Detailled semantic labeling (2D) result


Name X. Pan et al.
Affiliation Chinese Academy of Sciences, Institute for Remote Sensing and Digital Earth, China
Abbreviation CASRS2
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
0.915
0.028
0.039
0.016
0.002
0.000
building
0.070
0.894
0.031
0.005
0.001
0.000
low_veg
0.066
0.024
0.773
0.136
0.000
0.000
tree
0.024
0.005
0.104
0.867
0.000
0.000
car
0.406
0.028
0.012
0.005
0.548
0.000
clutter
0.494
0.256
0.011
0.012
0.013
0.214
Precision/Correctness
0.842
0.932
0.797
0.848
0.889
0.977
Recall/Completeness
0.915
0.894
0.773
0.867
0.548
0.214
F1
0.877
0.913
0.785
0.857
0.678
0.352

Overall accuracy 0.857

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
0.938
0.022
0.031
0.008
0.001
0.000
building
0.060
0.914
0.023
0.002
0.000
0.000
low_veg
0.052
0.017
0.808
0.122
0.000
0.000
tree
0.011
0.002
0.086
0.900
0.000
0.000
car
0.298
0.033
0.010
0.003
0.657
0.000
clutter
0.460
0.273
0.008
0.005
0.014
0.240
Precision/Correctness
0.877
0.950
0.833
0.877
0.920
0.985
Recall/Completeness
0.938
0.914
0.808
0.900
0.657
0.240
F1
0.906
0.932
0.820
0.888
0.766
0.385

Overall accuracy 0.887
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9517
0.0110
0.0234
0.0114
0.0025
0.0000
building
0.0810
0.8893
0.0268
0.0026
0.0003
0.0000
low_veg
0.0798
0.0165
0.7425
0.1612
0.0000
0.0000
tree
0.0317
0.0070
0.1066
0.8538
0.0000
0.0009
car
0.4173
0.0235
0.0000
0.0019
0.5574
0.0000
clutter
0.0213
0.0000
0.0000
0.0224
0.0000
0.9563
Precision/Correctness
0.819
0.958
0.826
0.830
0.925
0.988
Recall/Completeness
0.952
0.889
0.743
0.854
0.557
0.956
F1
0.880
0.923
0.782
0.841
0.696
0.972

Overall accuracy 0.857

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
0.9730
0.0085
0.0139
0.0030
0.0016
0.0000
building
0.0731
0.9078
0.0183
0.0004
0.0003
0.0000
low_veg
0.0596
0.0075
0.7787
0.1542
0.0000
0.0000
tree
0.0153
0.0037
0.0934
0.8874
0.0000
0.0003
car
0.2918
0.0264
0.0000
0.0006
0.6813
0.0000
clutter
0.0218
0.0000
0.0000
0.0069
0.0000
0.9713
Precision/Correctness
0.859
0.977
0.857
0.854
0.946
0.996
Recall/Completeness
0.973
0.908
0.779
0.887
0.681
0.971
F1
0.913
0.941
0.816
0.870
0.792
0.983

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_area4_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9278
0.0575
0.0088
0.0033
0.0025
0.0000
building
0.0846
0.9070
0.0063
0.0017
0.0004
0.0000
low_veg
0.2056
0.0457
0.4890
0.2589
0.0008
0.0000
tree
0.0710
0.0122
0.0786
0.8371
0.0012
0.0000
car
0.5114
0.0154
0.0078
0.0032
0.4623
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.801
0.963
0.686
0.748
0.865
--
Recall/Completeness
0.928
0.907
0.489
0.837
0.462
--
F1
0.859
0.934
0.571
0.790
0.602
--

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: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9490
0.0417
0.0068
0.0010
0.0015
0.0000
building
0.0682
0.9256
0.0051
0.0007
0.0004
0.0000
low_veg
0.1594
0.0168
0.5392
0.2839
0.0008
0.0000
tree
0.0387
0.0038
0.0740
0.8833
0.0002
0.0000
car
0.4157
0.0110
0.0080
0.0017
0.5636
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.836
0.977
0.718
0.774
0.894
--
Recall/Completeness
0.949
0.926
0.539
0.883
0.564
--
F1
0.889
0.951
0.616
0.825
0.691
--

