0001
0.0000
tree
0.0219
0.0043
0.0857
0.8879
0.0002
0.0000
car
0.4128
0.0006
0.0061
0.0149
0.5655
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.887
0.889
0.792
0.878
0.793
--
Recall/Completeness
0.900
0.923
0.746
0.888
0.565
--
F1
0.893
0.905
0.768
0.883
0.660
--

Overall accuracy 0.866

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
0.9310
0.0197
0.0314
0.0148
0.0032
0.0000
building
0.0487
0.9410
0.0071
0.0028
0.0003
0.0000
low_veg
0.0742
0.0370
0.7896
0.0991
0.0001
0.0000
tree
0.0092
0.0014
0.0661
0.9233
0.0001
0.0000
car
0.3115
0.0000
0.0047
0.0051
0.6787
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.914
0.924
0.835
0.915
0.828
--
Recall/Completeness
0.931
0.941
0.790
0.923
0.679
--
F1
0.922
0.933
0.812
0.919
0.746
--

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
0.8003
0.0397
0.1216
0.0343
0.0041
0.0000
building
0.0553
0.8785
0.0572
0.0091
0.0000
0.0000
low_veg
0.0248
0.0212
0.8792
0.0748
0.0001
0.0000
tree
0.0146
0.0077
0.1593
0.8183
0.0000
0.0000
car
0.2810
0.0003
0.0040
0.0023
0.7123
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.821
0.910
0.840
0.847
0.811
--
Recall/Completeness
0.800
0.879
0.879
0.818
0.712
--
F1
0.811
0.894
0.859
0.833
0.759
--

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_area24_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8351
0.0274
0.1116
0.0238
0.0020
0.0000
building
0.0542
0.8907
0.0487
0.0063
0.0000
0.0000
low_veg
0.0224
0.0158
0.8979
0.0638
0.0001
0.0000
tree
0.0084
0.0038
0.1373
0.8506
0.0000
0.0000
car
0.1843
0.0003
0.0007
0.0000
0.8147
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.843
0.937
0.863
0.872
0.873
--
Recall/Completeness
0.835
0.891
0.898
0.851
0.815
--
F1
0.839
0.913
0.880
0.861
0.843
--

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_area27_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9250
0.0393
0.0226
0.0056
0.0075
0.0000
building
0.0643
0.9060
0.0268
0.0025
0.0003
0.0000
low_veg
0.0688
0.0300
0.7188
0.1816
0.0008
0.0000
tree
0.0164
0.0040
0.0773
0.9024
0.0000
0.0000
car
0.4224
0.0121
0.0088
0.0055
0.5512
0.0000
clutter
0.3606
0.4224
0.1456
0.0061
0.0653
0.0000
Precision/Correctness
0.850
0.940
0.849
0.702
0.864
0.000
Recall/Completeness
0.925
0.906
0.719
0.902
0.551
0.000
F1
0.886
0.923
0.779
0.790
0.673
-nan

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_area27_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9514
0.0284
0.0148
0.0022
0.0031
0.0000
building
0.0529
0.9248
0.0212
0.0008
0.0002
0.0000
low_veg
0.0503
0.0158
0.7601
0.1732
0.0006
0.0000
tree
0.0075
0.0009
0.0569
0.9347
0.0000
0.0000
car
0.3215
0.0112
0.0066
0.0045
0.6561
0.0000
clutter
0.3372
0.4574
0.1164
0.0029
0.0861
0.0000
Precision/Correctness
0.888
0.962
0.887
0.729
0.922
0.000
Recall/Completeness
0.951
0.925
0.760
0.935
0.656
0.000
F1
0.919
0.943
0.819
0.819
0.767
-nan

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_area29_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9229
0.0343
0.0285
0.0101
0.0043
0.0000
building
0.0308
0.9522
0.0122
0.0046
0.0001
0.0000
low_veg
0.0604
0.0210
0.6734
0.2448
0.0004
0.0000
tree
0.0064
0.0029
0.0606
0.9302
0.0000
0.0000
car
0.3679
0.0147
0.0072
0.0069
0.6034
0.0000
clutter
0.4463
0.4379
0.0373
0.0049
0.0579
0.0156
Precision/Correctness
0.915
0.893
0.811
0.708
0.691
1.000
Recall/Completeness
0.923
0.952
0.673
0.930
0.603
0.016
F1
0.919
0.921
0.736
0.804
0.644
0.031

Overall accuracy 0.863

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
0.9455
0.0263
0.0210
0.0044
0.0028
0.0000
building
0.0252
0.9657
0.0067
0.0023
0.0001
0.0000
low_veg
0.0357
0.0082
0.7192
0.2367
0.0002
0.0000
tree
0.0019
0.0007
0.0488
0.9486
0.0000
0.0000
car
0.2802
0.0117
0.0059
0.0046
0.6976
0.0000
clutter
0.4292
0.4604
0.0276
0.0014
0.0628
0.0187
Precision/Correctness
0.939
0.915
0.853
0.742
0.708
1.000
Recall/Completeness
0.946
0.966
0.719
0.949
0.698
0.019
F1
0.942
0.940
0.780
0.833
0.703
0.037

