Detailled semantic labeling (2D) result


Name Y. Sun
Affiliation Huazhong University of Science and Technology (HUST), Wuhan, China
Abbreviation HUSTW2
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
0.906
0.032
0.041
0.019
0.003
0.000
building
0.051
0.931
0.014
0.004
0.001
0.000
low_veg
0.052
0.024
0.787
0.138
0.000
0.000
tree
0.017
0.009
0.079
0.895
0.000
0.000
car
0.437
0.021
0.014
0.008
0.521
0.000
clutter
0.536
0.149
0.118
0.011
0.187
0.000
Precision/Correctness
0.868
0.933
0.833
0.849
0.707
-nan
Recall/Completeness
0.906
0.931
0.787
0.895
0.521
0.000
F1
0.886
0.932
0.809
0.872
0.600
-nan

Overall accuracy 0.871

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
0.933
0.024
0.033
0.009
0.002
0.000
building
0.043
0.947
0.007
0.002
0.000
0.000
low_veg
0.041
0.014
0.826
0.119
0.000
0.000
tree
0.007
0.004
0.065
0.923
0.000
0.000
car
0.352
0.023
0.009
0.004
0.612
0.000
clutter
0.509
0.156
0.126
0.004
0.206
0.000
Precision/Correctness
0.897
0.954
0.867
0.881
0.720
-nan
Recall/Completeness
0.933
0.947
0.826
0.923
0.612
0.000
F1
0.915
0.951
0.846
0.901
0.662
-nan

Overall accuracy 0.901
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8987
0.0152
0.0653
0.0171
0.0037
0.0000
building
0.0193
0.9556
0.0222
0.0029
0.0001
0.0000
low_veg
0.0440
0.0251
0.7897
0.1412
0.0000
0.0000
tree
0.0181
0.0116
0.0874
0.8829
0.0000
0.0000
car
0.4869
0.0025
0.0127
0.0037
0.4941
0.0000
clutter
0.8643
0.0986
0.0002
0.0357
0.0012
0.0000
Precision/Correctness
0.839
0.937
0.817
0.844
0.888
-nan
Recall/Completeness
0.899
0.956
0.790
0.883
0.494
0.000
F1
0.868
0.946
0.803
0.863
0.635
-nan

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_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9275
0.0103
0.0538
0.0060
0.0023
0.0000
building
0.0130
0.9717
0.0143
0.0010
0.0001
0.0000
low_veg
0.0308
0.0132
0.8241
0.1319
0.0000
0.0000
tree
0.0073
0.0073
0.0745
0.9109
0.0000
0.0000
car
0.3906
0.0009
0.0120
0.0013
0.5952
0.0000
clutter
0.8860
0.1006
0.0001
0.0120
0.0012
0.0000
Precision/Correctness
0.869
0.960
0.848
0.871
0.919
-nan
Recall/Completeness
0.927
0.972
0.824
0.911
0.595
0.000
F1
0.897
0.966
0.836
0.891
0.723
-nan

Overall accuracy 0.887

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area4_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8867
0.0863
0.0171
0.0064
0.0035
0.0000
building
0.0361
0.9534
0.0089
0.0014
0.0002
0.0000
low_veg
0.1055
0.0856
0.5595
0.2493
0.0000
0.0000
tree
0.0451
0.0252
0.0648
0.8647
0.0001
0.0000
car
0.6030
0.0339
0.0039
0.0025
0.3567
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.878
0.946
0.655
0.750
0.819
--
Recall/Completeness
0.887
0.953
0.560
0.865
0.357
--
F1
0.882
0.950
0.603
0.803
0.497
--

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_area4_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9169
0.0635
0.0136
0.0038
0.0022
0.0000
building
0.0245
0.9671
0.0075
0.0008
0.0002
0.0000
low_veg
0.0723
0.0492
0.6107
0.2678
0.0000
0.0000
tree
0.0192
0.0098
0.0593
0.9117
0.0000
0.0000
car
0.5514
0.0265
0.0024
0.0008
0.4189
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.915
0.965
0.688
0.777
0.861
--
Recall/Completeness
0.917
0.967
0.611
0.912
0.419
--
F1
0.916
0.966
0.647
0.839
0.564
--

