Detailled semantic labeling (2D) result


Name N. Audebert et al.
Affiliation Onera and IRISA, France
Abbreviation ONE_6
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
0.910
0.025
0.045
0.016
0.004
0.000
building
0.059
0.912
0.024
0.005
0.000
0.000
low_veg
0.056
0.021
0.786
0.137
0.000
0.000
tree
0.022
0.005
0.095
0.877
0.000
0.000
car
0.224
0.036
0.005
0.005
0.731
0.000
clutter
0.423
0.277
0.254
0.010
0.036
0.000
Precision/Correctness
0.866
0.938
0.800
0.849
0.854
-nan
Recall/Completeness
0.910
0.912
0.786
0.877
0.731
0.000
F1
0.888
0.925
0.793
0.863
0.788
-nan

Overall accuracy 0.866

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
0.018
0.037
0.007
0.002
0.000
building
0.052
0.929
0.017
0.002
0.000
0.000
low_veg
0.044
0.012
0.821
0.123
0.000
0.000
tree
0.011
0.002
0.078
0.909
0.000
0.000
car
0.124
0.041
0.002
0.002
0.830
0.000
clutter
0.382
0.298
0.279
0.004
0.037
0.000
Precision/Correctness
0.896
0.958
0.833
0.877
0.887
-nan
Recall/Completeness
0.935
0.929
0.821
0.909
0.830
0.000
F1
0.915
0.943
0.827
0.893
0.857
-nan

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
0.9530
0.0074
0.0223
0.0124
0.0049
0.0000
building
0.0472
0.9293
0.0203
0.0032
0.0000
0.0000
low_veg
0.0726
0.0189
0.7355
0.1727
0.0002
0.0000
tree
0.0275
0.0042
0.0950
0.8728
0.0004
0.0000
car
0.2628
0.0004
0.0003
0.0018
0.7347
0.0000
clutter
0.0499
0.0000
0.9164
0.0264
0.0073
0.0000
Precision/Correctness
0.855
0.966
0.780
0.822
0.882
-nan
Recall/Completeness
0.953
0.929
0.736
0.873
0.735
0.000
F1
0.901
0.947
0.757
0.847
0.802
-nan

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_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9750
0.0040
0.0136
0.0038
0.0037
0.0000
building
0.0391
0.9493
0.0111
0.0006
0.0000
0.0000
low_veg
0.0545
0.0111
0.7674
0.1668
0.0002
0.0000
tree
0.0122
0.0012
0.0810
0.9053
0.0002
0.0000
car
0.1343
0.0001
0.0000
0.0008
0.8648
0.0000
clutter
0.0498
0.0000
0.9379
0.0070
0.0053
0.0000
Precision/Correctness
0.896
0.983
0.805
0.846
0.902
-nan
Recall/Completeness
0.975
0.949
0.767
0.905
0.865
0.000
F1
0.934
0.966
0.786
0.875
0.883
-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_area4_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9375
0.0413
0.0133
0.0042
0.0037
0.0000
building
0.0819
0.9058
0.0100
0.0013
0.0011
0.0000
low_veg
0.1552
0.0371
0.5359
0.2713
0.0005
0.0000
tree
0.0616
0.0155
0.0937
0.8290
0.0001
0.0000
car
0.2930
0.0059
0.0011
0.0013
0.6986
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.820
0.972
0.630
0.738
0.856
--
Recall/Completeness
0.937
0.906
0.536
0.829
0.699
--
F1
0.875
0.938
0.579
0.781
0.769
--

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: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9641
0.0219
0.0102
0.0017
0.0020
0.0000
building
0.0697
0.9201
0.0085
0.0006
0.0011
0.0000
low_veg
0.1130
0.0107
0.5753
0.3009
0.0000
0.0000
tree
0.0285
0.0072
0.0892
0.8752
0.0000
0.0000
car
0.1834
0.0017
0.0000
0.0002
0.8148
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.849
0.987
0.655
0.761
0.882
--
Recall/Completeness
0.964
0.920
0.575
0.875
0.815
--
F1
0.903
0.952
0.613
0.814
0.847
--

