Detailled semantic labeling (2D) result


Name W. Sun
Affiliation Univ. of Calgary, Canada
Abbreviation UCal2
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
0.902
0.033
0.043
0.018
0.004
0.000
building
0.056
0.910
0.029
0.005
0.000
0.000
low_veg
0.055
0.031
0.776
0.138
0.000
0.000
tree
0.021
0.006
0.088
0.886
0.000
0.000
car
0.387
0.042
0.011
0.007
0.553
0.000
clutter
0.437
0.271
0.017
0.010
0.009
0.257
Precision/Correctness
0.863
0.922
0.809
0.846
0.857
0.977
Recall/Completeness
0.902
0.910
0.776
0.886
0.553
0.257
F1
0.882
0.916
0.792
0.865
0.672
0.406

Overall accuracy 0.863

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
0.930
0.024
0.035
0.009
0.002
0.000
building
0.048
0.928
0.022
0.002
0.000
0.000
low_veg
0.042
0.021
0.815
0.123
0.000
0.000
tree
0.009
0.002
0.071
0.918
0.000
0.000
car
0.293
0.048
0.009
0.003
0.647
0.000
clutter
0.397
0.289
0.013
0.004
0.009
0.288
Precision/Correctness
0.896
0.945
0.845
0.877
0.916
0.983
Recall/Completeness
0.930
0.928
0.815
0.918
0.647
0.288
F1
0.912
0.936
0.829
0.897
0.758
0.445

Overall accuracy 0.894
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9406
0.0111
0.0294
0.0145
0.0043
0.0000
building
0.0479
0.9234
0.0247
0.0040
0.0000
0.0000
low_veg
0.0828
0.0229
0.7213
0.1729
0.0001
0.0000
tree
0.0290
0.0066
0.0807
0.8830
0.0001
0.0006
car
0.3655
0.0122
0.0001
0.0025
0.6197
0.0000
clutter
0.0142
0.0000
0.0000
0.0237
0.0000
0.9622
Precision/Correctness
0.841
0.954
0.843
0.822
0.896
0.992
Recall/Completeness
0.941
0.923
0.721
0.883
0.620
0.962
F1
0.888
0.938
0.777
0.851
0.733
0.977

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_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9669
0.0069
0.0191
0.0050
0.0022
0.0000
building
0.0398
0.9440
0.0153
0.0010
0.0000
0.0000
low_veg
0.0656
0.0115
0.7570
0.1658
0.0000
0.0000
tree
0.0137
0.0027
0.0694
0.9140
0.0000
0.0002
car
0.2493
0.0132
0.0000
0.0009
0.7366
0.0000
clutter
0.0145
0.0000
0.0000
0.0064
0.0000
0.9791
Precision/Correctness
0.882
0.977
0.876
0.847
0.941
0.997
Recall/Completeness
0.967
0.944
0.757
0.914
0.737
0.979
F1
0.923
0.960
0.812
0.879
0.826
0.988

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_area4_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9381
0.0448
0.0098
0.0035
0.0038
0.0000
building
0.0845
0.9070
0.0068
0.0014
0.0002
0.0000
low_veg
0.2054
0.0743
0.4787
0.2416
0.0000
0.0000
tree
0.0631
0.0134
0.0644
0.8587
0.0003
0.0000
car
0.5030
0.0145
0.0000
0.0009
0.4816
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.804
0.967
0.686
0.766
0.848
--
Recall/Completeness
0.938
0.907
0.479
0.859
0.482
--
F1
0.866
0.936
0.564
0.810
0.614
--

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_area4_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9658
0.0239
0.0075
0.0011
0.0016
0.0000
building
0.0691
0.9243
0.0058
0.0005
0.0002
0.0000
low_veg
0.1644
0.0370
0.5304
0.2682
0.0000
0.0000
tree
0.0276
0.0042
0.0601
0.9081
0.0000
0.0000
car
0.4251
0.0117
0.0000
0.0003
0.5629
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.838
0.984
0.717
0.790
0.911
--
Recall/Completeness
0.966
0.924
0.530
0.908
0.563
--
F1
0.897
0.953
0.610
0.845
0.696
--

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_area6_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9062
0.0389
0.0407
0.0116
0.0025
0.0000
building
0.0671
0.9071
0.0220
0.0038
0.0001
0.0000
low_veg
0.0716
0.0273
0.7716
0.1294
0.0001
0.0000
tree
0.0153
0.0034
0.0560
0.9252
0.0001
0.0000
car
0.5844
0.0182
0.0097
0.0058
0.3819
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.841
0.955
0.708
0.936
0.899
--
Recall/Completeness
0.906
0.907
0.772
0.925
0.382
--
F1
0.872
0.931
0.738
0.931
0.536
--

