Detailled semantic labeling (2D) result


Name N. Audebert et al.
Affiliation Onera and IRISA, France
Abbreviation ONE_7
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
0.923
0.022
0.038
0.015
0.002
0.000
building
0.065
0.907
0.021
0.007
0.000
0.000
low_veg
0.062
0.018
0.796
0.123
0.000
0.000
tree
0.022
0.005
0.094
0.880
0.000
0.000
car
0.390
0.038
0.008
0.005
0.559
0.000
clutter
0.726
0.204
0.031
0.012
0.027
0.000
Precision/Correctness
0.846
0.946
0.820
0.859
0.898
-nan
Recall/Completeness
0.923
0.907
0.796
0.880
0.559
0.000
F1
0.883
0.926
0.808
0.869
0.689
-nan

Overall accuracy 0.869

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
0.947
0.015
0.031
0.007
0.001
0.000
building
0.057
0.924
0.014
0.004
0.000
0.000
low_veg
0.049
0.009
0.833
0.108
0.000
0.000
tree
0.010
0.002
0.077
0.911
0.000
0.000
car
0.279
0.044
0.005
0.003
0.670
0.000
clutter
0.717
0.221
0.029
0.005
0.029
0.000
Precision/Correctness
0.877
0.966
0.855
0.887
0.927
-nan
Recall/Completeness
0.947
0.924
0.833
0.911
0.670
0.000
F1
0.910
0.945
0.844
0.899
0.778
-nan

Overall accuracy 0.898
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9610
0.0084
0.0187
0.0100
0.0020
0.0000
building
0.0399
0.9356
0.0213
0.0032
0.0000
0.0000
low_veg
0.0956
0.0153
0.7454
0.1437
0.0000
0.0000
tree
0.0313
0.0058
0.0992
0.8637
0.0000
0.0000
car
0.4256
0.0001
0.0001
0.0015
0.5727
0.0000
clutter
0.9129
0.0355
0.0000
0.0467
0.0049
0.0000
Precision/Correctness
0.790
0.964
0.843
0.844
0.937
-nan
Recall/Completeness
0.961
0.936
0.745
0.864
0.573
0.000
F1
0.867
0.950
0.791
0.854
0.711
-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_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9806
0.0049
0.0104
0.0027
0.0015
0.0000
building
0.0306
0.9565
0.0121
0.0009
0.0000
0.0000
low_veg
0.0776
0.0061
0.7784
0.1378
0.0000
0.0000
tree
0.0151
0.0026
0.0850
0.8972
0.0000
0.0000
car
0.2823
0.0000
0.0000
0.0008
0.7169
0.0000
clutter
0.9404
0.0355
0.0000
0.0201
0.0040
0.0000
Precision/Correctness
0.824
0.982
0.875
0.867
0.950
-nan
Recall/Completeness
0.981
0.956
0.778
0.897
0.717
0.000
F1
0.896
0.969
0.824
0.882
0.817
-nan

Overall accuracy 0.884

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area4_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9486
0.0371
0.0088
0.0041
0.0014
0.0000
building
0.0743
0.9157
0.0081
0.0015
0.0004
0.0000
low_veg
0.1749
0.0424
0.5136
0.2689
0.0001
0.0000
tree
0.0685
0.0135
0.0950
0.8230
0.0000
0.0000
car
0.5100
0.0072
0.0011
0.0017
0.4800
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.821
0.974
0.662
0.737
0.917
--
Recall/Completeness
0.949
0.916
0.514
0.823
0.480
--
F1
0.880
0.944
0.579
0.778
0.630
--

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
0.9742
0.0168
0.0063
0.0019
0.0007
0.0000
building
0.0612
0.9309
0.0068
0.0007
0.0004
0.0000
low_veg
0.1324
0.0143
0.5588
0.2946
0.0000
0.0000
tree
0.0356
0.0056
0.0906
0.8682
0.0000
0.0000
car
0.4048
0.0033
0.0002
0.0006
0.5911
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.854
0.990
0.690
0.761
0.938
--
Recall/Completeness
0.974
0.931
0.559
0.868
0.591
--
F1
0.910
0.959
0.617
0.811
0.725
--