Overall accuracy 0.915

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
0.9108
0.0417
0.0356
0.0086
0.0032
0.0000
building
0.0675
0.9154
0.0144
0.0024
0.0003
0.0000
low_veg
0.0938
0.0268
0.7507
0.1282
0.0004
0.0000
tree
0.0205
0.0041
0.0622
0.9127
0.0004
0.0000
car
0.2518
0.0114
0.0003
0.0006
0.7360
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.846
0.953
0.716
0.940
0.918
--
Recall/Completeness
0.911
0.915
0.751
0.913
0.736
--
F1
0.877
0.934
0.733
0.926
0.817
--

Overall accuracy 0.893

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area6_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9449
0.0263
0.0260
0.0024
0.0005
0.0000
building
0.0587
0.9308
0.0097
0.0005
0.0002
0.0000
low_veg
0.0766
0.0115
0.8000
0.1118
0.0001
0.0000
tree
0.0098
0.0011
0.0486
0.9404
0.0002
0.0000
car
0.1537
0.0063
0.0000
0.0000
0.8400
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.879
0.975
0.762
0.960
0.975
--
Recall/Completeness
0.945
0.931
0.800
0.940
0.840
--
F1
0.911
0.953
0.781
0.950
0.902
--

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
0.8913
0.0177
0.0785
0.0091
0.0033
0.0000
building
0.0417
0.9381
0.0164
0.0039
0.0000
0.0000
low_veg
0.0499
0.0133
0.8839
0.0525
0.0004
0.0000
tree
0.0244
0.0051
0.0978
0.8726
0.0001
0.0000
car
0.2616
0.0069
0.0096
0.0039
0.7180
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.904
0.958
0.770
0.936
0.915
--
Recall/Completeness
0.891
0.938
0.884
0.873
0.718
--
F1
0.898
0.948
0.823
0.903
0.804
--

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_area8_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9181
0.0105
0.0679
0.0021
0.0015
0.0000
building
0.0324
0.9571
0.0089
0.0016
0.0000
0.0000
low_veg
0.0334
0.0055
0.9187
0.0424
0.0000
0.0000
tree
0.0092
0.0020
0.0765
0.9123
0.0000
0.0000
car
0.1614
0.0071
0.0034
0.0020
0.8260
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.939
0.979
0.810
0.959
0.958
--
Recall/Completeness
0.918
0.957
0.919
0.912
0.826
--
F1
0.929
0.968
0.861
0.935
0.887
--

Overall accuracy 0.925

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
0.8383
0.0611
0.0787
0.0192
0.0027
0.0000
building
0.0368
0.9309
0.0210
0.0113
0.0000
0.0000
low_veg
0.0730
0.0278
0.7662
0.1329
0.0000
0.0000
tree
0.0154
0.0076
0.0733
0.9038
0.0000
0.0000
car
0.2064
0.0266
0.0012
0.0043
0.7615
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.923
0.881
0.731
0.848
0.842
--
Recall/Completeness
0.838
0.931
0.766
0.904
0.762
--
F1
0.879
0.906
0.748
0.875
0.800
--

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_area10_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8694
0.0482
0.0729
0.0082
0.0013
0.0000
building
0.0323
0.9431
0.0159
0.0086
0.0000
0.0000
low_veg
0.0707
0.0150
0.8102
0.1040
0.0000
0.0000
tree
0.0063
0.0033
0.0538
0.9366
0.0000
0.0000
car
0.1149
0.0333
0.0005
0.0004
0.8509
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.939
0.912
0.763
0.891
0.897
--
Recall/Completeness
0.869
0.943
0.810
0.937
0.851
--
F1
0.903
0.927
0.786
0.913
0.873
--

