Detailled semantic labeling (2D) result


Name X. Sun et al.
Affiliation NLPR, China
Abbreviation NLPR2
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
0.912
0.033
0.039
0.015
0.002
0.000
building
0.040
0.937
0.018
0.004
0.000
0.000
low_veg
0.052
0.024
0.791
0.133
0.000
0.000
tree
0.023
0.006
0.086
0.885
0.000
0.000
car
0.354
0.044
0.008
0.005
0.589
0.000
clutter
0.359
0.285
0.010
0.007
0.008
0.331
Precision/Correctness
0.880
0.929
0.830
0.855
0.896
0.968
Recall/Completeness
0.912
0.937
0.791
0.885
0.589
0.331
F1
0.896
0.933
0.810
0.870
0.710
0.493

Overall accuracy 0.877

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
0.936
0.025
0.031
0.007
0.001
0.000
building
0.032
0.955
0.012
0.002
0.000
0.000
low_veg
0.039
0.014
0.830
0.118
0.000
0.000
tree
0.010
0.002
0.070
0.918
0.000
0.000
car
0.224
0.050
0.005
0.003
0.718
0.000
clutter
0.315
0.301
0.008
0.002
0.009
0.365
Precision/Correctness
0.916
0.950
0.865
0.883
0.930
0.980
Recall/Completeness
0.936
0.955
0.830
0.918
0.718
0.365
F1
0.926
0.953
0.847
0.900
0.810
0.532

Overall accuracy 0.907
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9551
0.0132
0.0195
0.0091
0.0031
0.0000
building
0.0388
0.9411
0.0173
0.0028
0.0000
0.0000
low_veg
0.0723
0.0160
0.7524
0.1593
0.0000
0.0000
tree
0.0342
0.0037
0.1030
0.8573
0.0001
0.0017
car
0.4001
0.0008
0.0012
0.0017
0.5962
0.0000
clutter
0.0000
0.0000
0.0000
0.0098
0.0000
0.9902
Precision/Correctness
0.853
0.964
0.843
0.834
0.921
0.978
Recall/Completeness
0.955
0.941
0.752
0.857
0.596
0.990
F1
0.901
0.952
0.795
0.846
0.724
0.984

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_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9753
0.0091
0.0104
0.0028
0.0024
0.0000
building
0.0307
0.9600
0.0088
0.0005
0.0000
0.0000
low_veg
0.0503
0.0071
0.7884
0.1543
0.0000
0.0000
tree
0.0166
0.0008
0.0884
0.8934
0.0000
0.0008
car
0.2422
0.0000
0.0005
0.0005
0.7569
0.0000
clutter
0.0000
0.0000
0.0000
0.0019
0.0000
0.9981
Precision/Correctness
0.901
0.982
0.876
0.855
0.938
0.990
Recall/Completeness
0.975
0.960
0.788
0.893
0.757
0.998
F1
0.937
0.971
0.830
0.874
0.838
0.994

Overall accuracy 0.905

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
0.9421
0.0447
0.0089
0.0029
0.0014
0.0000
building
0.0521
0.9415
0.0056
0.0007
0.0001
0.0000
low_veg
0.1416
0.0755
0.5199
0.2620
0.0010
0.0000
tree
0.0613
0.0206
0.0565
0.8616
0.0001
0.0000
car
0.4567
0.0211
0.0002
0.0026
0.5193
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.859
0.968
0.733
0.762
0.934
--
Recall/Completeness
0.942
0.941
0.520
0.862
0.519
--
F1
0.899
0.954
0.608
0.808
0.667
--

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_area4_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9676
0.0243
0.0069
0.0008
0.0005
0.0000
building
0.0381
0.9570
0.0046
0.0002
0.0001
0.0000
low_veg
0.0997
0.0425
0.5641
0.2931
0.0006
0.0000
tree
0.0280
0.0071
0.0493
0.9156
0.0000
0.0000
car
0.3365
0.0141
0.0000
0.0012
0.6482
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.898
0.984
0.763
0.781
0.969
--
Recall/Completeness
0.968
0.957
0.564
0.916
0.648
--
F1
0.931
0.970
0.649
0.843
0.777
--