Overall accuracy 0.921

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
0.9174
0.0411
0.0316
0.0085
0.0014
0.0000
building
0.0487
0.9353
0.0125
0.0036
0.0000
0.0000
low_veg
0.0870
0.0298
0.7441
0.1391
0.0000
0.0000
tree
0.0190
0.0032
0.0500
0.9277
0.0002
0.0000
car
0.4569
0.0092
0.0043
0.0025
0.5271
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.859
0.955
0.749
0.936
0.955
--
Recall/Completeness
0.917
0.935
0.744
0.928
0.527
--
F1
0.887
0.945
0.746
0.932
0.679
--

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_area6_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9484
0.0269
0.0227
0.0019
0.0001
0.0000
building
0.0382
0.9537
0.0072
0.0009
0.0000
0.0000
low_veg
0.0702
0.0150
0.7943
0.1205
0.0000
0.0000
tree
0.0078
0.0007
0.0375
0.9540
0.0000
0.0000
car
0.3448
0.0058
0.0038
0.0012
0.6445
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.899
0.975
0.800
0.958
0.996
--
Recall/Completeness
0.948
0.954
0.794
0.954
0.644
--
F1
0.923
0.964
0.797
0.956
0.782
--

Overall accuracy 0.933

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
0.9005
0.0189
0.0714
0.0080
0.0011
0.0000
building
0.0371
0.9435
0.0152
0.0041
0.0000
0.0000
low_veg
0.0563
0.0128
0.8719
0.0589
0.0001
0.0000
tree
0.0240
0.0055
0.0879
0.8826
0.0000
0.0000
car
0.5011
0.0016
0.0164
0.0045
0.4764
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.893
0.957
0.784
0.933
0.954
--
Recall/Completeness
0.901
0.944
0.872
0.883
0.476
--
F1
0.897
0.950
0.826
0.907
0.635
--

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
0.9240
0.0129
0.0613
0.0014
0.0003
0.0000
building
0.0263
0.9647
0.0073
0.0017
0.0000
0.0000
low_veg
0.0381
0.0055
0.9065
0.0498
0.0000
0.0000
tree
0.0090
0.0022
0.0664
0.9224
0.0000
0.0000
car
0.3987
0.0004
0.0087
0.0035
0.5888
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.932
0.976
0.826
0.955
0.985
--
Recall/Completeness
0.924
0.965
0.907
0.922
0.589
--
F1
0.928
0.970
0.865
0.938
0.737
--

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_area10_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8787
0.0458
0.0547
0.0196
0.0012
0.0000
building
0.0286
0.9413
0.0155
0.0146
0.0000
0.0000
low_veg
0.0829
0.0257
0.7591
0.1323
0.0000
0.0000
tree
0.0154
0.0067
0.0682
0.9096
0.0000
0.0000
car
0.4436
0.0263
0.0042
0.0033
0.5226
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.923
0.905
0.777
0.846
0.894
--
Recall/Completeness
0.879
0.941
0.759
0.910
0.523
--
F1
0.900
0.923
0.768
0.877
0.660
--

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_area10_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9104
0.0323
0.0483
0.0084
0.0006
0.0000
building
0.0226
0.9557
0.0103
0.0114
0.0000
0.0000
low_veg
0.0811
0.0125
0.8056
0.1008
0.0000
0.0000
tree
0.0064
0.0029
0.0508
0.9399
0.0000
0.0000
car
0.3494
0.0318
0.0029
0.0003
0.6155
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.940
0.938
0.813
0.891
0.931
--
Recall/Completeness
0.910
0.956
0.806
0.940
0.616
--
F1
0.925
0.947
0.810
0.915
0.741
--