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_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8936
0.0254
0.0502
0.0282
0.0026
0.0000
building
0.0927
0.8904
0.0121
0.0048
0.0000
0.0000
low_veg
0.0510
0.0222
0.7665
0.1601
0.0002
0.0000
tree
0.0114
0.0069
0.1086
0.8730
0.0000
0.0000
car
0.1493
0.0000
0.0000
0.0037
0.8470
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.772
0.931
0.817
0.863
0.909
--
Recall/Completeness
0.894
0.890
0.767
0.873
0.847
--
F1
0.828
0.910
0.791
0.868
0.877
--

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_area12_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9216
0.0219
0.0422
0.0141
0.0003
0.0000
building
0.0962
0.8963
0.0059
0.0015
0.0000
0.0000
low_veg
0.0488
0.0121
0.8007
0.1382
0.0001
0.0000
tree
0.0062
0.0026
0.0912
0.9001
0.0000
0.0000
car
0.0550
0.0000
0.0000
0.0000
0.9450
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.790
0.959
0.847
0.890
0.981
--
Recall/Completeness
0.922
0.896
0.801
0.900
0.945
--
F1
0.851
0.926
0.823
0.895
0.963
--

Overall accuracy 0.874

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
0.8164
0.0307
0.1141
0.0325
0.0062
0.0000
building
0.0155
0.9649
0.0139
0.0057
0.0000
0.0000
low_veg
0.0836
0.0461
0.7237
0.1461
0.0004
0.0000
tree
0.0287
0.0113
0.1224
0.8376
0.0001
0.0000
car
0.1343
0.0000
0.0000
0.0059
0.8598
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.847
0.883
0.725
0.860
0.597
--
Recall/Completeness
0.816
0.965
0.724
0.838
0.860
--
F1
0.831
0.922
0.725
0.849
0.704
--

Overall accuracy 0.826

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
0.8345
0.0259
0.1117
0.0225
0.0054
0.0000
building
0.0105
0.9820
0.0052
0.0023
0.0000
0.0000
low_veg
0.0785
0.0305
0.7559
0.1346
0.0004
0.0000
tree
0.0203
0.0049
0.1100
0.8648
0.0000
0.0000
car
0.0414
0.0000
0.0000
0.0021
0.9565
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.873
0.918
0.746
0.882
0.576
--
Recall/Completeness
0.835
0.982
0.756
0.865
0.957
--
F1
0.853
0.949
0.751
0.873
0.719
--

Overall accuracy 0.851

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
0.8313
0.0360
0.0801
0.0491
0.0035
0.0000
building
0.0430
0.9252
0.0227
0.0089
0.0002
0.0000
low_veg
0.0207
0.0186
0.8413
0.1192
0.0001
0.0000
tree
0.0247
0.0046
0.1149
0.8558
0.0000
0.0000
car
0.1459
0.0017
0.0039
0.0093
0.8391
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.847
0.928
0.810
0.876
0.753
--
Recall/Completeness
0.831
0.925
0.841
0.856
0.839
--
F1
0.839
0.926
0.825
0.866
0.794
--

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
0.8657
0.0316
0.0709
0.0301
0.0018
0.0000
building
0.0401
0.9454
0.0111
0.0033
0.0001
0.0000
low_veg
0.0164
0.0121
0.8655
0.1058
0.0001
0.0000
tree
0.0171
0.0012
0.0999
0.8818
0.0000
0.0000
car
0.0890
0.0000
0.0006
0.0022
0.9082
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.876
0.951
0.839
0.899
0.819
--
Recall/Completeness
0.866
0.945
0.866
0.882
0.908
--
F1
0.871
0.948
0.852
0.890
0.861
--

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
0.8650
0.0364
0.0533
0.0399
0.0054
0.0000
building
0.0153
0.9652
0.0141
0.0055
0.0000
0.0000
low_veg
0.0621
0.0299
0.7562
0.1516
0.0002
0.0000
tree
0.0080
0.0020
0.0516
0.9384
0.0000
0.0000
car
0.1093
0.0045
0.0113
0.0136
0.8614
0.0000
clutter
0.0492
0.9494
0.0011
0.0003
0.0000
0.0000
Precision/Correctness
0.899
0.799
0.810
0.910
0.760
-nan
Recall/Completeness
0.865
0.965
0.756
0.938
0.861
0.000
F1
0.882
0.874
0.782
0.924
0.807
-nan