Overall accuracy 0.929

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
0.8981
0.0621
0.0283
0.0097
0.0018
0.0000
building
0.0278
0.9585
0.0108
0.0028
0.0001
0.0000
low_veg
0.0668
0.0501
0.6887
0.1944
0.0000
0.0000
tree
0.0127
0.0060
0.0408
0.9404
0.0001
0.0000
car
0.5311
0.0088
0.0020
0.0014
0.4567
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.889
0.932
0.765
0.918
0.936
--
Recall/Completeness
0.898
0.958
0.689
0.940
0.457
--
F1
0.893
0.945
0.725
0.929
0.614
--

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
0.9300
0.0462
0.0209
0.0024
0.0004
0.0000
building
0.0178
0.9751
0.0062
0.0008
0.0001
0.0000
low_veg
0.0484
0.0354
0.7466
0.1697
0.0000
0.0000
tree
0.0036
0.0021
0.0316
0.9627
0.0000
0.0000
car
0.4316
0.0025
0.0008
0.0000
0.5651
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.931
0.955
0.813
0.943
0.981
--
Recall/Completeness
0.930
0.975
0.747
0.963
0.565
--
F1
0.930
0.965
0.778
0.953
0.717
--

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
0.8876
0.0391
0.0566
0.0142
0.0024
0.0000
building
0.0279
0.9523
0.0168
0.0028
0.0002
0.0000
low_veg
0.0614
0.0149
0.8663
0.0575
0.0000
0.0000
tree
0.0206
0.0105
0.0749
0.8940
0.0000
0.0000
car
0.5352
0.0081
0.0201
0.0064
0.4302
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.896
0.925
0.810
0.928
0.901
--
Recall/Completeness
0.888
0.952
0.866
0.894
0.430
--
F1
0.892
0.938
0.837
0.911
0.582
--

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_area8_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9125
0.0335
0.0488
0.0043
0.0010
0.0000
building
0.0166
0.9737
0.0086
0.0010
0.0002
0.0000
low_veg
0.0439
0.0069
0.9048
0.0444
0.0000
0.0000
tree
0.0077
0.0053
0.0598
0.9273
0.0000
0.0000
car
0.4531
0.0092
0.0118
0.0046
0.5212
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.934
0.946
0.847
0.956
0.950
--
Recall/Completeness
0.912
0.974
0.905
0.927
0.521
--
F1
0.923
0.960
0.875
0.941
0.673
--

Overall accuracy 0.924

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
0.8773
0.0585
0.0414
0.0207
0.0022
0.0000
building
0.0203
0.9544
0.0136
0.0116
0.0000
0.0000
low_veg
0.0714
0.0379
0.7324
0.1582
0.0001
0.0000
tree
0.0130
0.0099
0.0644
0.9127
0.0000
0.0000
car
0.4856
0.0304
0.0119
0.0077
0.4644
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.933
0.880
0.801
0.830
0.795
--
Recall/Completeness
0.877
0.954
0.732
0.913
0.464
--
F1
0.905
0.916
0.765
0.870
0.586
--

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_area10_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9097
0.0460
0.0342
0.0085
0.0015
0.0000
building
0.0108
0.9727
0.0077
0.0089
0.0000
0.0000
low_veg
0.0678
0.0244
0.7828
0.1249
0.0001
0.0000
tree
0.0056
0.0042
0.0496
0.9406
0.0000
0.0000
car
0.4123
0.0336
0.0099
0.0028
0.5415
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.953
0.911
0.841
0.876
0.820
--
Recall/Completeness
0.910
0.973
0.783
0.941
0.541
--
F1
0.931
0.941
0.811
0.907
0.652
--