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_area6_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9420
0.0224
0.0310
0.0040
0.0007
0.0000
building
0.0559
0.9271
0.0157
0.0013
0.0001
0.0000
low_veg
0.0530
0.0111
0.8270
0.1089
0.0000
0.0000
tree
0.0050
0.0007
0.0415
0.9528
0.0000
0.0000
car
0.5080
0.0107
0.0091
0.0023
0.4699
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.880
0.978
0.759
0.959
0.967
--
Recall/Completeness
0.942
0.927
0.827
0.953
0.470
--
F1
0.910
0.952
0.792
0.956
0.632
--

Overall accuracy 0.923

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
0.8780
0.0303
0.0749
0.0133
0.0035
0.0000
building
0.0331
0.9453
0.0183
0.0033
0.0000
0.0000
low_veg
0.0516
0.0157
0.8712
0.0608
0.0007
0.0000
tree
0.0263
0.0062
0.0800
0.8874
0.0000
0.0000
car
0.3895
0.0082
0.0275
0.0072
0.5676
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.900
0.939
0.784
0.926
0.885
--
Recall/Completeness
0.878
0.945
0.871
0.887
0.568
--
F1
0.889
0.942
0.825
0.906
0.692
--

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_area8_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9077
0.0226
0.0638
0.0045
0.0012
0.0000
building
0.0243
0.9645
0.0101
0.0011
0.0000
0.0000
low_veg
0.0361
0.0065
0.9098
0.0475
0.0001
0.0000
tree
0.0111
0.0024
0.0609
0.9255
0.0000
0.0000
car
0.2960
0.0044
0.0217
0.0051
0.6729
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.936
0.963
0.826
0.953
0.954
--
Recall/Completeness
0.908
0.964
0.910
0.926
0.673
--
F1
0.922
0.964
0.866
0.939
0.789
--

Overall accuracy 0.923

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
0.8322
0.0847
0.0629
0.0188
0.0014
0.0000
building
0.0386
0.9289
0.0220
0.0104
0.0000
0.0000
low_veg
0.0695
0.0347
0.7434
0.1522
0.0001
0.0000
tree
0.0179
0.0087
0.0867
0.8867
0.0000
0.0000
car
0.4216
0.0191
0.0049
0.0031
0.5513
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.918
0.846
0.737
0.834
0.872
--
Recall/Completeness
0.832
0.929
0.743
0.887
0.551
--
F1
0.873
0.886
0.740
0.860
0.675
--

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_area10_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8644
0.0719
0.0543
0.0088
0.0006
0.0000
building
0.0326
0.9439
0.0163
0.0073
0.0000
0.0000
low_veg
0.0675
0.0204
0.7859
0.1261
0.0001
0.0000
tree
0.0067
0.0040
0.0656
0.9236
0.0000
0.0000
car
0.3324
0.0230
0.0016
0.0000
0.6429
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.937
0.877
0.778
0.875
0.937
--
Recall/Completeness
0.864
0.944
0.786
0.924
0.643
--
F1
0.899
0.909
0.782
0.898
0.763
--

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
0.8849
0.0302
0.0514
0.0310
0.0026
0.0000
building
0.1153
0.8614
0.0153
0.0081
0.0000
0.0000
low_veg
0.0311
0.0347
0.7722
0.1620
0.0000
0.0000
tree
0.0081
0.0073
0.0921
0.8926
0.0000
0.0000
car
0.3171
0.0012
0.0006
0.0170
0.6641
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.779
0.906
0.835
0.862
0.898
--
Recall/Completeness
0.885
0.861
0.772
0.893
0.664
--
F1
0.829
0.883
0.802
0.877
0.764
--

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_area12_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9143
0.0261
0.0434
0.0158
0.0005
0.0000
building
0.1202
0.8696
0.0074
0.0028
0.0000
0.0000
low_veg
0.0285
0.0224
0.8133
0.1358
0.0000
0.0000
tree
0.0033
0.0027
0.0756
0.9184
0.0000
0.0000
car
0.2114
0.0004
0.0004
0.0072
0.7805
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.796
0.938
0.866
0.892
0.977
--
Recall/Completeness
0.914
0.870
0.813
0.918
0.780
--
F1
0.851
0.903
0.839
0.905
0.868
--

