Detailled semantic labeling (2D) result


Name Z. Xinwei
Affiliation Chinese Academy of Sciences, Institute of Software, China
Abbreviation CASZX1
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
0.901
0.036
0.038
0.018
0.006
0.000
building
0.051
0.921
0.022
0.006
0.000
0.000
low_veg
0.061
0.030
0.761
0.147
0.000
0.000
tree
0.023
0.006
0.098
0.873
0.000
0.000
car
0.305
0.042
0.005
0.005
0.643
0.000
clutter
0.314
0.301
0.010
0.009
0.021
0.345
Precision/Correctness
0.868
0.918
0.811
0.837
0.792
0.945
Recall/Completeness
0.901
0.921
0.761
0.873
0.643
0.345
F1
0.884
0.920
0.785
0.855
0.710
0.505

Overall accuracy 0.862

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
0.927
0.029
0.030
0.009
0.004
0.000
building
0.041
0.940
0.015
0.003
0.000
0.000
low_veg
0.048
0.022
0.795
0.134
0.000
0.000
tree
0.012
0.003
0.082
0.903
0.000
0.000
car
0.218
0.046
0.003
0.003
0.730
0.000
clutter
0.279
0.317
0.008
0.003
0.021
0.373
Precision/Correctness
0.900
0.938
0.845
0.865
0.828
0.965
Recall/Completeness
0.927
0.940
0.795
0.903
0.730
0.373
F1
0.913
0.939
0.819
0.883
0.776
0.538

Overall accuracy 0.890
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9348
0.0196
0.0213
0.0153
0.0089
0.0000
building
0.0420
0.9288
0.0249
0.0038
0.0004
0.0001
low_veg
0.0823
0.0374
0.6929
0.1871
0.0003
0.0000
tree
0.0294
0.0081
0.0962
0.8655
0.0001
0.0008
car
0.3519
0.0023
0.0007
0.0033
0.6418
0.0000
clutter
0.0045
0.0000
0.0005
0.0177
0.0000
0.9772
Precision/Correctness
0.846
0.930
0.830
0.808
0.804
0.988
Recall/Completeness
0.935
0.929
0.693
0.865
0.642
0.977
F1
0.888
0.929
0.755
0.836
0.714
0.983

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_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9611
0.0150
0.0122
0.0056
0.0061
0.0000
building
0.0324
0.9495
0.0166
0.0011
0.0004
0.0001
low_veg
0.0634
0.0300
0.7235
0.1829
0.0002
0.0000
tree
0.0165
0.0046
0.0844
0.8941
0.0000
0.0003
car
0.2642
0.0026
0.0000
0.0018
0.7314
0.0000
clutter
0.0039
0.0000
0.0005
0.0037
0.0000
0.9918
Precision/Correctness
0.887
0.949
0.861
0.830
0.841
0.996
Recall/Completeness
0.961
0.949
0.724
0.894
0.731
0.992
F1
0.922
0.949
0.786
0.861
0.782
0.994

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_area4_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9276
0.0540
0.0077
0.0051
0.0056
0.0000
building
0.0870
0.9029
0.0078
0.0018
0.0006
0.0000
low_veg
0.1812
0.0682
0.4484
0.3000
0.0022
0.0000
tree
0.0560
0.0168
0.0749
0.8510
0.0014
0.0000
car
0.4248
0.0320
0.0001
0.0009
0.5422
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.805
0.962
0.662
0.720
0.788
--
Recall/Completeness
0.928
0.903
0.448
0.851
0.542
--
F1
0.862
0.931
0.535
0.780
0.642
--

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_area4_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9527
0.0361
0.0057
0.0020
0.0035
0.0000
building
0.0727
0.9194
0.0065
0.0008
0.0006
0.0000
low_veg
0.1414
0.0444
0.4833
0.3294
0.0016
0.0000
tree
0.0279
0.0091
0.0680
0.8936
0.0014
0.0000
car
0.3556
0.0294
0.0000
0.0002
0.6148
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.835
0.977
0.692
0.747
0.822
--
Recall/Completeness
0.953
0.919
0.483
0.894
0.615
--
F1
0.890
0.947
0.569
0.814
0.704
--