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
0.8970
0.0230
0.0396
0.0380
0.0025
0.0000
building
0.1747
0.8059
0.0156
0.0036
0.0002
0.0000
low_veg
0.0670
0.0254
0.7227
0.1849
0.0001
0.0000
tree
0.0088
0.0090
0.0937
0.8884
0.0000
0.0000
car
0.3026
0.0000
0.0077
0.0101
0.6797
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.689
0.917
0.829
0.846
0.894
--
Recall/Completeness
0.897
0.806
0.723
0.888
0.680
--
F1
0.779
0.858
0.772
0.867
0.772
--

Overall accuracy 0.825

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
0.9262
0.0193
0.0328
0.0209
0.0007
0.0000
building
0.1825
0.8090
0.0073
0.0010
0.0002
0.0000
low_veg
0.0654
0.0158
0.7611
0.1577
0.0000
0.0000
tree
0.0039
0.0038
0.0807
0.9117
0.0000
0.0000
car
0.1880
0.0000
0.0086
0.0032
0.8002
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.702
0.948
0.857
0.876
0.955
--
Recall/Completeness
0.926
0.809
0.761
0.912
0.800
--
F1
0.799
0.873
0.806
0.894
0.871
--

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_area14_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8753
0.0289
0.0575
0.0368
0.0015
0.0000
building
0.0141
0.9629
0.0187
0.0043
0.0000
0.0000
low_veg
0.0700
0.0510
0.7252
0.1538
0.0000
0.0000
tree
0.0223
0.0142
0.1045
0.8590
0.0000
0.0000
car
0.2493
0.0003
0.0000
0.0045
0.7459
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.876
0.874
0.782
0.856
0.846
--
Recall/Completeness
0.875
0.963
0.725
0.859
0.746
--
F1
0.876
0.916
0.752
0.858
0.793
--

Overall accuracy 0.847

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
0.8964
0.0248
0.0526
0.0254
0.0008
0.0000
building
0.0084
0.9833
0.0071
0.0013
0.0000
0.0000
low_veg
0.0639
0.0375
0.7589
0.1396
0.0000
0.0000
tree
0.0149
0.0075
0.0938
0.8839
0.0000
0.0000
car
0.1238
0.0004
0.0000
0.0001
0.8757
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.902
0.907
0.807
0.880
0.903
--
Recall/Completeness
0.896
0.983
0.759
0.884
0.876
--
F1
0.899
0.943
0.782
0.882
0.889
--

Overall accuracy 0.873

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
0.8523
0.0202
0.0667
0.0595
0.0012
0.0000
building
0.0309
0.9431
0.0185
0.0076
0.0000
0.0000
low_veg
0.0237
0.0134
0.7972
0.1656
0.0001
0.0000
tree
0.0218
0.0062
0.0832
0.8888
0.0000
0.0000
car
0.4113
0.0009
0.0202
0.0234
0.5443
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.860
0.947
0.843
0.845
0.846
--
Recall/Completeness
0.852
0.943
0.797
0.889
0.544
--
F1
0.856
0.945
0.819
0.866
0.662
--

Overall accuracy 0.865

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
0.8860
0.0162
0.0600
0.0374
0.0004
0.0000
building
0.0260
0.9637
0.0074
0.0029
0.0000
0.0000
low_veg
0.0195
0.0076
0.8242
0.1486
0.0001
0.0000
tree
0.0144
0.0024
0.0714
0.9118
0.0000
0.0000
car
0.3290
0.0000
0.0106
0.0118
0.6485
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.892
0.969
0.870
0.869
0.916
--
Recall/Completeness
0.886
0.964
0.824
0.912
0.649
--
F1
0.889
0.966
0.846
0.890
0.759
--