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_area20_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8977
0.0277
0.0492
0.0218
0.0036
0.0000
building
0.0131
0.9752
0.0101
0.0017
0.0000
0.0000
low_veg
0.0573
0.0179
0.8008
0.1239
0.0001
0.0000
tree
0.0035
0.0003
0.0386
0.9575
0.0000
0.0000
car
0.0470
0.0010
0.0013
0.0052
0.9456
0.0000
clutter
0.0408
0.9591
0.0001
0.0000
0.0000
0.0000
Precision/Correctness
0.921
0.818
0.842
0.936
0.792
-nan
Recall/Completeness
0.898
0.975
0.801
0.958
0.946
0.000
F1
0.909
0.890
0.821
0.946
0.862
-nan

Overall accuracy 0.892

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area22_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9017
0.0197
0.0410
0.0321
0.0055
0.0000
building
0.0350
0.9471
0.0122
0.0056
0.0001
0.0000
low_veg
0.0976
0.0406
0.7280
0.1327
0.0010
0.0000
tree
0.0214
0.0035
0.0677
0.9072
0.0001
0.0000
car
0.2189
0.0108
0.0086
0.0123
0.7495
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.893
0.915
0.808
0.873
0.803
--
Recall/Completeness
0.902
0.947
0.728
0.907
0.749
--
F1
0.897
0.931
0.766
0.890
0.776
--

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_area22_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9337
0.0122
0.0343
0.0162
0.0036
0.0000
building
0.0292
0.9630
0.0057
0.0020
0.0000
0.0000
low_veg
0.0934
0.0282
0.7728
0.1045
0.0011
0.0000
tree
0.0091
0.0008
0.0515
0.9386
0.0000
0.0000
car
0.1176
0.0121
0.0059
0.0053
0.8592
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.918
0.947
0.848
0.912
0.833
--
Recall/Completeness
0.934
0.963
0.773
0.939
0.859
--
F1
0.926
0.955
0.809
0.925
0.846
--

Overall accuracy 0.908

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
0.8165
0.0459
0.0932
0.0374
0.0070
0.0000
building
0.0761
0.8718
0.0397
0.0125
0.0000
0.0000
low_veg
0.0306
0.0185
0.8718
0.0788
0.0002
0.0000
tree
0.0192
0.0069
0.1531
0.8209
0.0000
0.0000
car
0.1884
0.0121
0.0008
0.0024
0.7963
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.785
0.911
0.857
0.838
0.729
--
Recall/Completeness
0.816
0.872
0.872
0.821
0.796
--
F1
0.801
0.891
0.864
0.829
0.761
--

Overall accuracy 0.851

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
0.8433
0.0372
0.0863
0.0275
0.0057
0.0000
building
0.0732
0.8835
0.0332
0.0101
0.0000
0.0000
low_veg
0.0266
0.0139
0.8912
0.0682
0.0002
0.0000
tree
0.0122
0.0032
0.1308
0.8539
0.0000
0.0000
car
0.0784
0.0182
0.0000
0.0005
0.9028
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.810
0.934
0.879
0.861
0.731
--
Recall/Completeness
0.843
0.883
0.891
0.854
0.903
--
F1
0.826
0.908
0.885
0.857
0.808
--

Overall accuracy 0.874

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
0.9402
0.0217
0.0247
0.0067
0.0067
0.0000
building
0.0854
0.8876
0.0222
0.0045
0.0004
0.0000
low_veg
0.0701
0.0226
0.7005
0.2065
0.0002
0.0000
tree
0.0138
0.0038
0.0424
0.9400
0.0001
0.0000
car
0.2361
0.0041
0.0034
0.0053
0.7511
0.0000
clutter
0.7162
0.1139
0.1147
0.0172
0.0380
0.0000
Precision/Correctness
0.847
0.962
0.871
0.680
0.911
-nan
Recall/Completeness
0.940
0.888
0.701
0.940
0.751
0.000
F1
0.891
0.923
0.777
0.789
0.823
-nan

