Detailled semantic labeling (2D) result


Name X. Pan et al.
Affiliation Chinese Academy of Sciences, Institute for Remote Sensing and Digital Earth, China
Abbreviation CASRS1
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
0.909
0.030
0.039
0.019
0.003
0.000
building
0.050
0.924
0.019
0.007
0.001
0.000
low_veg
0.059
0.025
0.759
0.156
0.000
0.000
tree
0.020
0.006
0.087
0.886
0.000
0.000
car
0.345
0.031
0.010
0.006
0.608
0.000
clutter
0.437
0.275
0.016
0.007
0.031
0.233
Precision/Correctness
0.867
0.930
0.821
0.831
0.861
0.916
Recall/Completeness
0.909
0.924
0.759
0.886
0.608
0.233
F1
0.888
0.927
0.789
0.858
0.713
0.372

Overall accuracy 0.865

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
0.935
0.023
0.031
0.010
0.001
0.000
building
0.042
0.942
0.012
0.004
0.001
0.000
low_veg
0.046
0.016
0.796
0.140
0.000
0.000
tree
0.010
0.003
0.071
0.916
0.000
0.000
car
0.237
0.036
0.006
0.003
0.717
0.000
clutter
0.399
0.295
0.013
0.002
0.033
0.257
Precision/Correctness
0.900
0.950
0.857
0.861
0.890
0.930
Recall/Completeness
0.935
0.942
0.796
0.916
0.717
0.257
F1
0.917
0.946
0.826
0.888
0.794
0.402

Overall accuracy 0.895
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9465
0.0113
0.0246
0.0137
0.0038
0.0000
building
0.0482
0.9258
0.0208
0.0049
0.0002
0.0000
low_veg
0.0671
0.0208
0.7405
0.1710
0.0006
0.0001
tree
0.0267
0.0065
0.1032
0.8625
0.0002
0.0010
car
0.3860
0.0118
0.0006
0.0020
0.5996
0.0000
clutter
0.0441
0.0000
0.0000
0.0154
0.0000
0.9406
Precision/Correctness
0.853
0.956
0.833
0.820
0.887
0.985
Recall/Completeness
0.946
0.926
0.741
0.862
0.600
0.941
F1
0.897
0.941
0.784
0.841
0.715
0.962

Overall accuracy 0.866

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
0.9711
0.0073
0.0145
0.0044
0.0027
0.0000
building
0.0422
0.9427
0.0131
0.0018
0.0002
0.0000
low_veg
0.0502
0.0103
0.7760
0.1628
0.0006
0.0001
tree
0.0119
0.0027
0.0903
0.8946
0.0001
0.0004
car
0.2631
0.0131
0.0000
0.0007
0.7230
0.0000
clutter
0.0444
0.0000
0.0000
0.0031
0.0000
0.9525
Precision/Correctness
0.892
0.978
0.864
0.846
0.908
0.994
Recall/Completeness
0.971
0.943
0.776
0.895
0.723
0.953
F1
0.930
0.960
0.818
0.870
0.805
0.973

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_area4_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9119
0.0685
0.0128
0.0041
0.0028
0.0000
building
0.0577
0.9356
0.0044
0.0017
0.0006
0.0000
low_veg
0.1741
0.0693
0.4763
0.2800
0.0003
0.0000
tree
0.0631
0.0276
0.0374
0.8718
0.0002
0.0000
car
0.4483
0.0096
0.0003
0.0007
0.5411
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.843
0.955
0.726
0.741
0.870
--
Recall/Completeness
0.912
0.936
0.476
0.872
0.541
--
F1
0.876
0.945
0.575
0.801
0.667
--

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_area4_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9403
0.0464
0.0102
0.0015
0.0016
0.0000
building
0.0449
0.9502
0.0036
0.0007
0.0006
0.0000
low_veg
0.1319
0.0328
0.5286
0.3068
0.0000
0.0000
tree
0.0346
0.0138
0.0338
0.9177
0.0000
0.0000
car
0.3472
0.0054
0.0000
0.0002
0.6472
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.878
0.973
0.762
0.767
0.897
--
Recall/Completeness
0.940
0.950
0.529
0.918
0.647
--
F1
0.908
0.962
0.624
0.835
0.752
--

