Detailled semantic labeling (2D) result


Name M. N. Duc and S. D. Viet
Affiliation Hanoi University of Science and Technology, Vietnam
Abbreviation BKHN10
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
0.916
0.025
0.039
0.016
0.004
0.000
building
0.038
0.940
0.016
0.006
0.000
0.000
low_veg
0.051
0.019
0.794
0.135
0.000
0.000
tree
0.021
0.005
0.088
0.886
0.000
0.000
car
0.184
0.025
0.005
0.004
0.780
0.001
clutter
0.440
0.156
0.032
0.007
0.027
0.338
Precision/Correctness
0.888
0.946
0.829
0.851
0.860
0.930
Recall/Completeness
0.916
0.940
0.794
0.886
0.780
0.338
F1
0.902
0.943
0.811
0.868
0.818
0.496

Overall accuracy 0.882

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
0.939
0.019
0.032
0.007
0.002
0.000
building
0.030
0.957
0.009
0.003
0.000
0.000
low_veg
0.039
0.011
0.829
0.121
0.000
0.000
tree
0.009
0.002
0.071
0.917
0.000
0.000
car
0.080
0.029
0.002
0.002
0.886
0.001
clutter
0.414
0.160
0.030
0.002
0.027
0.367
Precision/Correctness
0.920
0.963
0.864
0.879
0.891
0.944
Recall/Completeness
0.939
0.957
0.829
0.917
0.886
0.367
F1
0.929
0.960
0.846
0.898
0.888
0.528

Overall accuracy 0.910
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9603
0.0077
0.0168
0.0103
0.0049
0.0000
building
0.0285
0.9518
0.0170
0.0026
0.0000
0.0000
low_veg
0.0734
0.0194
0.7611
0.1461
0.0000
0.0000
tree
0.0293
0.0071
0.0912
0.8709
0.0003
0.0013
car
0.2108
0.0005
0.0005
0.0009
0.7872
0.0000
clutter
0.0000
0.0005
0.0000
0.0144
0.0000
0.9851
Precision/Correctness
0.873
0.963
0.859
0.846
0.903
0.983
Recall/Completeness
0.960
0.952
0.761
0.871
0.787
0.985
F1
0.915
0.957
0.807
0.858
0.841
0.984

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_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9812
0.0046
0.0079
0.0029
0.0035
0.0000
building
0.0211
0.9693
0.0091
0.0005
0.0000
0.0000
low_veg
0.0556
0.0116
0.7928
0.1399
0.0000
0.0000
tree
0.0133
0.0040
0.0767
0.9053
0.0002
0.0005
car
0.0838
0.0000
0.0000
0.0002
0.9160
0.0000
clutter
0.0000
0.0004
0.0000
0.0027
0.0000
0.9969
Precision/Correctness
0.914
0.979
0.891
0.868
0.924
0.994
Recall/Completeness
0.981
0.969
0.793
0.905
0.916
0.997
F1
0.947
0.974
0.839
0.886
0.920
0.995

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_area4_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9354
0.0450
0.0122
0.0041
0.0033
0.0001
building
0.0451
0.9471
0.0064
0.0014
0.0000
0.0000
low_veg
0.1400
0.0431
0.5313
0.2831
0.0025
0.0000
tree
0.0554
0.0138
0.0465
0.8842
0.0000
0.0000
car
0.2450
0.0057
0.0002
0.0020
0.7470
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.878
0.971
0.716
0.744
0.909
--
Recall/Completeness
0.935
0.947
0.531
0.884
0.747
--
F1
0.906
0.959
0.610
0.808
0.820
--

Overall accuracy 0.918

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
0.9601
0.0283
0.0091
0.0012
0.0012
0.0001
building
0.0316
0.9626
0.0054
0.0004
0.0000
0.0000
low_veg
0.1054
0.0152
0.5659
0.3113
0.0022
0.0000
tree
0.0258
0.0046
0.0413
0.9284
0.0000
0.0000
car
0.1266
0.0032
0.0000
0.0007
0.8695
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.915
0.985
0.746
0.769
0.957
--
Recall/Completeness
0.960
0.963
0.566
0.928
0.869
--
F1
0.937
0.973
0.643
0.841
0.911
--