Overall accuracy 0.938

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
0.9078
0.0507
0.0321
0.0067
0.0027
0.0000
building
0.0393
0.9458
0.0127
0.0021
0.0001
0.0000
low_veg
0.0877
0.0207
0.7375
0.1539
0.0001
0.0000
tree
0.0167
0.0049
0.0583
0.9200
0.0001
0.0000
car
0.3983
0.0200
0.0002
0.0016
0.5799
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.873
0.949
0.729
0.934
0.925
--
Recall/Completeness
0.908
0.946
0.737
0.920
0.580
--
F1
0.890
0.947
0.733
0.927
0.713
--

Overall accuracy 0.900

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
0.9396
0.0348
0.0228
0.0018
0.0009
0.0000
building
0.0297
0.9622
0.0077
0.0003
0.0000
0.0000
low_veg
0.0703
0.0054
0.7862
0.1381
0.0000
0.0000
tree
0.0050
0.0012
0.0451
0.9487
0.0000
0.0000
car
0.2710
0.0192
0.0000
0.0000
0.7098
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.915
0.971
0.779
0.953
0.974
--
Recall/Completeness
0.940
0.962
0.786
0.949
0.710
--
F1
0.927
0.967
0.782
0.951
0.821
--

Overall accuracy 0.932

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
0.9050
0.0250
0.0628
0.0058
0.0014
0.0000
building
0.0304
0.9532
0.0138
0.0026
0.0000
0.0000
low_veg
0.0504
0.0142
0.8997
0.0356
0.0002
0.0000
tree
0.0302
0.0076
0.1022
0.8600
0.0000
0.0000
car
0.3915
0.0086
0.0140
0.0022
0.5837
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.902
0.946
0.788
0.956
0.953
--
Recall/Completeness
0.905
0.953
0.900
0.860
0.584
--
F1
0.904
0.950
0.840
0.905
0.724
--

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_area8_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9287
0.0165
0.0528
0.0014
0.0006
0.0000
building
0.0205
0.9720
0.0067
0.0009
0.0000
0.0000
low_veg
0.0325
0.0058
0.9348
0.0269
0.0000
0.0000
tree
0.0123
0.0035
0.0789
0.9052
0.0000
0.0000
car
0.2563
0.0065
0.0065
0.0012
0.7295
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.943
0.970
0.830
0.974
0.979
--
Recall/Completeness
0.929
0.972
0.935
0.905
0.729
--
F1
0.936
0.971
0.879
0.938
0.836
--

Overall accuracy 0.932

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
0.8707
0.0659
0.0443
0.0163
0.0028
0.0000
building
0.0356
0.9384
0.0153
0.0101
0.0006
0.0000
low_veg
0.0696
0.0389
0.7323
0.1592
0.0000
0.0000
tree
0.0173
0.0081
0.0707
0.9039
0.0000
0.0000
car
0.3908
0.0236
0.0023
0.0034
0.5800
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.924
0.869
0.787
0.836
0.776
--
Recall/Completeness
0.871
0.938
0.732
0.904
0.580
--
F1
0.896
0.902
0.759
0.869
0.664
--

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_area10_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9005
0.0534
0.0372
0.0064
0.0025
0.0000
building
0.0287
0.9527
0.0108
0.0072
0.0005
0.0000
low_veg
0.0648
0.0259
0.7783
0.1310
0.0000
0.0000
tree
0.0062
0.0036
0.0526
0.9376
0.0000
0.0000
car
0.2534
0.0325
0.0002
0.0005
0.7134
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.944
0.899
0.828
0.877
0.775
--
Recall/Completeness
0.900
0.953
0.778
0.938
0.713
--
F1
0.922
0.925
0.802
0.906
0.743
--