Overall accuracy 0.925

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
0.9104
0.0464
0.0283
0.0100
0.0048
0.0000
building
0.0489
0.9331
0.0144
0.0031
0.0005
0.0000
low_veg
0.0707
0.0334
0.7031
0.1923
0.0006
0.0000
tree
0.0147
0.0031
0.0471
0.9350
0.0001
0.0000
car
0.2559
0.0086
0.0017
0.0011
0.7326
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.878
0.949
0.746
0.918
0.889
--
Recall/Completeness
0.910
0.933
0.703
0.935
0.733
--
F1
0.894
0.941
0.724
0.926
0.803
--

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
0.9435
0.0320
0.0197
0.0029
0.0020
0.0000
building
0.0388
0.9502
0.0099
0.0007
0.0004
0.0000
low_veg
0.0528
0.0173
0.7559
0.1739
0.0001
0.0000
tree
0.0045
0.0007
0.0349
0.9599
0.0000
0.0000
car
0.1560
0.0030
0.0005
0.0000
0.8404
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.915
0.971
0.798
0.941
0.940
--
Recall/Completeness
0.943
0.950
0.756
0.960
0.840
--
F1
0.929
0.960
0.776
0.950
0.888
--

Overall accuracy 0.931

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
0.8886
0.0281
0.0671
0.0140
0.0022
0.0000
building
0.0363
0.9455
0.0152
0.0030
0.0000
0.0000
low_veg
0.0571
0.0176
0.8530
0.0719
0.0005
0.0000
tree
0.0235
0.0074
0.0804
0.8886
0.0000
0.0000
car
0.3660
0.0077
0.0284
0.0053
0.5926
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.899
0.939
0.791
0.917
0.927
--
Recall/Completeness
0.889
0.945
0.853
0.889
0.593
--
F1
0.894
0.942
0.821
0.902
0.723
--

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_area8_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9145
0.0212
0.0575
0.0060
0.0008
0.0000
building
0.0265
0.9643
0.0084
0.0008
0.0000
0.0000
low_veg
0.0413
0.0086
0.8897
0.0603
0.0001
0.0000
tree
0.0098
0.0035
0.0609
0.9258
0.0000
0.0000
car
0.2648
0.0053
0.0195
0.0037
0.7067
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.934
0.962
0.832
0.941
0.973
--
Recall/Completeness
0.915
0.964
0.890
0.926
0.707
--
F1
0.924
0.963
0.860
0.934
0.819
--

Overall accuracy 0.922

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
0.8654
0.0584
0.0511
0.0186
0.0014
0.0051
building
0.0289
0.9345
0.0235
0.0123
0.0000
0.0008
low_veg
0.0808
0.0324
0.7281
0.1585
0.0002
0.0000
tree
0.0178
0.0088
0.0996
0.8738
0.0000
0.0000
car
0.3658
0.0016
0.0082
0.0044
0.6199
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.922
0.882
0.739
0.826
0.891
--
Recall/Completeness
0.865
0.935
0.728
0.874
0.620
--
F1
0.893
0.908
0.733
0.849
0.731
--

Overall accuracy 0.858

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area10_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8973
0.0466
0.0418
0.0081
0.0006
0.0055
building
0.0220
0.9503
0.0181
0.0088
0.0000
0.0008
low_veg
0.0767
0.0213
0.7682
0.1336
0.0002
0.0000
tree
0.0088
0.0044
0.0766
0.9101
0.0000
0.0000
car
0.2678
0.0014
0.0030
0.0008
0.7271
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.941
0.911
0.784
0.867
0.933
--
Recall/Completeness
0.897
0.950
0.768
0.910
0.727
--
F1
0.919
0.930
0.776
0.888
0.817
--