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_area31_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9581
0.0209
0.0092
0.0039
0.0079
0.0000
building
0.0708
0.9135
0.0105
0.0017
0.0034
0.0000
low_veg
0.0394
0.0049
0.9089
0.0466
0.0002
0.0000
tree
0.0403
0.0041
0.0835
0.8716
0.0005
0.0000
car
0.2386
0.0878
0.0163
0.0054
0.6520
0.0000
clutter
0.6010
0.2875
0.0174
0.0079
0.0832
0.0031
Precision/Correctness
0.864
0.920
0.888
0.913
0.773
1.000
Recall/Completeness
0.958
0.914
0.909
0.872
0.652
0.003
F1
0.908
0.917
0.898
0.892
0.707
0.006

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
0.9708
0.0181
0.0064
0.0007
0.0040
0.0000
building
0.0609
0.9298
0.0063
0.0002
0.0028
0.0000
low_veg
0.0206
0.0026
0.9364
0.0404
0.0000
0.0000
tree
0.0153
0.0010
0.0634
0.9202
0.0001
0.0000
car
0.1447
0.1047
0.0085
0.0014
0.7407
0.0000
clutter
0.5585
0.3273
0.0139
0.0023
0.0943
0.0038
Precision/Correctness
0.897
0.930
0.922
0.939
0.804
1.000
Recall/Completeness
0.971
0.930
0.936
0.920
0.741
0.004
F1
0.932
0.930
0.929
0.930
0.771
0.008

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_area33_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9568
0.0236
0.0157
0.0025
0.0013
0.0001
building
0.0830
0.8080
0.1056
0.0026
0.0008
0.0000
low_veg
0.0585
0.0176
0.7916
0.1314
0.0010
0.0000
tree
0.0444
0.0042
0.1745
0.7768
0.0000
0.0000
car
0.4347
0.0865
0.0035
0.0028
0.4724
0.0000
clutter
0.7255
0.0779
0.0017
0.0032
0.0888
0.1029
Precision/Correctness
0.817
0.930
0.689
0.786
0.515
0.991
Recall/Completeness
0.957
0.808
0.792
0.777
0.472
0.103
F1
0.881
0.865
0.737
0.781
0.493
0.186

Overall accuracy 0.817

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
0.9715
0.0178
0.0093
0.0006
0.0007
0.0000
building
0.0767
0.8177
0.1043
0.0007
0.0006
0.0000
low_veg
0.0315
0.0101
0.8203
0.1373
0.0008
0.0000
tree
0.0179
0.0010
0.1616
0.8195
0.0000
0.0000
car
0.3338
0.0828
0.0009
0.0007
0.5817
0.0000
clutter
0.7049
0.0768
0.0010
0.0014
0.0999
0.1161
Precision/Correctness
0.846
0.949
0.706
0.797
0.508
0.997
Recall/Completeness
0.971
0.818
0.820
0.819
0.582
0.116
F1
0.904
0.879
0.759
0.808
0.543
0.208

Overall accuracy 0.840

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
0.8077
0.0996
0.0748
0.0166
0.0013
0.0000
building
0.0383
0.9384
0.0177
0.0055
0.0001
0.0000
low_veg
0.0531
0.0207
0.6845
0.2417
0.0000
0.0000
tree
0.0352
0.0082
0.1106
0.8458
0.0002
0.0000
car
0.3997
0.0422
0.0023
0.0078
0.5480
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.854
0.885
0.775
0.751
0.912
--
Recall/Completeness
0.808
0.938
0.684
0.846
0.548
--
F1
0.830
0.911
0.727
0.796
0.685
--

Overall accuracy 0.819

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
0.8477
0.0949
0.0524
0.0043
0.0007
0.0000
building
0.0312
0.9589
0.0086
0.0012
0.0001
0.0000
low_veg
0.0391
0.0094
0.7168
0.2348
0.0000
0.0000
tree
0.0128
0.0030
0.0874
0.8968
0.0000
0.0000
car
0.2893
0.0421
0.0009
0.0021
0.6656
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.901
0.910
0.833
0.777
0.950
--
Recall/Completeness
0.848
0.959
0.717
0.897
0.666
--
F1
0.874
0.934
0.770
0.832
0.783
--

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_area38_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8975
0.0301
0.0555
0.0128
0.0041
0.0000
building
0.0459
0.8859
0.0623
0.0046
0.0014
0.0000
low_veg
0.0365
0.0230
0.8441
0.0961
0.0002
0.0000
tree
0.0232
0.0037
0.1443
0.8287
0.0001
0.0000
car
0.3642
0.0086
0.0681
0.0085
0.5506
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.890
0.936
0.799
0.837
0.776
--
Recall/Completeness
0.897
0.886
0.844
0.829
0.551
--
F1
0.894
0.910
0.821
0.833
0.644
--

Overall accuracy 0.863

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
0.9259
0.0278
0.0393
0.0045
0.0026
0.0000
building
0.0383
0.9128
0.0459
0.0017
0.0013
0.0000
low_veg
0.0212
0.0185
0.8768
0.0833
0.0001
0.0000
tree
0.0082
0.0009
0.1192
0.8716
0.0001
0.0000
car
0.2693
0.0083
0.0604
0.0030
0.6590
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.927
0.950
0.841
0.870
0.818
--
Recall/Completeness
0.926
0.913
0.877
0.872
0.659
--
F1
0.927
0.931
0.859
0.871
0.730
--

Overall accuracy 0.897

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image