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_area6_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8955
0.0565
0.0283
0.0118
0.0079
0.0000
building
0.0558
0.9224
0.0162
0.0056
0.0001
0.0000
low_veg
0.0883
0.0279
0.7254
0.1581
0.0003
0.0000
tree
0.0169
0.0040
0.0702
0.9087
0.0003
0.0000
car
0.3327
0.0220
0.0010
0.0019
0.6425
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.857
0.942
0.702
0.923
0.830
--
Recall/Completeness
0.896
0.922
0.725
0.909
0.642
--
F1
0.876
0.932
0.714
0.916
0.724
--

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_area6_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9289
0.0421
0.0193
0.0048
0.0049
0.0000
building
0.0439
0.9423
0.0111
0.0027
0.0000
0.0000
low_veg
0.0704
0.0150
0.7710
0.1435
0.0000
0.0000
tree
0.0079
0.0014
0.0572
0.9334
0.0002
0.0000
car
0.2507
0.0131
0.0000
0.0002
0.7360
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.894
0.963
0.745
0.945
0.876
--
Recall/Completeness
0.929
0.942
0.771
0.933
0.736
--
F1
0.911
0.952
0.758
0.939
0.800
--

Overall accuracy 0.917

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
0.8918
0.0291
0.0648
0.0093
0.0049
0.0000
building
0.0493
0.9320
0.0152
0.0035
0.0000
0.0000
low_veg
0.0609
0.0193
0.8537
0.0654
0.0007
0.0000
tree
0.0286
0.0067
0.0903
0.8737
0.0007
0.0000
car
0.3469
0.0024
0.0138
0.0049
0.6320
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.886
0.937
0.786
0.926
0.852
--
Recall/Completeness
0.892
0.932
0.854
0.874
0.632
--
F1
0.889
0.934
0.818
0.899
0.726
--

Overall accuracy 0.885

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
0.9165
0.0239
0.0540
0.0030
0.0026
0.0000
building
0.0381
0.9523
0.0083
0.0012
0.0000
0.0000
low_veg
0.0454
0.0115
0.8867
0.0559
0.0004
0.0000
tree
0.0134
0.0034
0.0701
0.9126
0.0005
0.0000
car
0.2514
0.0020
0.0072
0.0028
0.7366
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.922
0.956
0.828
0.948
0.901
--
Recall/Completeness
0.917
0.952
0.887
0.913
0.737
--
F1
0.919
0.954
0.856
0.930
0.811
--

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_area10_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8483
0.0796
0.0456
0.0208
0.0057
0.0000
building
0.0470
0.9234
0.0173
0.0118
0.0005
0.0000
low_veg
0.0835
0.0425
0.7255
0.1484
0.0001
0.0000
tree
0.0229
0.0093
0.0841
0.8836
0.0001
0.0000
car
0.2942
0.0200
0.0049
0.0038
0.6772
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.907
0.847
0.768
0.832
0.675
--
Recall/Completeness
0.848
0.923
0.726
0.884
0.677
--
F1
0.877
0.884
0.746
0.857
0.676
--

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_area10_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8776
0.0698
0.0376
0.0105
0.0045
0.0000
building
0.0385
0.9413
0.0114
0.0084
0.0004
0.0000
low_veg
0.0783
0.0324
0.7645
0.1248
0.0000
0.0000
tree
0.0121
0.0051
0.0645
0.9182
0.0001
0.0000
car
0.2090
0.0197
0.0028
0.0008
0.7676
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.928
0.872
0.811
0.871
0.686
--
Recall/Completeness
0.878
0.941
0.765
0.918
0.768
--
F1
0.902
0.905
0.787
0.894
0.725
--