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_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9072
0.0205
0.0438
0.0269
0.0016
0.0000
building
0.1615
0.8204
0.0121
0.0060
0.0000
0.0000
low_veg
0.0505
0.0196
0.7787
0.1512
0.0001
0.0000
tree
0.0112
0.0066
0.1080
0.8742
0.0000
0.0000
car
0.3069
0.0000
0.0003
0.0048
0.6879
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.716
0.934
0.823
0.869
0.935
--
Recall/Completeness
0.907
0.820
0.779
0.874
0.688
--
F1
0.800
0.874
0.800
0.871
0.793
--

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_area12_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9327
0.0166
0.0372
0.0132
0.0002
0.0000
building
0.1691
0.8253
0.0035
0.0020
0.0000
0.0000
low_veg
0.0483
0.0094
0.8145
0.1279
0.0000
0.0000
tree
0.0059
0.0027
0.0908
0.9006
0.0000
0.0000
car
0.1759
0.0000
0.0000
0.0000
0.8241
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.730
0.964
0.853
0.897
0.990
--
Recall/Completeness
0.933
0.825
0.814
0.901
0.824
--
F1
0.819
0.889
0.833
0.899
0.900
--

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_area14_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8344
0.0289
0.1003
0.0334
0.0030
0.0000
building
0.0154
0.9607
0.0161
0.0078
0.0000
0.0000
low_veg
0.0819
0.0417
0.7327
0.1437
0.0000
0.0000
tree
0.0268
0.0111
0.1143
0.8478
0.0000
0.0000
car
0.2597
0.0000
0.0000
0.0068
0.7336
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.852
0.890
0.744
0.862
0.739
--
Recall/Completeness
0.834
0.961
0.733
0.848
0.734
--
F1
0.843
0.924
0.738
0.855
0.736
--

Overall accuracy 0.835

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
0.8530
0.0243
0.0974
0.0229
0.0023
0.0000
building
0.0100
0.9798
0.0065
0.0037
0.0000
0.0000
low_veg
0.0766
0.0273
0.7649
0.1312
0.0000
0.0000
tree
0.0188
0.0048
0.1020
0.8744
0.0000
0.0000
car
0.1560
0.0000
0.0000
0.0029
0.8411
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.879
0.924
0.765
0.884
0.753
--
Recall/Completeness
0.853
0.980
0.765
0.874
0.841
--
F1
0.866
0.951
0.765
0.879
0.795
--

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: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8540
0.0244
0.0700
0.0502
0.0014
0.0000
building
0.0281
0.9426
0.0187
0.0106
0.0000
0.0000
low_veg
0.0211
0.0138
0.8563
0.1089
0.0000
0.0000
tree
0.0229
0.0047
0.1129
0.8595
0.0000
0.0000
car
0.2432
0.0025
0.0013
0.0111
0.7419
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.867
0.946
0.821
0.883
0.885
--
Recall/Completeness
0.854
0.943
0.856
0.860
0.742
--
F1
0.861
0.944
0.838
0.871
0.807
--

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_area16_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8880
0.0199
0.0611
0.0307
0.0004
0.0000
building
0.0236
0.9647
0.0075
0.0042
0.0000
0.0000
low_veg
0.0169
0.0072
0.8817
0.0942
0.0000
0.0000
tree
0.0153
0.0011
0.0989
0.8847
0.0000
0.0000
car
0.1509
0.0000
0.0000
0.0030
0.8461
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.899
0.969
0.848
0.907
0.960
--
Recall/Completeness
0.888
0.965
0.882
0.885
0.846
--
F1
0.893
0.967
0.865
0.896
0.899
--