Overall accuracy 0.910

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
0.9204
0.0363
0.0309
0.0096
0.0028
0.0000
building
0.0696
0.9068
0.0202
0.0033
0.0001
0.0000
low_veg
0.0853
0.0288
0.7165
0.1687
0.0007
0.0000
tree
0.0171
0.0034
0.0658
0.9136
0.0000
0.0000
car
0.3820
0.0283
0.0035
0.0016
0.5846
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.844
0.956
0.695
0.924
0.920
--
Recall/Completeness
0.920
0.907
0.717
0.914
0.585
--
F1
0.881
0.931
0.705
0.919
0.715
--

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_area6_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9506
0.0227
0.0230
0.0029
0.0008
0.0000
building
0.0577
0.9271
0.0142
0.0010
0.0000
0.0000
low_veg
0.0662
0.0165
0.7659
0.1511
0.0003
0.0000
tree
0.0065
0.0009
0.0516
0.9409
0.0000
0.0000
car
0.2844
0.0211
0.0013
0.0000
0.6932
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.882
0.976
0.742
0.947
0.972
--
Recall/Completeness
0.951
0.927
0.766
0.941
0.693
--
F1
0.915
0.951
0.754
0.944
0.809
--

Overall accuracy 0.919

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
0.9016
0.0256
0.0632
0.0080
0.0016
0.0000
building
0.0621
0.9119
0.0225
0.0032
0.0003
0.0000
low_veg
0.0684
0.0132
0.8734
0.0448
0.0002
0.0000
tree
0.0279
0.0058
0.1081
0.8582
0.0000
0.0000
car
0.4591
0.0086
0.0213
0.0044
0.5067
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.870
0.945
0.770
0.944
0.933
--
Recall/Completeness
0.902
0.912
0.873
0.858
0.507
--
F1
0.886
0.928
0.819
0.899
0.657
--

Overall accuracy 0.881

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
0.9241
0.0211
0.0515
0.0026
0.0007
0.0000
building
0.0487
0.9360
0.0138
0.0012
0.0003
0.0000
low_veg
0.0491
0.0064
0.9086
0.0359
0.0000
0.0000
tree
0.0110
0.0027
0.0839
0.9024
0.0000
0.0000
car
0.3500
0.0071
0.0140
0.0034
0.6255
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.911
0.963
0.816
0.964
0.963
--
Recall/Completeness
0.924
0.936
0.909
0.902
0.626
--
F1
0.917
0.949
0.860
0.932
0.758
--

Overall accuracy 0.915

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area10_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8828
0.0487
0.0527
0.0146
0.0011
0.0000
building
0.0458
0.9202
0.0244
0.0096
0.0000
0.0000
low_veg
0.0785
0.0270
0.7651
0.1294
0.0000
0.0000
tree
0.0216
0.0082
0.1247
0.8455
0.0000
0.0000
car
0.3867
0.0074
0.0316
0.0038
0.5705
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.912
0.898
0.724
0.851
0.907
--
Recall/Completeness
0.883
0.920
0.765
0.845
0.570
--
F1
0.897
0.909
0.744
0.848
0.700
--

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_area10_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9121
0.0384
0.0426
0.0064
0.0006
0.0000
building
0.0376
0.9378
0.0178
0.0068
0.0000
0.0000
low_veg
0.0736
0.0170
0.8022
0.1072
0.0000
0.0000
tree
0.0107
0.0038
0.0991
0.8864
0.0000
0.0000
car
0.2791
0.0089
0.0255
0.0005
0.6860
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.933
0.925
0.769
0.889
0.942
--
Recall/Completeness
0.912
0.938
0.802
0.886
0.686
--
F1
0.922
0.931
0.785
0.888
0.794
--