Overall accuracy 0.943

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
0.9087
0.0477
0.0295
0.0097
0.0044
0.0000
building
0.0386
0.9449
0.0135
0.0029
0.0001
0.0000
low_veg
0.0786
0.0346
0.7202
0.1663
0.0003
0.0000
tree
0.0144
0.0035
0.0601
0.9219
0.0001
0.0000
car
0.2139
0.0019
0.0002
0.0011
0.7828
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.889
0.949
0.724
0.926
0.914
--
Recall/Completeness
0.909
0.945
0.720
0.922
0.783
--
F1
0.899
0.947
0.722
0.924
0.844
--

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_area6_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9390
0.0351
0.0208
0.0030
0.0021
0.0000
building
0.0291
0.9612
0.0089
0.0007
0.0000
0.0000
low_veg
0.0605
0.0217
0.7673
0.1505
0.0000
0.0000
tree
0.0047
0.0008
0.0471
0.9474
0.0000
0.0000
car
0.1090
0.0000
0.0000
0.0000
0.8909
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.926
0.967
0.771
0.947
0.954
--
Recall/Completeness
0.939
0.961
0.767
0.947
0.891
--
F1
0.933
0.964
0.769
0.947
0.921
--

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
0.8956
0.0246
0.0692
0.0074
0.0032
0.0000
building
0.0232
0.9554
0.0174
0.0037
0.0003
0.0000
low_veg
0.0394
0.0119
0.9053
0.0431
0.0003
0.0000
tree
0.0263
0.0055
0.0759
0.8923
0.0001
0.0000
car
0.2241
0.0034
0.0140
0.0040
0.7544
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.924
0.951
0.801
0.948
0.918
--
Recall/Completeness
0.896
0.955
0.905
0.892
0.754
--
F1
0.909
0.953
0.850
0.919
0.828
--

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_area8_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9177
0.0198
0.0597
0.0012
0.0016
0.0000
building
0.0131
0.9769
0.0085
0.0013
0.0002
0.0000
low_veg
0.0235
0.0053
0.9398
0.0313
0.0001
0.0000
tree
0.0102
0.0024
0.0545
0.9328
0.0000
0.0000
car
0.1051
0.0026
0.0076
0.0029
0.8818
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.961
0.968
0.843
0.970
0.953
--
Recall/Completeness
0.918
0.977
0.940
0.933
0.882
--
F1
0.939
0.972
0.889
0.951
0.916
--

Overall accuracy 0.939

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
0.8469
0.0516
0.0770
0.0184
0.0038
0.0023
building
0.0204
0.9542
0.0143
0.0106
0.0005
0.0000
low_veg
0.0696
0.0258
0.7596
0.1445
0.0004
0.0000
tree
0.0141
0.0073
0.0819
0.8967
0.0000
0.0000
car
0.1609
0.0383
0.0118
0.0021
0.7869
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.938
0.898
0.731
0.841
0.772
--
Recall/Completeness
0.847
0.954
0.760
0.897
0.787
--
F1
0.890
0.925
0.745
0.868
0.780
--

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
0.8765
0.0403
0.0709
0.0073
0.0026
0.0025
building
0.0161
0.9660
0.0099
0.0077
0.0004
0.0000
low_veg
0.0650
0.0138
0.8050
0.1157
0.0005
0.0000
tree
0.0058
0.0033
0.0643
0.9266
0.0000
0.0000
car
0.0710
0.0410
0.0083
0.0001
0.8796
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.954
0.926
0.762
0.884
0.799
--
Recall/Completeness
0.876
0.966
0.805
0.927
0.880
--
F1
0.913
0.945
0.783
0.905
0.838
--