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_area20_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8411
0.0374
0.0809
0.0393
0.0012
0.0000
building
0.0185
0.9547
0.0229
0.0039
0.0000
0.0000
low_veg
0.0680
0.0155
0.7410
0.1756
0.0000
0.0000
tree
0.0075
0.0024
0.0379
0.9521
0.0000
0.0000
car
0.4275
0.0007
0.0497
0.0188
0.5033
0.0000
clutter
0.0343
0.2264
0.7373
0.0019
0.0000
0.0000
Precision/Correctness
0.885
0.898
0.720
0.902
0.896
-nan
Recall/Completeness
0.841
0.955
0.741
0.952
0.503
0.000
F1
0.863
0.926
0.730
0.926
0.644
-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_area20_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8719
0.0301
0.0768
0.0208
0.0004
0.0000
building
0.0155
0.9685
0.0147
0.0013
0.0000
0.0000
low_veg
0.0607
0.0066
0.7918
0.1409
0.0000
0.0000
tree
0.0029
0.0006
0.0287
0.9678
0.0000
0.0000
car
0.3553
0.0004
0.0362
0.0111
0.5970
0.0000
clutter
0.0240
0.2338
0.7414
0.0008
0.0000
0.0000
Precision/Correctness
0.913
0.920
0.741
0.930
0.957
-nan
Recall/Completeness
0.872
0.969
0.792
0.968
0.597
0.000
F1
0.892
0.943
0.766
0.948
0.735
-nan

Overall accuracy 0.888

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area22_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8966
0.0239
0.0415
0.0345
0.0035
0.0000
building
0.0259
0.9556
0.0128
0.0057
0.0001
0.0000
low_veg
0.0977
0.0381
0.7079
0.1563
0.0000
0.0000
tree
0.0186
0.0050
0.0462
0.9302
0.0000
0.0000
car
0.4533
0.0131
0.0272
0.0145
0.4919
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.892
0.910
0.831
0.860
0.827
--
Recall/Completeness
0.897
0.956
0.708
0.930
0.492
--
F1
0.894
0.932
0.764
0.894
0.617
--

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_area22_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9281
0.0171
0.0359
0.0170
0.0018
0.0000
building
0.0168
0.9753
0.0050
0.0029
0.0000
0.0000
low_veg
0.0946
0.0248
0.7569
0.1237
0.0000
0.0000
tree
0.0077
0.0020
0.0326
0.9578
0.0000
0.0000
car
0.3681
0.0161
0.0206
0.0061
0.5891
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.918
0.941
0.870
0.901
0.889
--
Recall/Completeness
0.928
0.975
0.757
0.958
0.589
--
F1
0.923
0.958
0.810
0.928
0.708
--

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_area24_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8274
0.0410
0.0914
0.0384
0.0018
0.0000
building
0.0584
0.9121
0.0242
0.0053
0.0000
0.0000
low_veg
0.0284
0.0176
0.8765
0.0774
0.0000
0.0000
tree
0.0152
0.0106
0.1146
0.8596
0.0000
0.0000
car
0.5676
0.0000
0.0058
0.0063
0.4202
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.808
0.915
0.885
0.850
0.861
--
Recall/Completeness
0.827
0.912
0.877
0.860
0.420
--
F1
0.817
0.914
0.881
0.855
0.565
--

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_area24_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8595
0.0313
0.0821
0.0266
0.0005
0.0000
building
0.0554
0.9256
0.0157
0.0032
0.0000
0.0000
low_veg
0.0255
0.0130
0.8978
0.0637
0.0000
0.0000
tree
0.0090
0.0062
0.0955
0.8893
0.0000
0.0000
car
0.5019
0.0000
0.0002
0.0002
0.4976
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.832
0.939
0.907
0.877
0.946
--
Recall/Completeness
0.859
0.926
0.898
0.889
0.498
--
F1
0.845
0.932
0.902
0.883
0.652
--

Overall accuracy 0.894

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
0.9320
0.0253
0.0249
0.0076
0.0103
0.0000
building
0.0478
0.9353
0.0109
0.0055
0.0005
0.0000
low_veg
0.0662
0.0311
0.7184
0.1842
0.0001
0.0000
tree
0.0100
0.0097
0.0300
0.9503
0.0000
0.0000
car
0.4332
0.0046
0.0080
0.0081
0.5462
0.0000
clutter
0.7818
0.0809
0.0686
0.0110
0.0576
0.0000
Precision/Correctness
0.864
0.955
0.902
0.701
0.831
-nan
Recall/Completeness
0.932
0.935
0.718
0.950
0.546
0.000
F1
0.897
0.945
0.800
0.807
0.659
-nan