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_area20_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8862
0.0217
0.0508
0.0403
0.0009
0.0000
building
0.0207
0.9482
0.0228
0.0082
0.0000
0.0000
low_veg
0.0672
0.0186
0.7650
0.1491
0.0000
0.0000
tree
0.0080
0.0018
0.0478
0.9424
0.0000
0.0000
car
0.3754
0.0016
0.0277
0.0175
0.5778
0.0000
clutter
0.4498
0.5486
0.0000
0.0016
0.0000
0.0000
Precision/Correctness
0.842
0.868
0.815
0.910
0.927
-nan
Recall/Completeness
0.886
0.948
0.765
0.942
0.578
0.000
F1
0.864
0.906
0.789
0.926
0.712
-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_area20_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9172
0.0127
0.0482
0.0213
0.0006
0.0000
building
0.0180
0.9596
0.0191
0.0033
0.0000
0.0000
low_veg
0.0596
0.0074
0.8141
0.1189
0.0000
0.0000
tree
0.0036
0.0002
0.0360
0.9602
0.0000
0.0000
car
0.2627
0.0001
0.0174
0.0086
0.7113
0.0000
clutter
0.4336
0.5659
0.0000
0.0005
0.0000
0.0000
Precision/Correctness
0.866
0.889
0.843
0.937
0.950
-nan
Recall/Completeness
0.917
0.960
0.814
0.960
0.711
0.000
F1
0.891
0.923
0.828
0.949
0.813
-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_area22_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9119
0.0187
0.0359
0.0320
0.0015
0.0000
building
0.0272
0.9524
0.0142
0.0062
0.0000
0.0000
low_veg
0.1037
0.0338
0.7310
0.1312
0.0004
0.0000
tree
0.0214
0.0032
0.0598
0.9156
0.0000
0.0000
car
0.4795
0.0006
0.0141
0.0146
0.4913
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.887
0.925
0.825
0.874
0.907
--
Recall/Completeness
0.912
0.952
0.731
0.916
0.491
--
F1
0.899
0.939
0.775
0.894
0.637
--

Overall accuracy 0.879

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area22_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9421
0.0118
0.0296
0.0158
0.0006
0.0000
building
0.0204
0.9704
0.0069
0.0022
0.0000
0.0000
low_veg
0.1009
0.0195
0.7790
0.1002
0.0004
0.0000
tree
0.0089
0.0008
0.0448
0.9455
0.0000
0.0000
car
0.3833
0.0000
0.0117
0.0055
0.5995
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.913
0.957
0.865
0.915
0.945
--
Recall/Completeness
0.942
0.970
0.779
0.945
0.599
--
F1
0.927
0.964
0.820
0.930
0.734
--

Overall accuracy 0.913

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
0.8350
0.0297
0.0985
0.0353
0.0015
0.0000
building
0.0729
0.8787
0.0313
0.0171
0.0000
0.0000
low_veg
0.0261
0.0179
0.8844
0.0717
0.0000
0.0000
tree
0.0172
0.0068
0.1550
0.8211
0.0000
0.0000
car
0.3538
0.0000
0.0029
0.0039
0.6394
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.801
0.925
0.859
0.846
0.914
--
Recall/Completeness
0.835
0.879
0.884
0.821
0.639
--
F1
0.818
0.901
0.872
0.834
0.753
--

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_area24_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8623
0.0216
0.0912
0.0242
0.0007
0.0000
building
0.0703
0.8921
0.0232
0.0145
0.0000
0.0000
low_veg
0.0223
0.0132
0.9036
0.0609
0.0000
0.0000
tree
0.0107
0.0031
0.1330
0.8533
0.0000
0.0000
car
0.2283
0.0000
0.0000
0.0012
0.7705
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.826
0.948
0.882
0.871
0.957
--
Recall/Completeness
0.862
0.892
0.904
0.853
0.771
--
F1
0.844
0.919
0.892
0.862
0.854
--

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_area27_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9581
0.0153
0.0178
0.0060
0.0028
0.0000
building
0.0748
0.9038
0.0162
0.0049
0.0003
0.0000
low_veg
0.0846
0.0221
0.7242
0.1690
0.0001
0.0000
tree
0.0138
0.0037
0.0420
0.9406
0.0000
0.0000
car
0.4208
0.0056
0.0049
0.0044
0.5643
0.0000
clutter
0.8003
0.0267
0.1107
0.0057
0.0565
0.0000
Precision/Correctness
0.837
0.970
0.899
0.719
0.940
-nan
Recall/Completeness
0.958
0.904
0.724
0.941
0.564
0.000
F1
0.893
0.936
0.802
0.815
0.705
-nan