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_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8692
0.0460
0.0536
0.0303
0.0009
0.0000
building
0.0804
0.9047
0.0082
0.0068
0.0000
0.0000
low_veg
0.0282
0.0267
0.7739
0.1700
0.0001
0.0012
tree
0.0091
0.0069
0.0772
0.9068
0.0000
0.0000
car
0.3723
0.0041
0.0010
0.0067
0.6158
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.811
0.911
0.856
0.859
0.957
--
Recall/Completeness
0.869
0.905
0.774
0.907
0.616
--
F1
0.839
0.908
0.813
0.882
0.749
--

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_area12_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8971
0.0427
0.0446
0.0153
0.0002
0.0000
building
0.0821
0.9133
0.0026
0.0020
0.0000
0.0000
low_veg
0.0255
0.0158
0.8126
0.1448
0.0000
0.0013
tree
0.0040
0.0025
0.0609
0.9325
0.0000
0.0000
car
0.2093
0.0016
0.0000
0.0005
0.7886
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.834
0.939
0.886
0.888
0.990
--
Recall/Completeness
0.897
0.913
0.813
0.933
0.789
--
F1
0.865
0.926
0.848
0.910
0.878
--

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_area14_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8441
0.0280
0.0966
0.0277
0.0035
0.0000
building
0.0069
0.9756
0.0120
0.0055
0.0000
0.0000
low_veg
0.0856
0.0510
0.7141
0.1492
0.0002
0.0000
tree
0.0256
0.0135
0.1169
0.8439
0.0000
0.0000
car
0.2388
0.0000
0.0000
0.0085
0.7527
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.858
0.878
0.741
0.862
0.696
--
Recall/Completeness
0.844
0.976
0.714
0.844
0.753
--
F1
0.851
0.924
0.727
0.853
0.723
--

Overall accuracy 0.834

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
0.8620
0.0229
0.0938
0.0181
0.0031
0.0000
building
0.0026
0.9906
0.0053
0.0015
0.0000
0.0000
low_veg
0.0806
0.0337
0.7467
0.1388
0.0002
0.0000
tree
0.0171
0.0062
0.1040
0.8726
0.0000
0.0000
car
0.0965
0.0000
0.0000
0.0039
0.8996
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.884
0.916
0.762
0.883
0.693
--
Recall/Completeness
0.862
0.991
0.747
0.873
0.900
--
F1
0.873
0.952
0.754
0.878
0.783
--

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_area16_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8009
0.0401
0.1029
0.0545
0.0016
0.0000
building
0.0255
0.9403
0.0222
0.0120
0.0000
0.0000
low_veg
0.0125
0.0157
0.8548
0.1170
0.0000
0.0000
tree
0.0199
0.0056
0.0955
0.8791
0.0000
0.0000
car
0.2441
0.0036
0.0012
0.0089
0.7422
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.885
0.928
0.822
0.877
0.871
--
Recall/Completeness
0.801
0.940
0.855
0.879
0.742
--
F1
0.841
0.934
0.838
0.878
0.802
--

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_area16_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8348
0.0352
0.0962
0.0332
0.0006
0.0000
building
0.0217
0.9618
0.0121
0.0045
0.0000
0.0000
low_veg
0.0091
0.0092
0.8803
0.1014
0.0000
0.0000
tree
0.0126
0.0019
0.0810
0.9046
0.0000
0.0000
car
0.1361
0.0003
0.0001
0.0010
0.8625
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.917
0.952
0.849
0.903
0.934
--
Recall/Completeness
0.835
0.962
0.880
0.905
0.862
--
F1
0.874
0.957
0.864
0.904
0.897
--

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_area20_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8743
0.0376
0.0412
0.0454
0.0015
0.0000
building
0.0166
0.9546
0.0220
0.0068
0.0000
0.0000
low_veg
0.0408
0.0382
0.7522
0.1689
0.0000
0.0000
tree
0.0093
0.0025
0.0425
0.9458
0.0000
0.0000
car
0.2104
0.0470
0.0161
0.0181
0.7084
0.0000
clutter
0.0022
0.9966
0.0005
0.0006
0.0000
0.0000
Precision/Correctness
0.920
0.784
0.832
0.900
0.904
-nan
Recall/Completeness
0.874
0.955
0.752
0.946
0.708
0.000
F1
0.896
0.861
0.790
0.922
0.794
-nan

