Detailled semantic labeling (2D) result


Name X. Sun et al.
Affiliation NLPR, China
Abbreviation NLPR
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
0.890
0.036
0.045
0.019
0.011
0.000
building
0.080
0.892
0.010
0.015
0.003
0.000
low_veg
0.081
0.028
0.730
0.159
0.002
0.000
tree
0.019
0.008
0.097
0.876
0.000
0.000
car
0.414
0.062
0.013
0.007
0.504
0.000
clutter
0.581
0.254
0.027
0.008
0.130
0.000
Precision/Correctness
0.824
0.918
0.808
0.820
0.544
-nan
Recall/Completeness
0.890
0.892
0.730
0.876
0.504
0.000
F1
0.856
0.905
0.767
0.847
0.523
-nan

Overall accuracy 0.840

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
0.919
0.029
0.036
0.010
0.008
0.000
building
0.072
0.908
0.006
0.011
0.003
0.000
low_veg
0.071
0.018
0.766
0.143
0.002
0.000
tree
0.010
0.004
0.082
0.904
0.000
0.000
car
0.371
0.074
0.008
0.004
0.543
0.000
clutter
0.566
0.277
0.025
0.002
0.130
0.000
Precision/Correctness
0.849
0.939
0.842
0.851
0.544
-nan
Recall/Completeness
0.919
0.908
0.766
0.904
0.543
0.000
F1
0.883
0.923
0.802
0.876
0.543
-nan

Overall accuracy 0.869
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9402
0.0064
0.0311
0.0135
0.0088
0.0000
building
0.0525
0.9271
0.0135
0.0059
0.0010
0.0000
low_veg
0.1507
0.0190
0.7030
0.1258
0.0014
0.0000
tree
0.0274
0.0058
0.1051
0.8615
0.0002
0.0000
car
0.5077
0.0059
0.0037
0.0046
0.4782
0.0000
clutter
0.9852
0.0000
0.0019
0.0129
0.0000
0.0000
Precision/Correctness
0.742
0.965
0.823
0.856
0.724
-nan
Recall/Completeness
0.940
0.927
0.703
0.862
0.478
0.000
F1
0.829
0.946
0.758
0.859
0.576
-nan

Overall accuracy 0.836

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
0.9671
0.0030
0.0183
0.0049
0.0067
0.0000
building
0.0424
0.9463
0.0083
0.0023
0.0007
0.0000
low_veg
0.1407
0.0106
0.7311
0.1165
0.0012
0.0000
tree
0.0141
0.0031
0.0910
0.8917
0.0001
0.0000
car
0.4539
0.0068
0.0030
0.0023
0.5340
0.0000
clutter
0.9978
0.0000
0.0005
0.0017
0.0000
0.0000
Precision/Correctness
0.767
0.982
0.857
0.882
0.750
-nan
Recall/Completeness
0.967
0.946
0.731
0.892
0.534
0.000
F1
0.856
0.964
0.789
0.887
0.624
-nan

Overall accuracy 0.863

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area4_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9151
0.0636
0.0063
0.0063
0.0087
0.0000
building
0.0782
0.9137
0.0037
0.0043
0.0001
0.0000
low_veg
0.2956
0.0510
0.3319
0.3199
0.0015
0.0000
tree
0.0638
0.0157
0.0695
0.8507
0.0003
0.0000
car
0.5709
0.0438
0.0032
0.0015
0.3806
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.796
0.958
0.669
0.687
0.674
--
Recall/Completeness
0.915
0.914
0.332
0.851
0.381
--
F1
0.851
0.936
0.444
0.760
0.486
--

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_area4_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9404
0.0446
0.0050
0.0032
0.0068
0.0000
building
0.0628
0.9312
0.0030
0.0028
0.0001
0.0000
low_veg
0.2657
0.0251
0.3728
0.3348
0.0016
0.0000
tree
0.0368
0.0055
0.0687
0.8890
0.0000
0.0000
car
0.5416
0.0439
0.0020
0.0005
0.4119
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.829
0.974
0.698
0.723
0.689
--
Recall/Completeness
0.940
0.931
0.373
0.889
0.412
--
F1
0.881
0.952
0.486
0.797
0.515
--