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_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8848
0.0311
0.0484
0.0331
0.0026
0.0000
building
0.0588
0.9226
0.0114
0.0072
0.0000
0.0000
low_veg
0.0529
0.0230
0.7480
0.1755
0.0002
0.0004
tree
0.0102
0.0067
0.0968
0.8863
0.0000
0.0000
car
0.2136
0.0006
0.0001
0.0070
0.7786
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.800
0.928
0.829
0.852
0.902
--
Recall/Completeness
0.885
0.923
0.748
0.886
0.779
--
F1
0.840
0.926
0.786
0.869
0.836
--

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_area12_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9126
0.0287
0.0389
0.0189
0.0009
0.0000
building
0.0580
0.9349
0.0048
0.0023
0.0000
0.0000
low_veg
0.0504
0.0141
0.7840
0.1510
0.0001
0.0004
tree
0.0052
0.0027
0.0795
0.9126
0.0000
0.0000
car
0.0825
0.0000
0.0000
0.0013
0.9163
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.824
0.952
0.860
0.881
0.957
--
Recall/Completeness
0.913
0.935
0.784
0.913
0.916
--
F1
0.866
0.944
0.820
0.896
0.936
--

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_area14_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8513
0.0267
0.0915
0.0287
0.0017
0.0000
building
0.0378
0.9319
0.0249
0.0054
0.0000
0.0000
low_veg
0.0851
0.0447
0.7388
0.1308
0.0006
0.0000
tree
0.0273
0.0104
0.1465
0.8158
0.0000
0.0000
car
0.3037
0.0000
0.0010
0.0063
0.6890
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.836
0.886
0.716
0.870
0.765
--
Recall/Completeness
0.851
0.932
0.739
0.816
0.689
--
F1
0.844
0.909
0.727
0.842
0.725
--

Overall accuracy 0.824

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
0.8697
0.0230
0.0865
0.0196
0.0011
0.0000
building
0.0310
0.9533
0.0140
0.0017
0.0000
0.0000
low_veg
0.0793
0.0312
0.7692
0.1196
0.0007
0.0000
tree
0.0185
0.0046
0.1325
0.8443
0.0000
0.0000
car
0.1849
0.0000
0.0000
0.0028
0.8123
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.865
0.919
0.739
0.892
0.787
--
Recall/Completeness
0.870
0.953
0.769
0.844
0.812
--
F1
0.867
0.936
0.754
0.867
0.800
--

Overall accuracy 0.851

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area16_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8435
0.0247
0.0760
0.0536
0.0022
0.0000
building
0.0482
0.8894
0.0473
0.0147
0.0004
0.0000
low_veg
0.0600
0.0141
0.7833
0.1426
0.0000
0.0000
tree
0.0243
0.0044
0.1036
0.8675
0.0001
0.0000
car
0.1820
0.0120
0.0265
0.0048
0.7747
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.785
0.943
0.800
0.857
0.796
--
Recall/Completeness
0.844
0.889
0.783
0.868
0.775
--
F1
0.813
0.915
0.791
0.862
0.785
--

Overall accuracy 0.842

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
0.8787
0.0192
0.0673
0.0340
0.0008
0.0000
building
0.0444
0.9124
0.0369
0.0059
0.0003
0.0000
low_veg
0.0578
0.0087
0.8051
0.1284
0.0000
0.0000
tree
0.0166
0.0017
0.0894
0.8922
0.0001
0.0000
car
0.0999
0.0065
0.0174
0.0012
0.8750
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.809
0.964
0.828
0.881
0.879
--
Recall/Completeness
0.879
0.912
0.805
0.892
0.875
--
F1
0.842
0.937
0.816
0.887
0.877
--