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: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9783
0.0079
0.0114
0.0020
0.0004
0.0000
building
0.0613
0.9258
0.0103
0.0024
0.0002
0.0000
low_veg
0.0656
0.0093
0.7685
0.1566
0.0001
0.0000
tree
0.0062
0.0010
0.0258
0.9670
0.0000
0.0000
car
0.3029
0.0053
0.0028
0.0029
0.6860
0.0000
clutter
0.8175
0.0228
0.0917
0.0021
0.0659
0.0000
Precision/Correctness
0.875
0.987
0.935
0.752
0.981
-nan
Recall/Completeness
0.978
0.926
0.769
0.967
0.686
0.000
F1
0.924
0.955
0.844
0.846
0.807
-nan

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_area29_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9558
0.0092
0.0219
0.0116
0.0016
0.0000
building
0.0376
0.9439
0.0116
0.0069
0.0000
0.0000
low_veg
0.0647
0.0221
0.6391
0.2741
0.0000
0.0000
tree
0.0066
0.0016
0.0221
0.9697
0.0000
0.0000
car
0.4006
0.0011
0.0076
0.0089
0.5818
0.0000
clutter
0.7199
0.2225
0.0200
0.0110
0.0267
0.0000
Precision/Correctness
0.896
0.948
0.859
0.690
0.841
-nan
Recall/Completeness
0.956
0.944
0.639
0.970
0.582
0.000
F1
0.925
0.946
0.733
0.806
0.688
-nan

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_area29_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9739
0.0040
0.0163
0.0047
0.0011
0.0000
building
0.0313
0.9582
0.0069
0.0037
0.0000
0.0000
low_veg
0.0406
0.0088
0.6892
0.2614
0.0000
0.0000
tree
0.0023
0.0002
0.0151
0.9824
0.0000
0.0000
car
0.2879
0.0000
0.0089
0.0060
0.6971
0.0000
clutter
0.7174
0.2376
0.0126
0.0035
0.0289
0.0000
Precision/Correctness
0.919
0.966
0.895
0.728
0.851
-nan
Recall/Completeness
0.974
0.958
0.689
0.982
0.697
0.000
F1
0.946
0.962
0.779
0.836
0.766
-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
0.9627
0.0139
0.0152
0.0036
0.0046
0.0000
building
0.1685
0.8200
0.0079
0.0024
0.0010
0.0000
low_veg
0.0278
0.0035
0.9444
0.0242
0.0000
0.0000
tree
0.0311
0.0036
0.0897
0.8751
0.0004
0.0000
car
0.1654
0.2017
0.0084
0.0044
0.6201
0.0000
clutter
0.6006
0.2622
0.0998
0.0097
0.0278
0.0000
Precision/Correctness
0.823
0.910
0.865
0.942
0.879
-nan
Recall/Completeness
0.963
0.820
0.944
0.875
0.620
0.000
F1
0.887
0.863
0.903
0.907
0.727
-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_area31_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9782
0.0090
0.0111
0.0005
0.0011
0.0000
building
0.1630
0.8321
0.0037
0.0006
0.0008
0.0000
low_veg
0.0137
0.0013
0.9684
0.0166
0.0000
0.0000
tree
0.0094
0.0006
0.0705
0.9195
0.0001
0.0000
car
0.0983
0.2254
0.0031
0.0007
0.6724
0.0000
clutter
0.5616
0.3003
0.1058
0.0033
0.0290
0.0000
Precision/Correctness
0.845
0.926
0.898
0.971
0.926
-nan
Recall/Completeness
0.978
0.832
0.968
0.919
0.672
0.000
F1
0.907
0.876
0.932
0.945
0.779
-nan