Overall accuracy 0.878

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area27_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9601
0.0158
0.0173
0.0029
0.0039
0.0000
building
0.0356
0.9556
0.0049
0.0036
0.0003
0.0000
low_veg
0.0519
0.0171
0.7623
0.1686
0.0002
0.0000
tree
0.0039
0.0044
0.0191
0.9726
0.0000
0.0000
car
0.3613
0.0039
0.0045
0.0065
0.6238
0.0000
clutter
0.7927
0.0766
0.0448
0.0078
0.0781
0.0000
Precision/Correctness
0.901
0.975
0.939
0.735
0.909
-nan
Recall/Completeness
0.960
0.956
0.762
0.973
0.624
0.000
F1
0.930
0.965
0.841
0.837
0.740
-nan

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_area29_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9435
0.0155
0.0248
0.0130
0.0033
0.0000
building
0.0439
0.9420
0.0094
0.0046
0.0001
0.0000
low_veg
0.0503
0.0260
0.6376
0.2860
0.0000
0.0000
tree
0.0044
0.0061
0.0189
0.9707
0.0000
0.0000
car
0.3604
0.0053
0.0061
0.0095
0.6187
0.0000
clutter
0.5954
0.2139
0.0195
0.0113
0.1599
0.0000
Precision/Correctness
0.904
0.936
0.857
0.682
0.573
-nan
Recall/Completeness
0.943
0.942
0.638
0.971
0.619
0.000
F1
0.923
0.939
0.731
0.801
0.595
-nan

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_area29_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9646
0.0093
0.0188
0.0057
0.0016
0.0000
building
0.0388
0.9541
0.0049
0.0021
0.0001
0.0000
low_veg
0.0278
0.0106
0.6894
0.2721
0.0000
0.0000
tree
0.0015
0.0030
0.0137
0.9818
0.0000
0.0000
car
0.2676
0.0024
0.0056
0.0065
0.7179
0.0000
clutter
0.5803
0.2206
0.0149
0.0039
0.1804
0.0000
Precision/Correctness
0.926
0.958
0.892
0.721
0.568
-nan
Recall/Completeness
0.965
0.954
0.689
0.982
0.718
0.000
F1
0.945
0.956
0.778
0.831
0.634
-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_area31_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9680
0.0079
0.0122
0.0047
0.0071
0.0000
building
0.1397
0.8498
0.0060
0.0013
0.0032
0.0000
low_veg
0.0323
0.0027
0.9416
0.0233
0.0001
0.0000
tree
0.0266
0.0057
0.0862
0.8814
0.0002
0.0000
car
0.2699
0.0687
0.0075
0.0086
0.6453
0.0000
clutter
0.5490
0.2004
0.0147
0.0100
0.2260
0.0000
Precision/Correctness
0.834
0.946
0.892
0.941
0.673
-nan
Recall/Completeness
0.968
0.850
0.942
0.881
0.645
0.000
F1
0.896
0.895
0.916
0.910
0.659
-nan