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_area27_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9648
0.0134
0.0177
0.0024
0.0018
0.0000
building
0.0750
0.9064
0.0162
0.0021
0.0002
0.0000
low_veg
0.0524
0.0104
0.7407
0.1965
0.0001
0.0000
tree
0.0059
0.0009
0.0260
0.9672
0.0000
0.0000
car
0.1318
0.0032
0.0013
0.0034
0.8603
0.0000
clutter
0.7211
0.1286
0.0951
0.0155
0.0397
0.0000
Precision/Correctness
0.878
0.980
0.907
0.709
0.967
-nan
Recall/Completeness
0.965
0.906
0.741
0.967
0.860
0.000
F1
0.920
0.942
0.816
0.818
0.910
-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
0.9424
0.0140
0.0262
0.0129
0.0046
0.0000
building
0.0388
0.9412
0.0141
0.0060
0.0000
0.0000
low_veg
0.0527
0.0192
0.6284
0.2995
0.0001
0.0000
tree
0.0063
0.0017
0.0241
0.9678
0.0000
0.0000
car
0.2482
0.0023
0.0033
0.0150
0.7311
0.0000
clutter
0.5324
0.3833
0.0373
0.0110
0.0361
0.0000
Precision/Correctness
0.913
0.926
0.833
0.671
0.765
-nan
Recall/Completeness
0.942
0.941
0.628
0.968
0.731
0.000
F1
0.927
0.934
0.716
0.793
0.748
-nan

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_area29_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9636
0.0075
0.0198
0.0057
0.0033
0.0000
building
0.0336
0.9544
0.0092
0.0028
0.0000
0.0000
low_veg
0.0303
0.0076
0.6740
0.2880
0.0001
0.0000
tree
0.0019
0.0004
0.0169
0.9808
0.0000
0.0000
car
0.1646
0.0002
0.0025
0.0134
0.8194
0.0000
clutter
0.5170
0.4113
0.0305
0.0033
0.0380
0.0000
Precision/Correctness
0.934
0.946
0.870
0.709
0.772
-nan
Recall/Completeness
0.964
0.954
0.674
0.981
0.819
0.000
F1
0.949
0.950
0.760
0.823
0.795
-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_area31_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9687
0.0099
0.0141
0.0035
0.0039
0.0000
building
0.0982
0.8879
0.0104
0.0023
0.0011
0.0000
low_veg
0.0339
0.0041
0.9307
0.0311
0.0002
0.0000
tree
0.0411
0.0030
0.0910
0.8642
0.0008
0.0000
car
0.1624
0.1686
0.0067
0.0037
0.6586
0.0000
clutter
0.5519
0.1998
0.1858
0.0147
0.0479
0.0000
Precision/Correctness
0.860
0.933
0.846
0.931
0.870
-nan
Recall/Completeness
0.969
0.888
0.931
0.864
0.659
0.000
F1
0.911
0.910
0.887
0.896
0.750
-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
0.9802
0.0073
0.0106
0.0006
0.0013
0.0000
building
0.0874
0.9063
0.0052
0.0004
0.0008
0.0000
low_veg
0.0158
0.0026
0.9567
0.0249
0.0000
0.0000
tree
0.0158
0.0004
0.0691
0.9145
0.0002
0.0000
car
0.0821
0.1916
0.0032
0.0005
0.7227
0.0000
clutter
0.5049
0.2267
0.2090
0.0073
0.0521
0.0000
Precision/Correctness
0.890
0.944
0.880
0.959
0.899
-nan
Recall/Completeness
0.980
0.906
0.957
0.914
0.723
0.000
F1
0.933
0.925
0.917
0.936
0.801
-nan