Overall accuracy 0.889

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area33_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9897
0.0038
0.0039
0.0022
0.0005
0.0000
building
0.1724
0.7493
0.0458
0.0308
0.0016
0.0000
low_veg
0.0889
0.0085
0.8246
0.0780
0.0000
0.0000
tree
0.0500
0.0035
0.1637
0.7829
0.0000
0.0000
car
0.4425
0.0022
0.0048
0.0008
0.5498
0.0000
clutter
0.8629
0.0696
0.0146
0.0002
0.0527
0.0000
Precision/Correctness
0.759
0.969
0.795
0.790
0.669
-nan
Recall/Completeness
0.990
0.749
0.825
0.783
0.550
0.000
F1
0.859
0.845
0.809
0.786
0.604
-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
0.9966
0.0015
0.0013
0.0004
0.0001
0.0000
building
0.1665
0.7598
0.0421
0.0301
0.0015
0.0000
low_veg
0.0529
0.0029
0.8626
0.0815
0.0000
0.0000
tree
0.0216
0.0003
0.1520
0.8262
0.0000
0.0000
car
0.3190
0.0001
0.0025
0.0001
0.6784
0.0000
clutter
0.8535
0.0716
0.0146
0.0000
0.0603
0.0000
Precision/Correctness
0.783
0.980
0.816
0.797
0.659
-nan
Recall/Completeness
0.997
0.760
0.863
0.826
0.678
0.000
F1
0.877
0.856
0.838
0.811
0.668
-nan

Overall accuracy 0.835

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
0.8917
0.0284
0.0649
0.0145
0.0004
0.0000
building
0.0556
0.9196
0.0196
0.0049
0.0003
0.0000
low_veg
0.0499
0.0099
0.7453
0.1950
0.0000
0.0000
tree
0.0308
0.0040
0.1154
0.8498
0.0000
0.0000
car
0.5016
0.0017
0.0001
0.0104
0.4863
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.854
0.959
0.792
0.788
0.951
--
Recall/Completeness
0.892
0.920
0.745
0.850
0.486
--
F1
0.873
0.939
0.768
0.818
0.643
--

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_area35_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9301
0.0237
0.0434
0.0027
0.0001
0.0000
building
0.0433
0.9478
0.0075
0.0012
0.0003
0.0000
low_veg
0.0339
0.0035
0.7733
0.1893
0.0000
0.0000
tree
0.0099
0.0006
0.0865
0.9030
0.0000
0.0000
car
0.3714
0.0024
0.0000
0.0035
0.6227
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.902
0.975
0.853
0.813
0.972
--
Recall/Completeness
0.930
0.948
0.773
0.903
0.623
--
F1
0.916
0.961
0.811
0.856
0.759
--

Overall accuracy 0.889

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area38_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9288
0.0223
0.0377
0.0101
0.0011
0.0000
building
0.0281
0.9097
0.0571
0.0047
0.0005
0.0000
low_veg
0.0499
0.0097
0.8728
0.0676
0.0000
0.0000
tree
0.0236
0.0031
0.1248
0.8485
0.0000
0.0000
car
0.3902
0.0348
0.0242
0.0109
0.5398
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.894
0.960
0.833
0.878
0.925
--
Recall/Completeness
0.929
0.910
0.873
0.849
0.540
--
F1
0.911
0.934
0.852
0.863
0.682
--

Overall accuracy 0.889

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area38_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9523
0.0200
0.0245
0.0027
0.0005
0.0000
building
0.0190
0.9363
0.0419
0.0022
0.0005
0.0000
low_veg
0.0340
0.0036
0.9077
0.0546
0.0000
0.0000
tree
0.0081
0.0007
0.0986
0.8926
0.0000
0.0000
car
0.2650
0.0441
0.0139
0.0081
0.6689
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.935
0.973
0.873
0.911
0.951
--
Recall/Completeness
0.952
0.936
0.908
0.893
0.669
--
F1
0.943
0.954
0.890
0.902
0.785
--

Overall accuracy 0.923

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image