Overall accuracy 0.903

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
0.8546
0.0776
0.0421
0.0118
0.0139
0.0000
building
0.0442
0.9295
0.0152
0.0103
0.0008
0.0000
low_veg
0.0567
0.0478
0.6452
0.2497
0.0007
0.0000
tree
0.0100
0.0050
0.0506
0.9344
0.0001
0.0000
car
0.4392
0.0479
0.0049
0.0025
0.5055
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.876
0.919
0.693
0.890
0.679
--
Recall/Completeness
0.855
0.929
0.645
0.934
0.506
--
F1
0.865
0.924
0.668
0.912
0.580
--

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_area6_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8950
0.0595
0.0314
0.0043
0.0099
0.0000
building
0.0359
0.9454
0.0121
0.0061
0.0006
0.0000
low_veg
0.0486
0.0338
0.6908
0.2263
0.0004
0.0000
tree
0.0032
0.0021
0.0395
0.9553
0.0000
0.0000
car
0.4053
0.0466
0.0031
0.0003
0.5446
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.907
0.944
0.739
0.918
0.713
--
Recall/Completeness
0.895
0.945
0.691
0.955
0.545
--
F1
0.901
0.945
0.714
0.937
0.617
--

Overall accuracy 0.906

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
0.8759
0.0588
0.0399
0.0136
0.0117
0.0000
building
0.0362
0.9467
0.0096
0.0067
0.0008
0.0000
low_veg
0.0786
0.0213
0.8401
0.0583
0.0017
0.0000
tree
0.0216
0.0123
0.0894
0.8767
0.0000
0.0000
car
0.3585
0.0643
0.0240
0.0063
0.5469
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.887
0.891
0.819
0.923
0.688
--
Recall/Completeness
0.876
0.947
0.840
0.877
0.547
--
F1
0.881
0.918
0.829
0.899
0.610
--

Overall accuracy 0.880

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
0.9058
0.0505
0.0303
0.0055
0.0080
0.0000
building
0.0266
0.9648
0.0042
0.0038
0.0005
0.0000
low_veg
0.0660
0.0119
0.8725
0.0483
0.0014
0.0000
tree
0.0093
0.0063
0.0724
0.9120
0.0000
0.0000
car
0.3133
0.0782
0.0143
0.0048
0.5893
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.918
0.918
0.858
0.948
0.722
--
Recall/Completeness
0.906
0.965
0.873
0.912
0.589
--
F1
0.912
0.941
0.865
0.930
0.649
--

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_area10_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8257
0.0742
0.0688
0.0220
0.0094
0.0000
building
0.0106
0.9587
0.0084
0.0195
0.0028
0.0000
low_veg
0.0541
0.0399
0.7425
0.1609
0.0026
0.0000
tree
0.0100
0.0078
0.0887
0.8935
0.0000
0.0000
car
0.3352
0.0832
0.0352
0.0093
0.5371
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.950
0.859
0.738
0.817
0.450
--
Recall/Completeness
0.826
0.959
0.742
0.893
0.537
--
F1
0.883
0.906
0.740
0.853
0.490
--

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_area10_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8643
0.0607
0.0567
0.0109
0.0074
0.0000
building
0.0063
0.9729
0.0045
0.0140
0.0023
0.0000
low_veg
0.0524
0.0295
0.7865
0.1291
0.0025
0.0000
tree
0.0051
0.0038
0.0690
0.9221
0.0000
0.0000
car
0.3153
0.0950
0.0301
0.0029
0.5566
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.962
0.888
0.783
0.862
0.435
--
Recall/Completeness
0.864
0.973
0.786
0.922
0.557
--
F1
0.911
0.929
0.785
0.891
0.488
--