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_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8714
0.0431
0.0503
0.0331
0.0021
0.0000
building
0.0347
0.9387
0.0198
0.0068
0.0000
0.0000
low_veg
0.0421
0.0250
0.7470
0.1844
0.0003
0.0012
tree
0.0098
0.0078
0.1099
0.8725
0.0000
0.0000
car
0.2269
0.0014
0.0001
0.0004
0.7713
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.840
0.917
0.808
0.844
0.909
--
Recall/Completeness
0.871
0.939
0.747
0.872
0.771
--
F1
0.855
0.928
0.776
0.858
0.834
--

Overall accuracy 0.848

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
0.8987
0.0406
0.0427
0.0174
0.0005
0.0000
building
0.0332
0.9561
0.0080
0.0026
0.0000
0.0000
low_veg
0.0392
0.0161
0.7773
0.1657
0.0002
0.0014
tree
0.0051
0.0039
0.0931
0.8979
0.0000
0.0000
car
0.1093
0.0004
0.0000
0.0000
0.8902
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.866
0.940
0.839
0.870
0.963
--
Recall/Completeness
0.899
0.956
0.777
0.898
0.890
--
F1
0.882
0.948
0.807
0.884
0.925
--

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_area14_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8015
0.0510
0.1092
0.0322
0.0061
0.0000
building
0.0138
0.9544
0.0261
0.0057
0.0000
0.0000
low_veg
0.0879
0.0448
0.7028
0.1641
0.0005
0.0000
tree
0.0298
0.0107
0.1333
0.8261
0.0002
0.0000
car
0.1870
0.0000
0.0000
0.0031
0.8099
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.839
0.863
0.706
0.847
0.577
--
Recall/Completeness
0.802
0.954
0.703
0.826
0.810
--
F1
0.820
0.906
0.705
0.836
0.674
--

Overall accuracy 0.812

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
0.8195
0.0473
0.1051
0.0228
0.0053
0.0000
building
0.0076
0.9752
0.0153
0.0019
0.0000
0.0000
low_veg
0.0817
0.0310
0.7312
0.1557
0.0004
0.0000
tree
0.0220
0.0055
0.1197
0.8527
0.0002
0.0000
car
0.0876
0.0000
0.0000
0.0000
0.9124
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.867
0.892
0.729
0.867
0.563
--
Recall/Completeness
0.820
0.975
0.731
0.853
0.912
--
F1
0.843
0.932
0.730
0.860
0.696
--

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_area16_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8319
0.0200
0.0894
0.0549
0.0039
0.0000
building
0.0303
0.9365
0.0227
0.0105
0.0000
0.0000
low_veg
0.0227
0.0164
0.8375
0.1228
0.0003
0.0002
tree
0.0248
0.0044
0.1252
0.8456
0.0000
0.0000
car
0.1906
0.0008
0.0253
0.0005
0.7828
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.856
0.946
0.796
0.869
0.719
--
Recall/Completeness
0.832
0.937
0.838
0.846
0.783
--
F1
0.844
0.941
0.816
0.857
0.750
--

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
0.8672
0.0148
0.0798
0.0354
0.0027
0.0000
building
0.0262
0.9577
0.0114
0.0048
0.0000
0.0000
low_veg
0.0184
0.0105
0.8605
0.1102
0.0003
0.0002
tree
0.0174
0.0017
0.1108
0.8701
0.0000
0.0000
car
0.1130
0.0000
0.0135
0.0000
0.8735
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.887
0.966
0.823
0.892
0.740
--
Recall/Completeness
0.867
0.958
0.860
0.870
0.874
--
F1
0.877
0.962
0.841
0.881
0.801
--

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
0.8429
0.0589
0.0426
0.0503
0.0053
0.0000
building
0.0143
0.9530
0.0244
0.0083
0.0000
0.0000
low_veg
0.0472
0.0383
0.7428
0.1713
0.0003
0.0001
tree
0.0109
0.0025
0.0528
0.9337
0.0000
0.0000
car
0.1534
0.0147
0.0086
0.0081
0.8152
0.0000
clutter
0.0095
0.9866
0.0033
0.0006
0.0000
0.0000
Precision/Correctness
0.910
0.768
0.807
0.896
0.748
0.000
Recall/Completeness
0.843
0.953
0.743
0.934
0.815
0.000
F1
0.875
0.851
0.774
0.914
0.780
-nan