Overall accuracy 0.911

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
0.9829
0.0066
0.0063
0.0030
0.0012
0.0000
building
0.0775
0.8397
0.0765
0.0038
0.0024
0.0000
low_veg
0.0680
0.0105
0.7897
0.1318
0.0001
0.0000
tree
0.0456
0.0040
0.1375
0.8129
0.0000
0.0000
car
0.2267
0.0224
0.0029
0.0012
0.7467
0.0000
clutter
0.6387
0.0770
0.2202
0.0002
0.0639
0.0000
Precision/Correctness
0.834
0.964
0.705
0.790
0.675
-nan
Recall/Completeness
0.983
0.840
0.790
0.813
0.747
0.000
F1
0.903
0.898
0.745
0.801
0.709
-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_area33_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9924
0.0036
0.0028
0.0007
0.0004
0.0000
building
0.0690
0.8524
0.0745
0.0019
0.0022
0.0000
low_veg
0.0368
0.0045
0.8203
0.1384
0.0000
0.0000
tree
0.0191
0.0007
0.1276
0.8526
0.0000
0.0000
car
0.1122
0.0260
0.0010
0.0002
0.8605
0.0000
clutter
0.6015
0.0797
0.2505
0.0000
0.0683
0.0000
Precision/Correctness
0.865
0.976
0.717
0.800
0.668
-nan
Recall/Completeness
0.992
0.852
0.820
0.853
0.861
0.000
F1
0.924
0.910
0.765
0.826
0.752
-nan

Overall accuracy 0.859

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
0.8821
0.0275
0.0720
0.0175
0.0009
0.0000
building
0.0587
0.9185
0.0175
0.0049
0.0003
0.0000
low_veg
0.0471
0.0109
0.7284
0.2135
0.0001
0.0000
tree
0.0319
0.0049
0.1130
0.8501
0.0001
0.0000
car
0.2794
0.0036
0.0014
0.0104
0.7051
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.857
0.958
0.786
0.772
0.938
--
Recall/Completeness
0.882
0.919
0.728
0.850
0.705
--
F1
0.869
0.938
0.756
0.809
0.805
--

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_area35_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9225
0.0218
0.0518
0.0039
0.0001
0.0000
building
0.0479
0.9441
0.0063
0.0015
0.0002
0.0000
low_veg
0.0328
0.0039
0.7558
0.2075
0.0000
0.0000
tree
0.0113
0.0011
0.0856
0.9020
0.0000
0.0000
car
0.1721
0.0011
0.0000
0.0029
0.8240
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.900
0.976
0.845
0.798
0.975
--
Recall/Completeness
0.922
0.944
0.756
0.902
0.824
--
F1
0.911
0.960
0.798
0.847
0.893
--

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_area38_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9200
0.0220
0.0431
0.0126
0.0023
0.0000
building
0.0355
0.9077
0.0524
0.0040
0.0004
0.0000
low_veg
0.0410
0.0108
0.8596
0.0885
0.0002
0.0000
tree
0.0209
0.0033
0.1195
0.8563
0.0000
0.0000
car
0.1970
0.0446
0.0192
0.0075
0.7317
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.903
0.958
0.833
0.851
0.900
--
Recall/Completeness
0.920
0.908
0.860
0.856
0.732
--
F1
0.912
0.932
0.846
0.854
0.807
--

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_area38_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9467
0.0189
0.0296
0.0039
0.0009
0.0000
building
0.0286
0.9309
0.0385
0.0016
0.0004
0.0000
low_veg
0.0261
0.0049
0.8944
0.0746
0.0001
0.0000
tree
0.0069
0.0008
0.0957
0.8965
0.0000
0.0000
car
0.1033
0.0531
0.0117
0.0024
0.8295
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.938
0.972
0.872
0.885
0.946
--
Recall/Completeness
0.947
0.931
0.894
0.897
0.829
--
F1
0.942
0.951
0.883
0.891
0.884
--

Overall accuracy 0.918

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image