Overall accuracy 0.896

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8922
0.0322
0.0420
0.0314
0.0023
0.0000
building
0.1703
0.8097
0.0143
0.0045
0.0012
0.0000
low_veg
0.0383
0.0193
0.7726
0.1697
0.0001
0.0001
tree
0.0098
0.0054
0.1060
0.8789
0.0000
0.0000
car
0.1587
0.0000
0.0022
0.0009
0.8381
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.725
0.927
0.824
0.856
0.878
--
Recall/Completeness
0.892
0.810
0.773
0.879
0.838
--
F1
0.800
0.864
0.797
0.867
0.858
--

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_area12_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9189
0.0297
0.0341
0.0170
0.0003
0.0000
building
0.1782
0.8127
0.0067
0.0012
0.0012
0.0000
low_veg
0.0352
0.0119
0.8052
0.1476
0.0000
0.0001
tree
0.0041
0.0021
0.0891
0.9048
0.0000
0.0000
car
0.0630
0.0000
0.0000
0.0000
0.9370
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.739
0.950
0.853
0.883
0.925
--
Recall/Completeness
0.919
0.813
0.805
0.905
0.937
--
F1
0.819
0.876
0.828
0.894
0.931
--

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_area14_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8331
0.0296
0.0955
0.0351
0.0065
0.0002
building
0.0080
0.9673
0.0190
0.0057
0.0000
0.0000
low_veg
0.0644
0.0419
0.7369
0.1564
0.0004
0.0000
tree
0.0218
0.0111
0.1141
0.8530
0.0000
0.0000
car
0.1144
0.0000
0.0000
0.0029
0.8827
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.883
0.889
0.747
0.854
0.594
--
Recall/Completeness
0.833
0.967
0.737
0.853
0.883
--
F1
0.857
0.927
0.742
0.854
0.710
--

Overall accuracy 0.839

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
0.8523
0.0252
0.0919
0.0245
0.0059
0.0002
building
0.0039
0.9851
0.0090
0.0020
0.0000
0.0000
low_veg
0.0590
0.0285
0.7666
0.1455
0.0004
0.0000
tree
0.0142
0.0051
0.1008
0.8799
0.0000
0.0000
car
0.0235
0.0000
0.0000
0.0000
0.9765
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.908
0.921
0.770
0.876
0.569
--
Recall/Completeness
0.852
0.985
0.767
0.880
0.976
--
F1
0.879
0.952
0.768
0.878
0.719
--

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_area16_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8653
0.0184
0.0640
0.0491
0.0032
0.0000
building
0.0258
0.9412
0.0210
0.0119
0.0001
0.0000
low_veg
0.0162
0.0140
0.8234
0.1450
0.0000
0.0014
tree
0.0243
0.0035
0.0958
0.8764
0.0000
0.0000
car
0.1357
0.0006
0.0211
0.0006
0.8419
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.878
0.953
0.833
0.859
0.784
--
Recall/Completeness
0.865
0.941
0.823
0.876
0.842
--
F1
0.872
0.947
0.828
0.868
0.812
--

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
0.8979
0.0146
0.0557
0.0301
0.0017
0.0000
building
0.0216
0.9659
0.0080
0.0044
0.0000
0.0000
low_veg
0.0120
0.0091
0.8464
0.1310
0.0000
0.0015
tree
0.0165
0.0007
0.0815
0.9013
0.0000
0.0000
car
0.0590
0.0000
0.0218
0.0000
0.9193
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.909
0.971
0.863
0.882
0.847
--
Recall/Completeness
0.898
0.966
0.846
0.901
0.919
--
F1
0.903
0.968
0.855
0.892
0.882
--

Overall accuracy 0.896

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area20_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8709
0.0234
0.0572
0.0435
0.0050
0.0000
building
0.0137
0.9607
0.0199
0.0057
0.0000
0.0000
low_veg
0.0460
0.0183
0.7461
0.1895
0.0000
0.0000
tree
0.0078
0.0009
0.0485
0.9428
0.0000
0.0000
car
0.1221
0.0150
0.0193
0.0128
0.8308
0.0000
clutter
0.6760
0.2149
0.1086
0.0005
0.0000
0.0000
Precision/Correctness
0.841
0.915
0.793
0.893
0.773
0.000
Recall/Completeness
0.871
0.961
0.746
0.943
0.831
0.000
F1
0.856
0.938
0.769
0.917
0.801
-nan