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_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8428
0.0377
0.0695
0.0418
0.0082
0.0000
building
0.1733
0.8079
0.0072
0.0094
0.0023
0.0000
low_veg
0.0633
0.0369
0.6749
0.2221
0.0028
0.0000
tree
0.0084
0.0082
0.1102
0.8731
0.0001
0.0000
car
0.3493
0.0999
0.0044
0.0126
0.5338
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.680
0.887
0.790
0.817
0.526
--
Recall/Completeness
0.843
0.808
0.675
0.873
0.534
--
F1
0.753
0.846
0.728
0.844
0.530
--

Overall accuracy 0.797

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
0.8767
0.0340
0.0593
0.0246
0.0053
0.0000
building
0.1820
0.8096
0.0028
0.0032
0.0024
0.0000
low_veg
0.0632
0.0272
0.7080
0.1986
0.0029
0.0000
tree
0.0042
0.0046
0.0964
0.8948
0.0000
0.0000
car
0.2840
0.1304
0.0042
0.0078
0.5736
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.691
0.914
0.817
0.846
0.508
--
Recall/Completeness
0.877
0.810
0.708
0.895
0.574
--
F1
0.773
0.859
0.759
0.870
0.539
--

Overall accuracy 0.821

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
0.8408
0.0344
0.0803
0.0351
0.0094
0.0000
building
0.0126
0.9626
0.0137
0.0102
0.0008
0.0000
low_veg
0.0669
0.0644
0.7164
0.1497
0.0026
0.0000
tree
0.0210
0.0176
0.1336
0.8273
0.0004
0.0000
car
0.1599
0.0314
0.0165
0.0157
0.7765
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.878
0.848
0.735
0.852
0.402
--
Recall/Completeness
0.841
0.963
0.716
0.827
0.777
--
F1
0.859
0.902
0.726
0.840
0.529
--

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
0.8665
0.0297
0.0711
0.0248
0.0079
0.0000
building
0.0082
0.9783
0.0076
0.0053
0.0006
0.0000
low_veg
0.0632
0.0490
0.7497
0.1359
0.0024
0.0000
tree
0.0149
0.0107
0.1226
0.8515
0.0003
0.0000
car
0.0986
0.0385
0.0085
0.0117
0.8428
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.900
0.882
0.758
0.877
0.389
--
Recall/Completeness
0.867
0.978
0.750
0.851
0.843
--
F1
0.883
0.928
0.754
0.864
0.532
--

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_area16_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8058
0.0317
0.0877
0.0642
0.0105
0.0000
building
0.0217
0.9517
0.0098
0.0166
0.0003
0.0000
low_veg
0.0389
0.0243
0.7070
0.2266
0.0032
0.0000
tree
0.0212
0.0091
0.1133
0.8559
0.0005
0.0000
car
0.2382
0.0762
0.0783
0.0065
0.6009
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.840
0.915
0.786
0.797
0.325
--
Recall/Completeness
0.806
0.952
0.707
0.856
0.601
--
F1
0.823
0.933
0.744
0.825
0.422
--

Overall accuracy 0.820

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
0.8447
0.0259
0.0785
0.0423
0.0086
0.0000
building
0.0178
0.9710
0.0041
0.0071
0.0001
0.0000
low_veg
0.0358
0.0168
0.7293
0.2150
0.0032
0.0000
tree
0.0150
0.0053
0.1025
0.8768
0.0004
0.0000
car
0.2039
0.0951
0.0710
0.0001
0.6299
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.866
0.941
0.811
0.818
0.295
--
Recall/Completeness
0.845
0.971
0.729
0.877
0.630
--
F1
0.855
0.956
0.768
0.847
0.402
--