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_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8853
0.0275
0.0481
0.0367
0.0024
0.0000
building
0.1072
0.8762
0.0097
0.0069
0.0000
0.0000
low_veg
0.0462
0.0283
0.7210
0.2036
0.0004
0.0005
tree
0.0103
0.0082
0.0809
0.9006
0.0000
0.0000
car
0.2067
0.0000
0.0001
0.0083
0.7848
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.764
0.917
0.844
0.835
0.898
--
Recall/Completeness
0.885
0.876
0.721
0.901
0.785
--
F1
0.820
0.896
0.778
0.867
0.838
--

Overall accuracy 0.841

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
0.9136
0.0244
0.0399
0.0218
0.0004
0.0000
building
0.1102
0.8836
0.0043
0.0020
0.0000
0.0000
low_veg
0.0435
0.0173
0.7592
0.1791
0.0003
0.0006
tree
0.0053
0.0037
0.0649
0.9261
0.0000
0.0000
car
0.0884
0.0000
0.0000
0.0017
0.9099
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.784
0.946
0.875
0.864
0.959
--
Recall/Completeness
0.914
0.884
0.759
0.926
0.910
--
F1
0.844
0.914
0.813
0.894
0.934
--

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_area14_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8520
0.0273
0.0850
0.0339
0.0018
0.0000
building
0.0264
0.9504
0.0176
0.0056
0.0000
0.0000
low_veg
0.0882
0.0527
0.6999
0.1587
0.0004
0.0000
tree
0.0270
0.0150
0.1203
0.8377
0.0000
0.0000
car
0.2685
0.0000
0.0000
0.0062
0.7253
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.842
0.871
0.739
0.851
0.781
--
Recall/Completeness
0.852
0.950
0.700
0.838
0.725
--
F1
0.847
0.909
0.719
0.844
0.752
--

Overall accuracy 0.825

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area14_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8712
0.0229
0.0813
0.0234
0.0012
0.0000
building
0.0200
0.9703
0.0080
0.0017
0.0000
0.0000
low_veg
0.0823
0.0384
0.7302
0.1487
0.0004
0.0000
tree
0.0185
0.0082
0.1081
0.8652
0.0000
0.0000
car
0.1523
0.0000
0.0000
0.0019
0.8458
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.869
0.905
0.761
0.873
0.809
--
Recall/Completeness
0.871
0.970
0.730
0.865
0.846
--
F1
0.870
0.937
0.745
0.869
0.827
--

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
0.8467
0.0250
0.0684
0.0580
0.0019
0.0000
building
0.0430
0.9190
0.0246
0.0133
0.0000
0.0000
low_veg
0.0290
0.0159
0.8082
0.1469
0.0001
0.0000
tree
0.0243
0.0052
0.1007
0.8698
0.0000
0.0000
car
0.1810
0.0076
0.0043
0.0021
0.8051
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.837
0.940
0.822
0.853
0.847
--
Recall/Completeness
0.847
0.919
0.808
0.870
0.805
--
F1
0.842
0.929
0.815
0.861
0.826
--

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_area16_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8821
0.0198
0.0602
0.0373
0.0006
0.0000
building
0.0396
0.9423
0.0129
0.0053
0.0000
0.0000
low_veg
0.0247
0.0098
0.8344
0.1310
0.0001
0.0000
tree
0.0166
0.0023
0.0880
0.8931
0.0000
0.0000
car
0.0952
0.0032
0.0000
0.0000
0.9016
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.865
0.962
0.850
0.878
0.925
--
Recall/Completeness
0.882
0.942
0.834
0.893
0.902
--
F1
0.874
0.952
0.842
0.886
0.913
--