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_area20_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9014
0.0172
0.0535
0.0249
0.0030
0.0000
building
0.0113
0.9729
0.0144
0.0014
0.0000
0.0000
low_veg
0.0388
0.0100
0.7897
0.1615
0.0000
0.0000
tree
0.0030
0.0001
0.0367
0.9601
0.0000
0.0000
car
0.0591
0.0214
0.0086
0.0053
0.9056
0.0000
clutter
0.6847
0.2120
0.1033
0.0000
0.0000
0.0000
Precision/Correctness
0.858
0.934
0.823
0.920
0.817
0.000
Recall/Completeness
0.901
0.973
0.790
0.960
0.906
0.000
F1
0.879
0.953
0.806
0.939
0.859
-nan

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_area22_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9100
0.0199
0.0342
0.0296
0.0063
0.0000
building
0.0233
0.9564
0.0134
0.0068
0.0001
0.0000
low_veg
0.0839
0.0339
0.7415
0.1403
0.0002
0.0001
tree
0.0216
0.0030
0.0459
0.9293
0.0001
0.0000
car
0.1929
0.0002
0.0078
0.0079
0.7912
0.0001
clutter
--
--
--
--
--
--
Precision/Correctness
0.908
0.924
0.849
0.873
0.805
--
Recall/Completeness
0.910
0.956
0.741
0.929
0.791
--
F1
0.909
0.940
0.792
0.900
0.798
--

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: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9401
0.0144
0.0277
0.0138
0.0040
0.0000
building
0.0176
0.9741
0.0054
0.0028
0.0001
0.0000
low_veg
0.0794
0.0243
0.7867
0.1095
0.0001
0.0001
tree
0.0090
0.0007
0.0313
0.9589
0.0000
0.0000
car
0.0922
0.0000
0.0027
0.0014
0.9035
0.0001
clutter
--
--
--
--
--
--
Precision/Correctness
0.933
0.948
0.890
0.913
0.845
--
Recall/Completeness
0.940
0.974
0.787
0.959
0.904
--
F1
0.936
0.961
0.835
0.935
0.873
--

Overall accuracy 0.921

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area24_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8280
0.0249
0.1049
0.0382
0.0041
0.0000
building
0.0553
0.8873
0.0379
0.0194
0.0000
0.0000
low_veg
0.0232
0.0190
0.8685
0.0891
0.0003
0.0000
tree
0.0170
0.0065
0.1477
0.8288
0.0001
0.0000
car
0.2011
0.0000
0.0001
0.0045
0.7943
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.828
0.927
0.856
0.821
0.806
--
Recall/Completeness
0.828
0.887
0.868
0.829
0.794
--
F1
0.828
0.907
0.862
0.825
0.800
--

Overall accuracy 0.856

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
0.8566
0.0158
0.0964
0.0283
0.0028
0.0000
building
0.0519
0.9002
0.0310
0.0168
0.0000
0.0000
low_veg
0.0192
0.0148
0.8860
0.0797
0.0003
0.0000
tree
0.0102
0.0033
0.1258
0.8607
0.0000
0.0000
car
0.1000
0.0000
0.0000
0.0012
0.8988
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.855
0.949
0.879
0.841
0.820
--
Recall/Completeness
0.857
0.900
0.886
0.861
0.899
--
F1
0.856
0.924
0.882
0.851
0.857
--

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: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9484
0.0208
0.0170
0.0069
0.0069
0.0000
building
0.0519
0.9317
0.0117
0.0042
0.0005
0.0000
low_veg
0.0750
0.0214
0.7241
0.1789
0.0005
0.0000
tree
0.0111
0.0055
0.0673
0.9159
0.0001
0.0001
car
0.1860
0.0017
0.0028
0.0058
0.8036
0.0000
clutter
0.5964
0.0656
0.1805
0.0050
0.1469
0.0056
Precision/Correctness
0.880
0.966
0.894
0.702
0.902
0.589
Recall/Completeness
0.948
0.932
0.724
0.916
0.804
0.006
F1
0.913
0.948
0.800
0.795
0.850
0.011