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_area20_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8737
0.0525
0.0378
0.0326
0.0035
0.0000
building
0.0102
0.9674
0.0185
0.0038
0.0000
0.0000
low_veg
0.0424
0.0279
0.7849
0.1444
0.0002
0.0001
tree
0.0058
0.0011
0.0406
0.9525
0.0000
0.0000
car
0.0797
0.0137
0.0017
0.0039
0.9010
0.0000
clutter
0.0072
0.9914
0.0014
0.0000
0.0000
0.0000
Precision/Correctness
0.934
0.785
0.840
0.922
0.782
0.000
Recall/Completeness
0.874
0.967
0.785
0.952
0.901
0.000
F1
0.903
0.867
0.811
0.937
0.837
-nan

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_area22_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8929
0.0279
0.0392
0.0322
0.0078
0.0000
building
0.0310
0.9451
0.0157
0.0073
0.0008
0.0000
low_veg
0.0859
0.0407
0.7274
0.1452
0.0007
0.0001
tree
0.0255
0.0050
0.0640
0.9053
0.0002
0.0000
car
0.2595
0.0026
0.0071
0.0067
0.7241
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.896
0.901
0.813
0.864
0.737
--
Recall/Completeness
0.893
0.945
0.727
0.905
0.724
--
F1
0.895
0.922
0.768
0.884
0.730
--

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
0.9233
0.0214
0.0323
0.0174
0.0056
0.0000
building
0.0233
0.9659
0.0065
0.0037
0.0006
0.0000
low_veg
0.0810
0.0295
0.7687
0.1201
0.0006
0.0001
tree
0.0122
0.0021
0.0494
0.9362
0.0001
0.0000
car
0.1665
0.0025
0.0046
0.0013
0.8251
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.923
0.929
0.853
0.900
0.764
--
Recall/Completeness
0.923
0.966
0.769
0.936
0.825
--
F1
0.923
0.947
0.809
0.918
0.793
--

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
0.8383
0.0361
0.0833
0.0361
0.0062
0.0000
building
0.0635
0.8836
0.0386
0.0143
0.0000
0.0000
low_veg
0.0255
0.0223
0.8641
0.0878
0.0002
0.0000
tree
0.0164
0.0087
0.1566
0.8183
0.0000
0.0000
car
0.2021
0.0015
0.0020
0.0001
0.7944
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.817
0.909
0.857
0.825
0.749
--
Recall/Completeness
0.838
0.884
0.864
0.818
0.794
--
F1
0.827
0.896
0.861
0.822
0.771
--

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_area24_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8680
0.0279
0.0742
0.0253
0.0046
0.0000
building
0.0616
0.8948
0.0310
0.0125
0.0000
0.0000
low_veg
0.0221
0.0172
0.8832
0.0772
0.0003
0.0000
tree
0.0103
0.0043
0.1388
0.8465
0.0000
0.0000
car
0.0822
0.0023
0.0000
0.0000
0.9155
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.839
0.933
0.878
0.847
0.763
--
Recall/Completeness
0.868
0.895
0.883
0.847
0.916
--
F1
0.853
0.914
0.881
0.847
0.832
--