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_area20_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8591
0.0416
0.0549
0.0436
0.0009
0.0000
building
0.0311
0.9385
0.0232
0.0072
0.0000
0.0000
low_veg
0.0691
0.0325
0.6780
0.2197
0.0002
0.0004
tree
0.0089
0.0020
0.0401
0.9490
0.0000
0.0000
car
0.3691
0.0000
0.0408
0.0124
0.5777
0.0000
clutter
0.0000
0.9976
0.0000
0.0023
0.0000
0.0000
Precision/Correctness
0.880
0.783
0.806
0.881
0.915
0.000
Recall/Completeness
0.859
0.938
0.678
0.949
0.578
0.000
F1
0.869
0.854
0.737
0.914
0.708
-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_area20_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8896
0.0332
0.0519
0.0251
0.0003
0.0000
building
0.0276
0.9524
0.0176
0.0024
0.0000
0.0000
low_veg
0.0635
0.0210
0.7216
0.1931
0.0003
0.0005
tree
0.0041
0.0005
0.0292
0.9662
0.0000
0.0000
car
0.2670
0.0000
0.0358
0.0048
0.6924
0.0000
clutter
0.0000
0.9994
0.0000
0.0006
0.0000
0.0000
Precision/Correctness
0.905
0.803
0.839
0.907
0.954
0.000
Recall/Completeness
0.890
0.952
0.722
0.966
0.692
0.000
F1
0.897
0.871
0.776
0.936
0.802
-nan

Overall accuracy 0.875

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area22_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8990
0.0255
0.0417
0.0297
0.0040
0.0000
building
0.0469
0.9275
0.0200
0.0052
0.0004
0.0000
low_veg
0.0982
0.0346
0.7244
0.1425
0.0004
0.0000
tree
0.0241
0.0033
0.0752
0.8974
0.0000
0.0000
car
0.4540
0.0009
0.0215
0.0115
0.5121
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.877
0.911
0.790
0.868
0.797
--
Recall/Completeness
0.899
0.928
0.724
0.897
0.512
--
F1
0.888
0.919
0.756
0.883
0.623
--

Overall accuracy 0.864

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
0.9283
0.0194
0.0345
0.0149
0.0029
0.0000
building
0.0398
0.9467
0.0116
0.0017
0.0003
0.0000
low_veg
0.0953
0.0218
0.7660
0.1165
0.0004
0.0000
tree
0.0107
0.0008
0.0572
0.9313
0.0000
0.0000
car
0.3635
0.0007
0.0172
0.0034
0.6152
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.904
0.941
0.834
0.905
0.825
--
Recall/Completeness
0.928
0.947
0.766
0.931
0.615
--
F1
0.916
0.944
0.798
0.918
0.705
--

Overall accuracy 0.898

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
0.8260
0.0361
0.0930
0.0419
0.0030
0.0000
building
0.0603
0.8599
0.0733
0.0065
0.0000
0.0000
low_veg
0.0194
0.0431
0.8626
0.0748
0.0001
0.0000
tree
0.0170
0.0069
0.1568
0.8193
0.0000
0.0000
car
0.4568
0.0000
0.0067
0.0019
0.5347
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.826
0.867
0.841
0.845
0.806
--
Recall/Completeness
0.826
0.860
0.863
0.819
0.535
--
F1
0.826
0.864
0.852
0.832
0.643
--

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_area24_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8549
0.0268
0.0847
0.0310
0.0025
0.0000
building
0.0563
0.8738
0.0653
0.0046
0.0000
0.0000
low_veg
0.0151
0.0409
0.8793
0.0646
0.0001
0.0000
tree
0.0105
0.0037
0.1334
0.8524
0.0000
0.0000
car
0.3472
0.0000
0.0023
0.0000
0.6504
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.856
0.884
0.864
0.868
0.811
--
Recall/Completeness
0.855
0.874
0.879
0.852
0.650
--
F1
0.855
0.879
0.871
0.860
0.722
--

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_area27_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9385
0.0281
0.0241
0.0056
0.0036
0.0000
building
0.0968
0.8725
0.0272
0.0032
0.0003
0.0000
low_veg
0.0932
0.0234
0.7049
0.1782
0.0003
0.0000
tree
0.0165
0.0029
0.0969
0.8836
0.0001
0.0000
car
0.4436
0.0039
0.0053
0.0053
0.5419
0.0000
clutter
0.6523
0.1187
0.2002
0.0045
0.0244
0.0000
Precision/Correctness
0.811
0.955
0.833
0.700
0.927
-nan
Recall/Completeness
0.939
0.872
0.705
0.884
0.542
0.000
F1
0.870
0.912
0.764
0.781
0.684
-nan