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_area20_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.7339
0.0507
0.1678
0.0410
0.0066
0.0000
building
0.0180
0.9304
0.0240
0.0274
0.0002
0.0000
low_veg
0.0343
0.0201
0.7522
0.1912
0.0023
0.0000
tree
0.0045
0.0013
0.0511
0.9431
0.0000
0.0000
car
0.1921
0.1816
0.0334
0.0173
0.5755
0.0000
clutter
0.0100
0.8371
0.1460
0.0012
0.0057
0.0000
Precision/Correctness
0.922
0.800
0.699
0.886
0.547
-nan
Recall/Completeness
0.734
0.930
0.752
0.943
0.576
0.000
F1
0.817
0.860
0.724
0.914
0.561
-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_area20_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.7680
0.0441
0.1598
0.0235
0.0046
0.0000
building
0.0166
0.9441
0.0188
0.0204
0.0001
0.0000
low_veg
0.0308
0.0115
0.7958
0.1595
0.0024
0.0000
tree
0.0017
0.0003
0.0378
0.9602
0.0000
0.0000
car
0.1541
0.2241
0.0157
0.0081
0.5980
0.0000
clutter
0.0034
0.8615
0.1288
0.0005
0.0058
0.0000
Precision/Correctness
0.941
0.813
0.729
0.914
0.530
-nan
Recall/Completeness
0.768
0.944
0.796
0.960
0.598
0.000
F1
0.846
0.874
0.761
0.937
0.562
-nan

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_area22_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8445
0.0371
0.0690
0.0384
0.0110
0.0000
building
0.0255
0.9472
0.0154
0.0117
0.0002
0.0000
low_veg
0.0825
0.0436
0.7005
0.1711
0.0023
0.0000
tree
0.0149
0.0050
0.0627
0.9174
0.0001
0.0000
car
0.5071
0.0477
0.0406
0.0146
0.3900
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.897
0.882
0.766
0.844
0.514
--
Recall/Completeness
0.845
0.947
0.701
0.917
0.390
--
F1
0.870
0.913
0.732
0.879
0.443
--

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_area22_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8814
0.0294
0.0592
0.0210
0.0090
0.0000
building
0.0216
0.9625
0.0104
0.0054
0.0001
0.0000
low_veg
0.0823
0.0300
0.7441
0.1413
0.0024
0.0000
tree
0.0064
0.0022
0.0472
0.9442
0.0000
0.0000
car
0.4888
0.0608
0.0284
0.0062
0.4159
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.917
0.914
0.806
0.884
0.496
--
Recall/Completeness
0.881
0.962
0.744
0.944
0.416
--
F1
0.899
0.937
0.774
0.913
0.452
--

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_area24_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.7402
0.0518
0.1584
0.0309
0.0188
0.0000
building
0.0522
0.9040
0.0156
0.0273
0.0010
0.0000
low_veg
0.0262
0.0238
0.8425
0.1061
0.0015
0.0000
tree
0.0101
0.0110
0.1738
0.8046
0.0005
0.0000
car
0.2195
0.0029
0.0309
0.0056
0.7412
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.818
0.894
0.831
0.793
0.433
--
Recall/Completeness
0.740
0.904
0.842
0.805
0.741
--
F1
0.777
0.899
0.837
0.799
0.546
--

Overall accuracy 0.829

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
0.7774
0.0410
0.1453
0.0203
0.0160
0.0000
building
0.0506
0.9150
0.0105
0.0230
0.0009
0.0000
low_veg
0.0240
0.0185
0.8615
0.0945
0.0015
0.0000
tree
0.0060
0.0071
0.1557
0.8307
0.0004
0.0000
car
0.1933
0.0021
0.0153
0.0015
0.7879
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.837
0.919
0.854
0.816
0.400
--
Recall/Completeness
0.777
0.915
0.862
0.831
0.788
--
F1
0.806
0.917
0.858
0.823
0.531
--

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_area27_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9377
0.0238
0.0147
0.0072
0.0165
0.0000
building
0.0810
0.9003
0.0049
0.0131
0.0007
0.0000
low_veg
0.1480
0.0313
0.6490
0.1686
0.0031
0.0000
tree
0.0154
0.0072
0.0452
0.9322
0.0000
0.0000
car
0.4171
0.0110
0.0077
0.0067
0.5576
0.0000
clutter
0.5390
0.1104
0.0455
0.0150
0.2901
0.0000
Precision/Correctness
0.803
0.954
0.918
0.699
0.726
-nan
Recall/Completeness
0.938
0.900
0.649
0.932
0.558
0.000
F1
0.865
0.926
0.760
0.799
0.631
-nan