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_area27_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9318
0.0337
0.0181
0.0070
0.0095
0.0000
building
0.0862
0.8910
0.0178
0.0047
0.0003
0.0000
low_veg
0.1026
0.0290
0.6582
0.2095
0.0007
0.0000
tree
0.0195
0.0058
0.0649
0.9098
0.0001
0.0000
car
0.3640
0.0062
0.0026
0.0062
0.6210
0.0001
clutter
0.5324
0.3141
0.1176
0.0067
0.0292
0.0000
Precision/Correctness
0.820
0.945
0.872
0.669
0.858
0.000
Recall/Completeness
0.932
0.891
0.658
0.910
0.621
0.000
F1
0.872
0.917
0.750
0.771
0.720
-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
0.9568
0.0234
0.0122
0.0029
0.0046
0.0000
building
0.0742
0.9103
0.0132
0.0021
0.0002
0.0000
low_veg
0.0831
0.0170
0.6974
0.2021
0.0004
0.0000
tree
0.0097
0.0024
0.0494
0.9385
0.0000
0.0000
car
0.2746
0.0034
0.0010
0.0048
0.7161
0.0001
clutter
0.5796
0.2828
0.0981
0.0016
0.0380
0.0000
Precision/Correctness
0.855
0.966
0.906
0.696
0.913
0.000
Recall/Completeness
0.957
0.910
0.697
0.939
0.716
0.000
F1
0.903
0.938
0.788
0.799
0.803
-nan

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_area29_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9366
0.0201
0.0235
0.0133
0.0065
0.0000
building
0.0407
0.9352
0.0154
0.0084
0.0002
0.0000
low_veg
0.0686
0.0223
0.6188
0.2892
0.0012
0.0000
tree
0.0079
0.0019
0.0286
0.9616
0.0000
0.0000
car
0.3143
0.0081
0.0072
0.0105
0.6599
0.0000
clutter
0.4903
0.4303
0.0221
0.0149
0.0340
0.0084
Precision/Correctness
0.907
0.911
0.836
0.672
0.689
1.000
Recall/Completeness
0.937
0.935
0.619
0.962
0.660
0.008
F1
0.921
0.923
0.711
0.791
0.674
0.017

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_area29_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9577
0.0139
0.0173
0.0065
0.0045
0.0000
building
0.0337
0.9521
0.0091
0.0050
0.0001
0.0000
low_veg
0.0458
0.0132
0.6617
0.2784
0.0010
0.0000
tree
0.0034
0.0005
0.0203
0.9759
0.0000
0.0000
car
0.2501
0.0056
0.0077
0.0083
0.7282
0.0000
clutter
0.4716
0.4618
0.0163
0.0063
0.0342
0.0099
Precision/Correctness
0.930
0.929
0.877
0.709
0.709
1.000
Recall/Completeness
0.958
0.952
0.662
0.976
0.728
0.010
F1
0.943
0.941
0.754
0.821
0.718
0.020

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_area31_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9540
0.0159
0.0116
0.0058
0.0097
0.0030
building
0.0523
0.9384
0.0066
0.0016
0.0008
0.0003
low_veg
0.0508
0.0082
0.9005
0.0395
0.0009
0.0000
tree
0.0409
0.0130
0.0936
0.8511
0.0014
0.0000
car
0.2116
0.1841
0.0064
0.0046
0.5932
0.0001
clutter
0.4125
0.2417
0.0133
0.0137
0.0439
0.2750
Precision/Correctness
0.885
0.917
0.884
0.913
0.788
0.879
Recall/Completeness
0.954
0.938
0.901
0.851
0.593
0.275
F1
0.918
0.927
0.892
0.881
0.677
0.419

Overall accuracy 0.894

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
0.9701
0.0121
0.0079
0.0023
0.0055
0.0021
building
0.0398
0.9558
0.0032
0.0004
0.0006
0.0002
low_veg
0.0341
0.0041
0.9287
0.0327
0.0004
0.0000
tree
0.0198
0.0069
0.0777
0.8948
0.0008
0.0000
car
0.1394
0.2031
0.0040
0.0018
0.6517
0.0000
clutter
0.3662
0.2611
0.0121
0.0064
0.0460
0.3081
Precision/Correctness
0.918
0.933
0.915
0.941
0.830
0.913
Recall/Completeness
0.970
0.956
0.929
0.895
0.652
0.308
F1
0.943
0.944
0.922
0.917
0.730
0.461