Overall accuracy 0.869

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
0.9043
0.0284
0.0390
0.0274
0.0009
0.0000
building
0.0132
0.9658
0.0192
0.0018
0.0000
0.0000
low_veg
0.0339
0.0248
0.8015
0.1398
0.0000
0.0000
tree
0.0041
0.0005
0.0310
0.9644
0.0000
0.0000
car
0.0867
0.0546
0.0036
0.0101
0.8450
0.0000
clutter
0.0003
0.9997
0.0000
0.0000
0.0000
0.0000
Precision/Correctness
0.946
0.805
0.860
0.927
0.935
-nan
Recall/Completeness
0.904
0.966
0.802
0.964
0.845
0.000
F1
0.925
0.878
0.830
0.945
0.888
-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_area22_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9029
0.0281
0.0373
0.0283
0.0034
0.0000
building
0.0329
0.9524
0.0085
0.0061
0.0001
0.0000
low_veg
0.0778
0.0426
0.7389
0.1406
0.0000
0.0000
tree
0.0235
0.0045
0.0551
0.9168
0.0001
0.0000
car
0.3740
0.0000
0.0102
0.0164
0.5990
0.0003
clutter
--
--
--
--
--
--
Precision/Correctness
0.899
0.900
0.835
0.872
0.852
--
Recall/Completeness
0.903
0.952
0.739
0.917
0.599
--
F1
0.901
0.925
0.784
0.894
0.704
--

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
0.9319
0.0205
0.0316
0.0137
0.0023
0.0000
building
0.0253
0.9689
0.0032
0.0026
0.0000
0.0000
low_veg
0.0733
0.0270
0.7879
0.1119
0.0000
0.0000
tree
0.0095
0.0013
0.0396
0.9495
0.0000
0.0000
car
0.2462
0.0000
0.0062
0.0077
0.7394
0.0005
clutter
--
--
--
--
--
--
Precision/Correctness
0.927
0.935
0.874
0.910
0.886
--
Recall/Completeness
0.932
0.969
0.788
0.950
0.739
--
F1
0.930
0.952
0.829
0.930
0.806
--

Overall accuracy 0.914

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
0.8298
0.0366
0.0951
0.0352
0.0033
0.0000
building
0.0646
0.8900
0.0366
0.0087
0.0000
0.0000
low_veg
0.0170
0.0196
0.8817
0.0815
0.0001
0.0000
tree
0.0184
0.0067
0.1314
0.8435
0.0000
0.0000
car
0.3008
0.0000
0.0015
0.0008
0.6969
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.829
0.917
0.870
0.842
0.829
--
Recall/Completeness
0.830
0.890
0.882
0.844
0.697
--
F1
0.829
0.903
0.876
0.843
0.757
--

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_area24_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8594
0.0260
0.0870
0.0255
0.0021
0.0000
building
0.0625
0.9016
0.0304
0.0055
0.0000
0.0000
low_veg
0.0135
0.0144
0.9028
0.0692
0.0002
0.0000
tree
0.0116
0.0025
0.1108
0.8750
0.0000
0.0000
car
0.1523
0.0000
0.0000
0.0000
0.8477
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.855
0.943
0.891
0.867
0.861
--
Recall/Completeness
0.859
0.902
0.903
0.875
0.848
--
F1
0.857
0.922
0.897
0.871
0.854
--