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_area27_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9649
0.0147
0.0088
0.0029
0.0088
0.0000
building
0.0674
0.9204
0.0021
0.0097
0.0004
0.0000
low_veg
0.1327
0.0188
0.6949
0.1507
0.0029
0.0000
tree
0.0064
0.0035
0.0322
0.9580
0.0000
0.0000
car
0.3780
0.0099
0.0060
0.0052
0.6010
0.0000
clutter
0.5526
0.1054
0.0292
0.0074
0.3055
0.0000
Precision/Correctness
0.835
0.974
0.950
0.739
0.783
-nan
Recall/Completeness
0.965
0.920
0.695
0.958
0.601
0.000
F1
0.895
0.946
0.803
0.834
0.680
-nan

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_area29_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9461
0.0176
0.0147
0.0123
0.0093
0.0000
building
0.0622
0.9017
0.0030
0.0080
0.0251
0.0000
low_veg
0.0942
0.0272
0.5993
0.2782
0.0011
0.0000
tree
0.0108
0.0042
0.0257
0.9594
0.0000
0.0000
car
0.4930
0.0051
0.0052
0.0123
0.4846
0.0000
clutter
0.6172
0.1934
0.0138
0.0134
0.1623
0.0000
Precision/Correctness
0.876
0.932
0.896
0.681
0.292
-nan
Recall/Completeness
0.946
0.902
0.599
0.959
0.485
0.000
F1
0.910
0.917
0.718
0.797
0.365
-nan

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_area29_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9670
0.0118
0.0088
0.0055
0.0068
0.0000
building
0.0562
0.9133
0.0008
0.0039
0.0258
0.0000
low_veg
0.0750
0.0132
0.6492
0.2619
0.0007
0.0000
tree
0.0055
0.0020
0.0190
0.9735
0.0000
0.0000
car
0.4654
0.0028
0.0058
0.0093
0.5167
0.0000
clutter
0.6104
0.2022
0.0113
0.0042
0.1719
0.0000
Precision/Correctness
0.897
0.953
0.933
0.724
0.262
-nan
Recall/Completeness
0.967
0.913
0.649
0.973
0.517
0.000
F1
0.931
0.933
0.766
0.830
0.347
-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_area31_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9708
0.0095
0.0052
0.0042
0.0103
0.0000
building
0.3170
0.6636
0.0034
0.0050
0.0110
0.0000
low_veg
0.0884
0.0052
0.8695
0.0354
0.0015
0.0000
tree
0.0478
0.0027
0.0604
0.8889
0.0001
0.0000
car
0.3073
0.2022
0.0062
0.0100
0.4742
0.0000
clutter
0.5550
0.3143
0.0056
0.0121
0.1130
0.0000
Precision/Correctness
0.735
0.890
0.927
0.918
0.606
-nan
Recall/Completeness
0.971
0.664
0.869
0.889
0.474
0.000
F1
0.837
0.760
0.897
0.903
0.532
-nan

Overall accuracy 0.811

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
0.9832
0.0070
0.0031
0.0011
0.0056
0.0000
building
0.3123
0.6748
0.0011
0.0017
0.0101
0.0000
low_veg
0.0647
0.0030
0.9046
0.0265
0.0012
0.0000
tree
0.0243
0.0005
0.0457
0.9294
0.0001
0.0000
car
0.2464
0.2438
0.0022
0.0037
0.5038
0.0000
clutter
0.5136
0.3622
0.0054
0.0054
0.1134
0.0000
Precision/Correctness
0.753
0.902
0.952
0.952
0.624
-nan
Recall/Completeness
0.983
0.675
0.905
0.929
0.504
0.000
F1
0.853
0.772
0.928
0.941
0.558
-nan