Overall accuracy 0.883

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
0.8598
0.0383
0.0474
0.0530
0.0015
0.0000
building
0.0201
0.9654
0.0076
0.0069
0.0000
0.0000
low_veg
0.0620
0.0297
0.6619
0.2463
0.0001
0.0000
tree
0.0064
0.0019
0.0386
0.9531
0.0000
0.0000
car
0.3081
0.0000
0.0429
0.0153
0.6337
0.0000
clutter
0.0359
0.9453
0.0180
0.0008
0.0000
0.0000
Precision/Correctness
0.896
0.799
0.824
0.868
0.890
-nan
Recall/Completeness
0.860
0.965
0.662
0.953
0.634
0.000
F1
0.877
0.874
0.734
0.909
0.740
-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_area20_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8905
0.0315
0.0451
0.0320
0.0009
0.0000
building
0.0173
0.9775
0.0032
0.0020
0.0000
0.0000
low_veg
0.0547
0.0197
0.7070
0.2185
0.0001
0.0000
tree
0.0024
0.0005
0.0283
0.9688
0.0000
0.0000
car
0.2144
0.0000
0.0359
0.0048
0.7449
0.0000
clutter
0.0191
0.9659
0.0151
0.0000
0.0000
0.0000
Precision/Correctness
0.922
0.813
0.856
0.896
0.920
-nan
Recall/Completeness
0.891
0.977
0.707
0.969
0.745
0.000
F1
0.906
0.888
0.774
0.931
0.823
-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_area22_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8963
0.0207
0.0431
0.0351
0.0048
0.0000
building
0.0375
0.9334
0.0200
0.0084
0.0007
0.0000
low_veg
0.0914
0.0288
0.7053
0.1739
0.0006
0.0000
tree
0.0209
0.0031
0.0479
0.9281
0.0001
0.0000
car
0.3553
0.0000
0.0054
0.0132
0.6261
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.891
0.926
0.820
0.848
0.793
--
Recall/Completeness
0.896
0.933
0.705
0.928
0.626
--
F1
0.894
0.930
0.758
0.886
0.700
--

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_area22_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9273
0.0142
0.0366
0.0185
0.0033
0.0000
building
0.0326
0.9517
0.0113
0.0039
0.0006
0.0000
low_veg
0.0896
0.0165
0.7491
0.1444
0.0004
0.0000
tree
0.0087
0.0006
0.0335
0.9572
0.0000
0.0000
car
0.2487
0.0000
0.0028
0.0053
0.7433
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.915
0.956
0.861
0.887
0.825
--
Recall/Completeness
0.927
0.952
0.749
0.957
0.743
--
F1
0.921
0.954
0.801
0.921
0.782
--

Overall accuracy 0.904

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
0.8279
0.0315
0.0999
0.0380
0.0027
0.0000
building
0.0583
0.9009
0.0229
0.0179
0.0000
0.0000
low_veg
0.0250
0.0203
0.8809
0.0737
0.0002
0.0000
tree
0.0158
0.0075
0.1596
0.8172
0.0000
0.0000
car
0.4007
0.0000
0.0107
0.0104
0.5782
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.818
0.920
0.859
0.841
0.827
--
Recall/Completeness
0.828
0.901
0.881
0.817
0.578
--
F1
0.823
0.910
0.870
0.829
0.681
--

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_area24_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8598
0.0208
0.0901
0.0274
0.0019
0.0000
building
0.0574
0.9136
0.0139
0.0151
0.0000
0.0000
low_veg
0.0218
0.0157
0.8997
0.0627
0.0002
0.0000
tree
0.0097
0.0037
0.1376
0.8490
0.0000
0.0000
car
0.3001
0.0000
0.0010
0.0064
0.6925
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.841
0.944
0.883
0.865
0.845
--
Recall/Completeness
0.860
0.914
0.900
0.849
0.693
--
F1
0.850
0.928
0.891
0.857
0.761
--