Overall accuracy 0.849

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
0.9583
0.0216
0.0168
0.0022
0.0011
0.0000
building
0.0817
0.8962
0.0208
0.0011
0.0002
0.0000
low_veg
0.0717
0.0138
0.7448
0.1696
0.0001
0.0000
tree
0.0067
0.0005
0.0743
0.9185
0.0000
0.0000
car
0.3362
0.0031
0.0037
0.0041
0.6530
0.0000
clutter
0.6789
0.1102
0.1838
0.0022
0.0250
0.0000
Precision/Correctness
0.850
0.971
0.872
0.729
0.971
-nan
Recall/Completeness
0.958
0.896
0.745
0.919
0.653
0.000
F1
0.901
0.932
0.803
0.813
0.781
-nan

Overall accuracy 0.882

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area29_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9493
0.0170
0.0203
0.0114
0.0014
0.0006
building
0.0381
0.9416
0.0139
0.0064
0.0000
0.0000
low_veg
0.0810
0.0180
0.6323
0.2685
0.0002
0.0000
tree
0.0077
0.0025
0.0369
0.9529
0.0000
0.0000
car
0.4086
0.0026
0.0041
0.0133
0.5714
0.0000
clutter
0.5480
0.3036
0.0241
0.0247
0.0206
0.0789
Precision/Correctness
0.900
0.930
0.845
0.688
0.859
0.909
Recall/Completeness
0.949
0.942
0.632
0.953
0.571
0.079
F1
0.924
0.936
0.723
0.799
0.686
0.145

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_area29_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9667
0.0124
0.0149
0.0048
0.0007
0.0005
building
0.0300
0.9578
0.0088
0.0034
0.0000
0.0000
low_veg
0.0527
0.0069
0.6842
0.2561
0.0001
0.0000
tree
0.0027
0.0007
0.0265
0.9701
0.0000
0.0000
car
0.3154
0.0010
0.0048
0.0108
0.6679
0.0000
clutter
0.5173
0.3304
0.0219
0.0141
0.0227
0.0936
Precision/Correctness
0.927
0.946
0.883
0.728
0.879
0.915
Recall/Completeness
0.967
0.958
0.684
0.970
0.668
0.094
F1
0.946
0.952
0.771
0.832
0.759
0.170

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_area31_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9754
0.0132
0.0052
0.0034
0.0027
0.0001
building
0.0820
0.9060
0.0085
0.0019
0.0016
0.0000
low_veg
0.0603
0.0037
0.9005
0.0350
0.0004
0.0001
tree
0.0447
0.0030
0.0990
0.8530
0.0002
0.0000
car
0.2904
0.1264
0.0065
0.0058
0.5709
0.0000
clutter
0.6753
0.2084
0.0101
0.0116
0.0230
0.0715
Precision/Correctness
0.844
0.934
0.892
0.927
0.897
0.984
Recall/Completeness
0.975
0.906
0.901
0.853
0.571
0.072
F1
0.905
0.920
0.896
0.888
0.698
0.133

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_area31_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9838
0.0111
0.0030
0.0010
0.0012
0.0000
building
0.0693
0.9258
0.0032
0.0003
0.0014
0.0000
low_veg
0.0350
0.0015
0.9335
0.0299
0.0002
0.0000
tree
0.0150
0.0007
0.0778
0.9065
0.0000
0.0000
car
0.1836
0.1516
0.0026
0.0019
0.6602
0.0000
clutter
0.6517
0.2280
0.0078
0.0035
0.0255
0.0835
Precision/Correctness
0.881
0.944
0.928
0.951
0.919
0.998
Recall/Completeness
0.984
0.926
0.933
0.907
0.660
0.084
F1
0.929
0.935
0.931
0.928
0.769
0.154