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_area33_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9695
0.0128
0.0061
0.0041
0.0045
0.0030
building
0.0401
0.8990
0.0542
0.0050
0.0012
0.0005
low_veg
0.0757
0.0167
0.8302
0.0771
0.0003
0.0000
tree
0.0474
0.0051
0.1326
0.8149
0.0000
0.0000
car
0.3127
0.0108
0.0036
0.0066
0.6663
0.0000
clutter
0.4406
0.0660
0.0021
0.0005
0.0166
0.4742
Precision/Correctness
0.869
0.957
0.799
0.850
0.738
0.952
Recall/Completeness
0.969
0.899
0.830
0.815
0.666
0.474
F1
0.917
0.927
0.814
0.832
0.700
0.633

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_area33_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9831
0.0086
0.0027
0.0015
0.0030
0.0010
building
0.0315
0.9101
0.0536
0.0033
0.0012
0.0003
low_veg
0.0441
0.0091
0.8696
0.0770
0.0002
0.0000
tree
0.0258
0.0013
0.1213
0.8517
0.0000
0.0000
car
0.2235
0.0135
0.0013
0.0041
0.7576
0.0000
clutter
0.4089
0.0638
0.0011
0.0001
0.0184
0.5077
Precision/Correctness
0.901
0.971
0.816
0.868
0.754
0.980
Recall/Completeness
0.983
0.910
0.870
0.852
0.758
0.508
F1
0.940
0.940
0.842
0.860
0.756
0.669

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_area35_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8522
0.0605
0.0583
0.0266
0.0024
0.0000
building
0.0487
0.9189
0.0266
0.0056
0.0001
0.0000
low_veg
0.0605
0.0204
0.6853
0.2338
0.0000
0.0000
tree
0.0315
0.0074
0.1061
0.8549
0.0001
0.0000
car
0.3298
0.0246
0.0016
0.0093
0.6347
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.850
0.917
0.785
0.751
0.877
--
Recall/Completeness
0.852
0.919
0.685
0.855
0.635
--
F1
0.851
0.918
0.732
0.800
0.737
--

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
0.8917
0.0568
0.0390
0.0112
0.0013
0.0000
building
0.0364
0.9446
0.0167
0.0022
0.0001
0.0000
low_veg
0.0440
0.0118
0.7154
0.2289
0.0000
0.0000
tree
0.0123
0.0027
0.0842
0.9008
0.0000
0.0000
car
0.2242
0.0268
0.0015
0.0061
0.7413
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.897
0.938
0.839
0.776
0.925
--
Recall/Completeness
0.892
0.945
0.715
0.901
0.741
--
F1
0.894
0.941
0.772
0.834
0.823
--

Overall accuracy 0.865

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area38_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9132
0.0255
0.0417
0.0155
0.0041
0.0000
building
0.0317
0.9277
0.0341
0.0051
0.0012
0.0001
low_veg
0.0438
0.0439
0.8148
0.0972
0.0002
0.0000
tree
0.0184
0.0038
0.1126
0.8652
0.0002
0.0000
car
0.2562
0.0579
0.0120
0.0087
0.6651
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.903
0.920
0.845
0.838
0.809
--
Recall/Completeness
0.913
0.928
0.815
0.865
0.665
--
F1
0.908
0.924
0.830
0.851
0.730
--

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_area38_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9415
0.0228
0.0278
0.0053
0.0026
0.0000
building
0.0235
0.9519
0.0216
0.0018
0.0010
0.0001
low_veg
0.0279
0.0420
0.8487
0.0811
0.0002
0.0000
tree
0.0064
0.0014
0.0920
0.9001
0.0001
0.0000
car
0.1516
0.0680
0.0047
0.0031
0.7727
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.940
0.932
0.884
0.875
0.845
--
Recall/Completeness
0.942
0.952
0.849
0.900
0.773
--
F1
0.941
0.942
0.866
0.887
0.807
--

Overall accuracy 0.910

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image