Overall accuracy 0.832

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
0.9764
0.0075
0.0058
0.0028
0.0075
0.0000
building
0.2504
0.6773
0.0099
0.0589
0.0035
0.0000
low_veg
0.1033
0.0176
0.7352
0.1418
0.0021
0.0000
tree
0.0446
0.0074
0.1624
0.7854
0.0001
0.0000
car
0.5479
0.0001
0.0057
0.0011
0.4451
0.0000
clutter
0.6559
0.0911
0.0022
0.0014
0.2493
0.0000
Precision/Correctness
0.735
0.946
0.835
0.673
0.244
-nan
Recall/Completeness
0.976
0.677
0.735
0.785
0.445
0.000
F1
0.839
0.789
0.782
0.725
0.315
-nan

Overall accuracy 0.773

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
0.9871
0.0053
0.0021
0.0008
0.0047
0.0000
building
0.2472
0.6832
0.0079
0.0585
0.0031
0.0000
low_veg
0.0710
0.0120
0.7650
0.1505
0.0014
0.0000
tree
0.0210
0.0035
0.1520
0.8235
0.0000
0.0000
car
0.5153
0.0000
0.0032
0.0002
0.4813
0.0000
clutter
0.6396
0.0967
0.0012
0.0004
0.2622
0.0000
Precision/Correctness
0.753
0.958
0.860
0.675
0.229
-nan
Recall/Completeness
0.987
0.683
0.765
0.823
0.481
0.000
F1
0.855
0.798
0.810
0.742
0.311
-nan

Overall accuracy 0.791

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
0.8739
0.0399
0.0564
0.0208
0.0090
0.0000
building
0.0666
0.9134
0.0102
0.0074
0.0024
0.0000
low_veg
0.0817
0.0149
0.7014
0.2004
0.0016
0.0000
tree
0.0272
0.0055
0.1400
0.8271
0.0002
0.0000
car
0.4426
0.0770
0.0009
0.0094
0.4700
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.821
0.940
0.778
0.773
0.514
--
Recall/Completeness
0.874
0.913
0.701
0.827
0.470
--
F1
0.847
0.926
0.738
0.799
0.491
--

Overall accuracy 0.828

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
0.9174
0.0356
0.0323
0.0072
0.0075
0.0000
building
0.0516
0.9403
0.0038
0.0026
0.0017
0.0000
low_veg
0.0669
0.0076
0.7325
0.1917
0.0013
0.0000
tree
0.0104
0.0013
0.1127
0.8755
0.0001
0.0000
car
0.3831
0.0992
0.0007
0.0029
0.5141
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.864
0.958
0.838
0.802
0.530
--
Recall/Completeness
0.917
0.940
0.733
0.875
0.514
--
F1
0.890
0.949
0.782
0.837
0.522
--

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_area38_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9053
0.0307
0.0357
0.0183
0.0100
0.0000
building
0.0263
0.9269
0.0162
0.0279
0.0028
0.0000
low_veg
0.0828
0.0169
0.7707
0.1273
0.0022
0.0000
tree
0.0233
0.0059
0.1054
0.8652
0.0002
0.0000
car
0.4049
0.0346
0.0256
0.0078
0.5271
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.864
0.942
0.862
0.780
0.557
--
Recall/Completeness
0.905
0.927
0.771
0.865
0.527
--
F1
0.884
0.934
0.814
0.820
0.542
--

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_area38_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9344
0.0281
0.0221
0.0073
0.0081
0.0000
building
0.0170
0.9503
0.0101
0.0207
0.0018
0.0000
low_veg
0.0737
0.0101
0.8062
0.1080
0.0020
0.0000
tree
0.0138
0.0026
0.0851
0.8985
0.0001
0.0000
car
0.3585
0.0403
0.0159
0.0022
0.5830
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.893
0.958
0.900
0.821
0.569
--
Recall/Completeness
0.934
0.950
0.806
0.898
0.583
--
F1
0.913
0.954
0.850
0.858
0.576
--

Overall accuracy 0.894

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image