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_area33_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9721
0.0158
0.0085
0.0031
0.0004
0.0002
building
0.1274
0.7824
0.0837
0.0044
0.0022
0.0000
low_veg
0.0961
0.0194
0.8395
0.0450
0.0000
0.0000
tree
0.0553
0.0060
0.1414
0.7973
0.0000
0.0000
car
0.5292
0.0078
0.0058
0.0015
0.4557
0.0000
clutter
0.8396
0.0187
0.0001
0.0027
0.0141
0.1248
Precision/Correctness
0.773
0.955
0.753
0.897
0.791
0.991
Recall/Completeness
0.972
0.782
0.840
0.797
0.456
0.125
F1
0.861
0.860
0.794
0.844
0.578
0.222

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_area33_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9800
0.0136
0.0052
0.0011
0.0001
0.0000
building
0.1151
0.7972
0.0834
0.0022
0.0021
0.0000
low_veg
0.0575
0.0155
0.8847
0.0423
0.0000
0.0000
tree
0.0258
0.0035
0.1316
0.8391
0.0000
0.0000
car
0.4143
0.0053
0.0031
0.0000
0.5773
0.0000
clutter
0.8249
0.0172
0.0000
0.0011
0.0157
0.1411
Precision/Correctness
0.805
0.964
0.767
0.919
0.799
0.998
Recall/Completeness
0.980
0.797
0.885
0.839
0.577
0.141
F1
0.884
0.873
0.822
0.877
0.670
0.247

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: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8767
0.0397
0.0609
0.0224
0.0004
0.0000
building
0.0550
0.9187
0.0180
0.0067
0.0015
0.0000
low_veg
0.0555
0.0123
0.6976
0.2346
0.0000
0.0000
tree
0.0383
0.0056
0.1140
0.8420
0.0001
0.0000
car
0.4908
0.0003
0.0052
0.0065
0.4972
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.843
0.945
0.787
0.750
0.877
--
Recall/Completeness
0.877
0.919
0.698
0.842
0.497
--
F1
0.859
0.932
0.740
0.793
0.635
--

Overall accuracy 0.833

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
0.9147
0.0354
0.0414
0.0084
0.0001
0.0000
building
0.0421
0.9470
0.0079
0.0016
0.0015
0.0000
low_veg
0.0398
0.0046
0.7281
0.2275
0.0000
0.0000
tree
0.0150
0.0020
0.0903
0.8927
0.0000
0.0000
car
0.3797
0.0000
0.0023
0.0015
0.6165
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.892
0.963
0.844
0.778
0.889
--
Recall/Completeness
0.915
0.947
0.728
0.893
0.616
--
F1
0.903
0.955
0.782
0.831
0.728
--

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_area38_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9192
0.0212
0.0461
0.0120
0.0015
0.0000
building
0.0784
0.8421
0.0741
0.0047
0.0007
0.0000
low_veg
0.0453
0.0218
0.8495
0.0831
0.0003
0.0000
tree
0.0249
0.0020
0.1465
0.8265
0.0000
0.0000
car
0.3922
0.0122
0.0546
0.0058
0.5352
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.857
0.945
0.798
0.853
0.886
--
Recall/Completeness
0.919
0.842
0.850
0.827
0.535
--
F1
0.887
0.891
0.823
0.840
0.667
--

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_area38_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9442
0.0195
0.0319
0.0039
0.0006
0.0000
building
0.0688
0.8712
0.0578
0.0015
0.0007
0.0000
low_veg
0.0276
0.0200
0.8832
0.0690
0.0003
0.0000
tree
0.0095
0.0005
0.1212
0.8687
0.0000
0.0000
car
0.2831
0.0146
0.0522
0.0014
0.6487
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.895
0.955
0.838
0.889
0.919
--
Recall/Completeness
0.944
0.871
0.883
0.869
0.649
--
F1
0.919
0.911
0.860
0.879
0.760
--

Overall accuracy 0.892

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image