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_area27_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9426
0.0298
0.0182
0.0056
0.0038
0.0000
building
0.0610
0.9246
0.0114
0.0029
0.0001
0.0000
low_veg
0.0900
0.0282
0.6897
0.1920
0.0001
0.0000
tree
0.0160
0.0066
0.0383
0.9391
0.0000
0.0000
car
0.4233
0.0145
0.0078
0.0049
0.5494
0.0000
clutter
0.5263
0.2892
0.1395
0.0034
0.0415
0.0000
Precision/Correctness
0.844
0.950
0.905
0.699
0.928
-nan
Recall/Completeness
0.943
0.925
0.690
0.939
0.549
0.000
F1
0.891
0.937
0.783
0.801
0.690
-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_area27_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9655
0.0195
0.0120
0.0020
0.0010
0.0000
building
0.0495
0.9430
0.0065
0.0009
0.0001
0.0000
low_veg
0.0685
0.0139
0.7357
0.1820
0.0000
0.0000
tree
0.0070
0.0021
0.0251
0.9657
0.0000
0.0000
car
0.2993
0.0148
0.0060
0.0039
0.6760
0.0000
clutter
0.5563
0.2713
0.1205
0.0010
0.0509
0.0000
Precision/Correctness
0.884
0.972
0.939
0.727
0.973
-nan
Recall/Completeness
0.965
0.943
0.736
0.966
0.676
0.000
F1
0.923
0.957
0.825
0.829
0.798
-nan

Overall accuracy 0.905

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
0.9437
0.0185
0.0235
0.0118
0.0025
0.0000
building
0.0204
0.9621
0.0109
0.0066
0.0000
0.0000
low_veg
0.0607
0.0219
0.6329
0.2844
0.0001
0.0000
tree
0.0058
0.0029
0.0201
0.9712
0.0000
0.0000
car
0.3543
0.0079
0.0066
0.0115
0.6197
0.0000
clutter
0.4606
0.4111
0.0183
0.0081
0.0154
0.0865
Precision/Correctness
0.923
0.917
0.856
0.683
0.844
0.994
Recall/Completeness
0.944
0.962
0.633
0.971
0.620
0.086
F1
0.933
0.939
0.728
0.802
0.715
0.159

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_area29_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9641
0.0118
0.0169
0.0053
0.0019
0.0000
building
0.0142
0.9768
0.0056
0.0033
0.0000
0.0000
low_veg
0.0370
0.0087
0.6809
0.2734
0.0000
0.0000
tree
0.0015
0.0007
0.0129
0.9850
0.0000
0.0000
car
0.2308
0.0080
0.0074
0.0090
0.7449
0.0000
clutter
0.4246
0.4417
0.0114
0.0021
0.0174
0.1029
Precision/Correctness
0.948
0.937
0.898
0.720
0.857
0.999
Recall/Completeness
0.964
0.977
0.681
0.985
0.745
0.103
F1
0.956
0.957
0.774
0.832
0.797
0.187

Overall accuracy 0.905

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
0.9722
0.0112
0.0076
0.0038
0.0050
0.0003
building
0.0405
0.9494
0.0056
0.0026
0.0017
0.0002
low_veg
0.0496
0.0072
0.9034
0.0387
0.0002
0.0010
tree
0.0394
0.0030
0.0600
0.8968
0.0008
0.0000
car
0.2125
0.1855
0.0035
0.0051
0.5933
0.0000
clutter
0.5206
0.2228
0.0165
0.0145
0.0144
0.2112
Precision/Correctness
0.887
0.929
0.918
0.922
0.877
0.957
Recall/Completeness
0.972
0.949
0.903
0.897
0.593
0.211
F1
0.928
0.939
0.911
0.909
0.708
0.346

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_area31_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9843
0.0080
0.0049
0.0009
0.0019
0.0001
building
0.0273
0.9695
0.0013
0.0003
0.0014
0.0002
low_veg
0.0292
0.0035
0.9356
0.0313
0.0000
0.0004
tree
0.0115
0.0003
0.0431
0.9450
0.0001
0.0000
car
0.1076
0.2110
0.0006
0.0014
0.6794
0.0000
clutter
0.4711
0.2467
0.0165
0.0060
0.0169
0.2428
Precision/Correctness
0.926
0.942
0.949
0.951
0.921
0.980
Recall/Completeness
0.984
0.969
0.936
0.945
0.679
0.243
F1
0.954
0.956
0.942
0.948
0.782
0.389