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_area31_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9817
0.0057
0.0093
0.0008
0.0026
0.0000
building
0.1308
0.8647
0.0015
0.0002
0.0028
0.0000
low_veg
0.0158
0.0008
0.9696
0.0138
0.0000
0.0000
tree
0.0081
0.0021
0.0694
0.9204
0.0000
0.0000
car
0.1881
0.0795
0.0019
0.0032
0.7273
0.0000
clutter
0.5021
0.2272
0.0091
0.0026
0.2590
0.0000
Precision/Correctness
0.861
0.955
0.924
0.975
0.684
-nan
Recall/Completeness
0.982
0.865
0.970
0.920
0.727
0.000
F1
0.917
0.908
0.946
0.947
0.705
-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_area33_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9743
0.0058
0.0156
0.0028
0.0015
0.0000
building
0.1639
0.8257
0.0055
0.0018
0.0030
0.0000
low_veg
0.0613
0.0118
0.9036
0.0227
0.0007
0.0000
tree
0.0372
0.0201
0.1444
0.7983
0.0000
0.0000
car
0.4870
0.0005
0.0118
0.0008
0.5000
0.0000
clutter
0.5482
0.0572
0.0033
0.0006
0.3907
0.0000
Precision/Correctness
0.795
0.963
0.858
0.942
0.221
-nan
Recall/Completeness
0.974
0.826
0.904
0.798
0.500
0.000
F1
0.876
0.889
0.880
0.864
0.306
-nan

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_area33_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9841
0.0033
0.0115
0.0005
0.0006
0.0000
building
0.1606
0.8338
0.0021
0.0007
0.0028
0.0000
low_veg
0.0313
0.0058
0.9432
0.0190
0.0007
0.0000
tree
0.0139
0.0143
0.1331
0.8387
0.0000
0.0000
car
0.3846
0.0005
0.0070
0.0001
0.6079
0.0000
clutter
0.4995
0.0525
0.0021
0.0001
0.4457
0.0000
Precision/Correctness
0.820
0.976
0.883
0.963
0.205
-nan
Recall/Completeness
0.984
0.834
0.943
0.839
0.608
0.000
F1
0.894
0.899
0.912
0.897
0.306
-nan

Overall accuracy 0.865

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
0.8784
0.0338
0.0630
0.0237
0.0011
0.0000
building
0.0337
0.9418
0.0215
0.0028
0.0002
0.0000
low_veg
0.0352
0.0147
0.7325
0.2177
0.0000
0.0000
tree
0.0205
0.0069
0.1041
0.8685
0.0000
0.0000
car
0.5806
0.0056
0.0120
0.0103
0.3916
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.891
0.948
0.798
0.770
0.900
--
Recall/Completeness
0.878
0.942
0.732
0.868
0.392
--
F1
0.885
0.945
0.764
0.816
0.546
--

Overall accuracy 0.853

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area35_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9235
0.0284
0.0408
0.0068
0.0004
0.0000
building
0.0216
0.9686
0.0090
0.0006
0.0002
0.0000
low_veg
0.0220
0.0065
0.7649
0.2066
0.0000
0.0000
tree
0.0053
0.0020
0.0798
0.9130
0.0000
0.0000
car
0.5043
0.0074
0.0089
0.0033
0.4761
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.936
0.968
0.859
0.799
0.949
--
Recall/Completeness
0.924
0.969
0.765
0.913
0.476
--
F1
0.930
0.968
0.809
0.852
0.634
--

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_area38_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9089
0.0302
0.0427
0.0155
0.0028
0.0000
building
0.0235
0.9527
0.0187
0.0044
0.0006
0.0000
low_veg
0.0376
0.0153
0.8736
0.0735
0.0000
0.0000
tree
0.0150
0.0079
0.1145
0.8626
0.0000
0.0000
car
0.4034
0.0415
0.0494
0.0122
0.4935
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.913
0.944
0.862
0.866
0.839
--
Recall/Completeness
0.909
0.953
0.874
0.863
0.493
--
F1
0.911
0.948
0.868
0.865
0.621
--

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_area38_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9376
0.0273
0.0283
0.0051
0.0017
0.0000
building
0.0152
0.9751
0.0069
0.0023
0.0006
0.0000
low_veg
0.0237
0.0077
0.9128
0.0558
0.0000
0.0000
tree
0.0041
0.0036
0.0933
0.8990
0.0000
0.0000
car
0.3184
0.0488
0.0352
0.0054
0.5923
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.949
0.961
0.902
0.907
0.876
--
Recall/Completeness
0.938
0.975
0.913
0.899
0.592
--
F1
0.943
0.968
0.907
0.903
0.707
--

Overall accuracy 0.931

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image