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_area27_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9730
0.0123
0.0103
0.0025
0.0018
0.0000
building
0.0404
0.9507
0.0064
0.0020
0.0004
0.0000
low_veg
0.0573
0.0093
0.7647
0.1684
0.0003
0.0000
tree
0.0042
0.0015
0.0491
0.9451
0.0000
0.0001
car
0.0787
0.0006
0.0013
0.0042
0.9152
0.0000
clutter
0.6042
0.0594
0.1656
0.0023
0.1606
0.0079
Precision/Correctness
0.914
0.983
0.931
0.734
0.953
0.589
Recall/Completeness
0.973
0.951
0.765
0.945
0.915
0.008
F1
0.943
0.967
0.840
0.826
0.934
0.016

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_area29_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9440
0.0143
0.0236
0.0120
0.0060
0.0000
building
0.0136
0.9703
0.0102
0.0057
0.0001
0.0000
low_veg
0.0643
0.0180
0.6405
0.2765
0.0006
0.0000
tree
0.0055
0.0028
0.0226
0.9691
0.0000
0.0000
car
0.1807
0.0016
0.0016
0.0086
0.7925
0.0151
clutter
0.5838
0.3164
0.0308
0.0108
0.0348
0.0233
Precision/Correctness
0.923
0.935
0.854
0.689
0.741
0.759
Recall/Completeness
0.944
0.970
0.641
0.969
0.792
0.023
F1
0.933
0.952
0.732
0.805
0.766
0.045

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_area29_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9646
0.0085
0.0172
0.0050
0.0048
0.0000
building
0.0083
0.9842
0.0047
0.0026
0.0001
0.0000
low_veg
0.0427
0.0070
0.6849
0.2648
0.0005
0.0000
tree
0.0017
0.0013
0.0150
0.9820
0.0000
0.0000
car
0.0874
0.0004
0.0015
0.0056
0.8877
0.0174
clutter
0.5805
0.3295
0.0250
0.0035
0.0353
0.0260
Precision/Correctness
0.944
0.953
0.895
0.727
0.744
0.796
Recall/Completeness
0.965
0.984
0.685
0.982
0.888
0.026
F1
0.954
0.968
0.776
0.835
0.810
0.050

Overall accuracy 0.907

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
0.9780
0.0062
0.0077
0.0033
0.0045
0.0002
building
0.0359
0.9508
0.0095
0.0020
0.0015
0.0002
low_veg
0.0323
0.0009
0.9254
0.0408
0.0003
0.0002
tree
0.0368
0.0036
0.0985
0.8608
0.0003
0.0000
car
0.1420
0.1273
0.0040
0.0046
0.7216
0.0006
clutter
0.4751
0.1932
0.0292
0.0099
0.0346
0.2580
Precision/Correctness
0.905
0.949
0.885
0.921
0.884
0.977
Recall/Completeness
0.978
0.951
0.925
0.861
0.722
0.258
F1
0.940
0.950
0.905
0.890
0.795
0.408

Overall accuracy 0.916

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
0.9874
0.0043
0.0054
0.0006
0.0023
0.0000
building
0.0233
0.9714
0.0038
0.0002
0.0012
0.0001
low_veg
0.0140
0.0001
0.9518
0.0342
0.0000
0.0000
tree
0.0126
0.0005
0.0808
0.9061
0.0000
0.0000
car
0.0585
0.1437
0.0007
0.0014
0.7952
0.0005
clutter
0.4224
0.2148
0.0280
0.0053
0.0375
0.2921
Precision/Correctness
0.940
0.958
0.917
0.947
0.906
0.993
Recall/Completeness
0.987
0.971
0.952
0.906
0.795
0.292
F1
0.963
0.965
0.934
0.926
0.847
0.451