Overall accuracy 0.937

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
0.9681
0.0228
0.0065
0.0013
0.0006
0.0006
building
0.0638
0.8649
0.0668
0.0037
0.0001
0.0007
low_veg
0.0615
0.0101
0.9007
0.0274
0.0003
0.0000
tree
0.0532
0.0054
0.1302
0.8112
0.0000
0.0000
car
0.3172
0.0856
0.0015
0.0029
0.5927
0.0000
clutter
0.5474
0.0284
0.0016
0.0024
0.0061
0.4140
Precision/Correctness
0.847
0.949
0.796
0.934
0.920
0.981
Recall/Completeness
0.968
0.865
0.901
0.811
0.593
0.414
F1
0.904
0.905
0.845
0.868
0.721
0.582

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_area33_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9778
0.0191
0.0025
0.0002
0.0003
0.0001
building
0.0550
0.8783
0.0645
0.0015
0.0001
0.0006
low_veg
0.0299
0.0058
0.9392
0.0249
0.0002
0.0000
tree
0.0231
0.0008
0.1186
0.8575
0.0000
0.0000
car
0.1704
0.0821
0.0000
0.0009
0.7466
0.0000
clutter
0.5024
0.0241
0.0010
0.0010
0.0069
0.4647
Precision/Correctness
0.882
0.962
0.814
0.953
0.934
0.991
Recall/Completeness
0.978
0.878
0.939
0.857
0.747
0.465
F1
0.928
0.918
0.872
0.903
0.830
0.633

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_area35_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8824
0.0475
0.0583
0.0113
0.0005
0.0000
building
0.0334
0.9502
0.0137
0.0027
0.0000
0.0000
low_veg
0.0582
0.0119
0.7387
0.1912
0.0001
0.0000
tree
0.0401
0.0076
0.1170
0.8351
0.0001
0.0000
car
0.4068
0.0096
0.0000
0.0080
0.5757
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.861
0.938
0.800
0.793
0.963
--
Recall/Completeness
0.882
0.950
0.739
0.835
0.576
--
F1
0.871
0.944
0.768
0.813
0.721
--

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_area35_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9175
0.0427
0.0379
0.0019
0.0000
0.0000
building
0.0224
0.9721
0.0052
0.0003
0.0000
0.0000
low_veg
0.0392
0.0040
0.7686
0.1882
0.0000
0.0000
tree
0.0132
0.0024
0.0888
0.8955
0.0000
0.0000
car
0.2683
0.0049
0.0000
0.0028
0.7239
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.917
0.958
0.858
0.814
0.997
--
Recall/Completeness
0.918
0.972
0.769
0.896
0.724
--
F1
0.917
0.965
0.811
0.853
0.839
--

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_area38_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9000
0.0360
0.0491
0.0131
0.0016
0.0002
building
0.0213
0.9408
0.0329
0.0038
0.0012
0.0000
low_veg
0.0344
0.0157
0.8625
0.0872
0.0003
0.0000
tree
0.0229
0.0040
0.1138
0.8593
0.0000
0.0000
car
0.3078
0.0306
0.0454
0.0078
0.6084
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.915
0.940
0.845
0.853
0.876
--
Recall/Completeness
0.900
0.941
0.862
0.859
0.608
--
F1
0.907
0.941
0.854
0.856
0.718
--

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
0.9271
0.0333
0.0345
0.0043
0.0005
0.0003
building
0.0141
0.9655
0.0184
0.0011
0.0010
0.0000
low_veg
0.0188
0.0100
0.8997
0.0713
0.0002
0.0000
tree
0.0074
0.0008
0.0917
0.9001
0.0000
0.0000
car
0.1839
0.0332
0.0347
0.0025
0.7457
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.955
0.955
0.887
0.890
0.923
--
Recall/Completeness
0.927
0.965
0.900
0.900
0.746
--
F1
0.941
0.960
0.893
0.895
0.825
--

Overall accuracy 0.923

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image