Overall accuracy 0.883

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
0.9395
0.0298
0.0189
0.0078
0.0040
0.0000
building
0.0708
0.9052
0.0194
0.0043
0.0003
0.0000
low_veg
0.0903
0.0294
0.6751
0.2049
0.0003
0.0000
tree
0.0137
0.0060
0.0638
0.9164
0.0001
0.0000
car
0.3905
0.0069
0.0064
0.0063
0.5898
0.0000
clutter
0.6528
0.1569
0.1134
0.0286
0.0483
0.0000
Precision/Correctness
0.838
0.950
0.870
0.674
0.924
-nan
Recall/Completeness
0.939
0.905
0.675
0.916
0.590
0.000
F1
0.886
0.927
0.760
0.777
0.720
-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_area27_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9627
0.0204
0.0123
0.0036
0.0010
0.0000
building
0.0582
0.9258
0.0139
0.0018
0.0002
0.0000
low_veg
0.0702
0.0176
0.7186
0.1936
0.0000
0.0000
tree
0.0058
0.0022
0.0472
0.9448
0.0000
0.0000
car
0.2781
0.0055
0.0051
0.0054
0.7059
0.0000
clutter
0.6787
0.1505
0.0975
0.0158
0.0576
0.0000
Precision/Correctness
0.876
0.970
0.907
0.705
0.970
-nan
Recall/Completeness
0.963
0.926
0.719
0.945
0.706
0.000
F1
0.917
0.947
0.802
0.808
0.817
-nan

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_area29_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9389
0.0191
0.0243
0.0144
0.0032
0.0000
building
0.0233
0.9580
0.0131
0.0055
0.0000
0.0000
low_veg
0.0618
0.0244
0.6301
0.2835
0.0001
0.0000
tree
0.0054
0.0026
0.0296
0.9624
0.0000
0.0000
car
0.3500
0.0056
0.0001
0.0127
0.6317
0.0000
clutter
0.6364
0.2271
0.0278
0.0039
0.0751
0.0296
Precision/Correctness
0.909
0.933
0.839
0.679
0.700
1.000
Recall/Completeness
0.939
0.958
0.630
0.962
0.632
0.030
F1
0.924
0.945
0.720
0.796
0.664
0.058

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_area29_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9591
0.0131
0.0177
0.0075
0.0026
0.0000
building
0.0171
0.9724
0.0078
0.0027
0.0000
0.0000
low_veg
0.0383
0.0114
0.6759
0.2744
0.0000
0.0000
tree
0.0015
0.0008
0.0207
0.9770
0.0000
0.0000
car
0.2520
0.0014
0.0000
0.0098
0.7367
0.0000
clutter
0.6195
0.2382
0.0214
0.0005
0.0849
0.0355
Precision/Correctness
0.934
0.952
0.880
0.714
0.688
1.000
Recall/Completeness
0.959
0.972
0.676
0.977
0.737
0.035
F1
0.946
0.962
0.765
0.825
0.711
0.069

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_area31_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9626
0.0202
0.0086
0.0053
0.0028
0.0005
building
0.0645
0.9233
0.0087
0.0019
0.0015
0.0001
low_veg
0.0384
0.0051
0.9076
0.0448
0.0002
0.0039
tree
0.0345
0.0032
0.0994
0.8627
0.0002
0.0000
car
0.2814
0.1536
0.0053
0.0061
0.5535
0.0000
clutter
0.4345
0.2759
0.0257
0.0118
0.0268
0.2253
Precision/Correctness
0.878
0.915
0.882
0.908
0.890
0.907
Recall/Completeness
0.963
0.923
0.908
0.863
0.553
0.225
F1
0.918
0.919
0.895
0.885
0.682
0.361

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_area31_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9749
0.0170
0.0050
0.0017
0.0012
0.0001
building
0.0526
0.9424
0.0033
0.0004
0.0012
0.0001
low_veg
0.0185
0.0028
0.9385
0.0380
0.0000
0.0021
tree
0.0123
0.0005
0.0802
0.9070
0.0000
0.0000
car
0.1786
0.1838
0.0015
0.0023
0.6338
0.0000
clutter
0.3887
0.2976
0.0262
0.0053
0.0294
0.2528
Precision/Correctness
0.913
0.928
0.918
0.937
0.915
0.952
Recall/Completeness
0.975
0.942
0.939
0.907
0.634
0.253
F1
0.943
0.935
0.928
0.922
0.749
0.400