Overall accuracy 0.942

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
0.9854
0.0043
0.0045
0.0024
0.0020
0.0014
building
0.0372
0.9292
0.0166
0.0135
0.0010
0.0025
low_veg
0.0768
0.0073
0.8725
0.0416
0.0015
0.0004
tree
0.0484
0.0046
0.1296
0.8174
0.0000
0.0000
car
0.1968
0.0055
0.0016
0.0020
0.7888
0.0053
clutter
0.4299
0.0837
0.0013
0.0009
0.0361
0.4480
Precision/Correctness
0.877
0.972
0.869
0.883
0.757
0.947
Recall/Completeness
0.985
0.929
0.872
0.817
0.789
0.448
F1
0.928
0.950
0.871
0.849
0.773
0.608

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_area33_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9952
0.0019
0.0014
0.0004
0.0010
0.0001
building
0.0289
0.9421
0.0138
0.0122
0.0009
0.0021
low_veg
0.0440
0.0019
0.9126
0.0398
0.0014
0.0003
tree
0.0225
0.0010
0.1170
0.8595
0.0000
0.0000
car
0.0857
0.0067
0.0000
0.0006
0.9018
0.0053
clutter
0.3900
0.0868
0.0002
0.0008
0.0380
0.4843
Precision/Correctness
0.910
0.981
0.892
0.899
0.764
0.969
Recall/Completeness
0.995
0.942
0.913
0.860
0.902
0.484
F1
0.951
0.961
0.902
0.879
0.827
0.646

Overall accuracy 0.926

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area35_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8897
0.0357
0.0599
0.0135
0.0011
0.0001
building
0.0399
0.9372
0.0167
0.0056
0.0006
0.0000
low_veg
0.0535
0.0100
0.7332
0.2031
0.0001
0.0000
tree
0.0320
0.0051
0.1201
0.8427
0.0001
0.0000
car
0.1946
0.0219
0.0018
0.0048
0.7768
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.872
0.951
0.793
0.781
0.925
--
Recall/Completeness
0.890
0.937
0.733
0.843
0.777
--
F1
0.881
0.944
0.762
0.811
0.844
--

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
0.9234
0.0328
0.0412
0.0022
0.0003
0.0001
building
0.0275
0.9642
0.0069
0.0009
0.0005
0.0000
low_veg
0.0356
0.0047
0.7619
0.1977
0.0000
0.0000
tree
0.0102
0.0014
0.0920
0.8964
0.0000
0.0000
car
0.0672
0.0258
0.0002
0.0007
0.9061
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.922
0.966
0.849
0.806
0.959
--
Recall/Completeness
0.923
0.964
0.762
0.896
0.906
--
F1
0.923
0.965
0.803
0.849
0.932
--

Overall accuracy 0.889

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area38_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9131
0.0303
0.0391
0.0127
0.0036
0.0012
building
0.0215
0.9445
0.0279
0.0052
0.0009
0.0000
low_veg
0.0389
0.0132
0.8685
0.0792
0.0002
0.0000
tree
0.0217
0.0042
0.0970
0.8769
0.0001
0.0000
car
0.1471
0.0197
0.0145
0.0040
0.8147
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.918
0.949
0.869
0.864
0.861
--
Recall/Completeness
0.913
0.944
0.868
0.877
0.815
--
F1
0.915
0.947
0.869
0.870
0.837
--

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_area38_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9377
0.0288
0.0262
0.0040
0.0019
0.0013
building
0.0137
0.9668
0.0165
0.0023
0.0007
0.0000
low_veg
0.0248
0.0080
0.9038
0.0633
0.0001
0.0000
tree
0.0077
0.0014
0.0734
0.9175
0.0000
0.0000
car
0.0507
0.0214
0.0033
0.0008
0.9238
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.953
0.961
0.908
0.901
0.903
--
Recall/Completeness
0.938
0.967
0.904
0.918
0.924
--
F1
0.946
0.964
0.906
0.909
0.913
--

Overall accuracy 0.932

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image