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_area33_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9708
0.0119
0.0127
0.0034
0.0011
0.0000
building
0.0433
0.9002
0.0308
0.0226
0.0031
0.0000
low_veg
0.0637
0.0081
0.8726
0.0551
0.0005
0.0000
tree
0.0446
0.0027
0.1284
0.8243
0.0000
0.0000
car
0.3935
0.0016
0.0027
0.0056
0.5936
0.0030
clutter
0.7291
0.1145
0.0014
0.0030
0.0380
0.1139
Precision/Correctness
0.839
0.955
0.831
0.839
0.688
0.991
Recall/Completeness
0.971
0.900
0.873
0.824
0.594
0.114
F1
0.900
0.927
0.851
0.832
0.637
0.204

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_area33_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9809
0.0097
0.0079
0.0009
0.0007
0.0000
building
0.0351
0.9151
0.0260
0.0209
0.0029
0.0000
low_veg
0.0344
0.0029
0.9108
0.0514
0.0005
0.0000
tree
0.0194
0.0004
0.1200
0.8601
0.0000
0.0000
car
0.2651
0.0005
0.0000
0.0034
0.7278
0.0032
clutter
0.7046
0.1250
0.0005
0.0011
0.0412
0.1276
Precision/Correctness
0.872
0.963
0.856
0.859
0.689
0.995
Recall/Completeness
0.981
0.915
0.911
0.860
0.728
0.128
F1
0.923
0.939
0.883
0.859
0.708
0.226

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_area35_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8686
0.0398
0.0650
0.0253
0.0013
0.0000
building
0.0438
0.9289
0.0203
0.0065
0.0006
0.0000
low_veg
0.0600
0.0124
0.6614
0.2657
0.0005
0.0000
tree
0.0269
0.0052
0.0805
0.8873
0.0001
0.0000
car
0.3553
0.0188
0.0072
0.0105
0.6082
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.860
0.945
0.802
0.737
0.881
--
Recall/Completeness
0.869
0.929
0.661
0.887
0.608
--
F1
0.864
0.937
0.725
0.805
0.720
--

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_area35_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9122
0.0355
0.0441
0.0074
0.0008
0.0000
building
0.0327
0.9557
0.0094
0.0016
0.0005
0.0000
low_veg
0.0464
0.0050
0.6918
0.2563
0.0005
0.0000
tree
0.0086
0.0012
0.0589
0.9314
0.0000
0.0000
car
0.2413
0.0200
0.0039
0.0044
0.7303
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.904
0.963
0.863
0.766
0.901
--
Recall/Completeness
0.912
0.956
0.692
0.931
0.730
--
F1
0.908
0.959
0.768
0.840
0.807
--

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_area38_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9149
0.0219
0.0444
0.0166
0.0022
0.0000
building
0.0505
0.8977
0.0440
0.0066
0.0012
0.0000
low_veg
0.0452
0.0290
0.8155
0.1103
0.0000
0.0000
tree
0.0216
0.0038
0.1125
0.8621
0.0000
0.0000
car
0.3178
0.0143
0.0454
0.0081
0.6144
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.882
0.939
0.834
0.819
0.866
--
Recall/Completeness
0.915
0.898
0.816
0.862
0.614
--
F1
0.898
0.918
0.825
0.840
0.719
--

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_area38_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9418
0.0194
0.0316
0.0063
0.0009
0.0000
building
0.0414
0.9255
0.0299
0.0021
0.0011
0.0000
low_veg
0.0281
0.0263
0.8528
0.0929
0.0000
0.0000
tree
0.0077
0.0013
0.0913
0.8997
0.0000
0.0000
car
0.2101
0.0154
0.0384
0.0035
0.7326
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.921
0.950
0.874
0.859
0.910
--
Recall/Completeness
0.942
0.926
0.853
0.900
0.733
--
F1
0.931
0.938
0.863
0.879
0.812
--

Overall accuracy 0.904

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image