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_area14_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8537
0.0293
0.0807
0.0323
0.0040
0.0000
building
0.0102
0.9618
0.0215
0.0065
0.0000
0.0000
low_veg
0.0624
0.0500
0.7359
0.1514
0.0000
0.0002
tree
0.0205
0.0128
0.1081
0.8585
0.0000
0.0000
car
0.2182
0.0000
0.0000
0.0052
0.7767
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.886
0.877
0.762
0.859
0.687
--
Recall/Completeness
0.854
0.962
0.736
0.858
0.777
--
F1
0.870
0.917
0.749
0.859
0.729
--

Overall accuracy 0.844

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
0.8744
0.0239
0.0768
0.0218
0.0032
0.0000
building
0.0066
0.9795
0.0117
0.0022
0.0000
0.0000
low_veg
0.0571
0.0335
0.7698
0.1393
0.0000
0.0002
tree
0.0125
0.0065
0.0952
0.8857
0.0000
0.0000
car
0.1137
0.0000
0.0000
0.0019
0.8844
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.911
0.914
0.786
0.882
0.699
--
Recall/Completeness
0.874
0.979
0.770
0.886
0.884
--
F1
0.893
0.945
0.778
0.884
0.781
--

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_area16_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8189
0.0366
0.0886
0.0537
0.0021
0.0001
building
0.0385
0.9229
0.0268
0.0117
0.0002
0.0000
low_veg
0.0154
0.0173
0.8399
0.1270
0.0000
0.0005
tree
0.0212
0.0051
0.1053
0.8683
0.0000
0.0001
car
0.2828
0.0023
0.0092
0.0104
0.6953
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.865
0.928
0.813
0.869
0.817
--
Recall/Completeness
0.819
0.923
0.840
0.868
0.695
--
F1
0.841
0.926
0.826
0.869
0.751
--

Overall accuracy 0.862

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area16_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8537
0.0316
0.0801
0.0337
0.0008
0.0001
building
0.0355
0.9430
0.0166
0.0047
0.0001
0.0000
low_veg
0.0116
0.0104
0.8658
0.1118
0.0000
0.0005
tree
0.0139
0.0016
0.0914
0.8932
0.0000
0.0000
car
0.1945
0.0001
0.0047
0.0048
0.7958
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.894
0.953
0.841
0.894
0.897
--
Recall/Completeness
0.854
0.943
0.866
0.893
0.796
--
F1
0.874
0.948
0.853
0.893
0.843
--

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_area20_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8566
0.0472
0.0461
0.0475
0.0027
0.0000
building
0.0116
0.9564
0.0257
0.0062
0.0000
0.0000
low_veg
0.0391
0.0363
0.7528
0.1718
0.0000
0.0000
tree
0.0079
0.0022
0.0527
0.9372
0.0000
0.0000
car
0.3313
0.0092
0.0382
0.0109
0.6103
0.0000
clutter
0.0308
0.9659
0.0029
0.0004
0.0000
0.0000
Precision/Correctness
0.920
0.782
0.805
0.898
0.822
-nan
Recall/Completeness
0.857
0.956
0.753
0.937
0.610
0.000
F1
0.887
0.860
0.778
0.917
0.700
-nan

Overall accuracy 0.862

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area20_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8895
0.0371
0.0433
0.0286
0.0015
0.0000
building
0.0098
0.9665
0.0215
0.0022
0.0000
0.0000
low_veg
0.0334
0.0236
0.8000
0.1429
0.0000
0.0000
tree
0.0033
0.0004
0.0403
0.9560
0.0000
0.0000
car
0.2417
0.0050
0.0329
0.0026
0.7178
0.0000
clutter
0.0222
0.9762
0.0016
0.0000
0.0000
0.0000
Precision/Correctness
0.944
0.803
0.835
0.925
0.874
-nan
Recall/Completeness
0.890
0.967
0.800
0.956
0.718
0.000
F1
0.916
0.877
0.817
0.940
0.788
-nan

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: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8930
0.0291
0.0390
0.0362
0.0028
0.0000
building
0.0268
0.9505
0.0149
0.0078
0.0000
0.0000
low_veg
0.0753
0.0411
0.7273
0.1562
0.0000
0.0000
tree
0.0210
0.0039
0.0590
0.9160
0.0000
0.0000
car
0.4043
0.0095
0.0148
0.0188
0.5526
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.903
0.900
0.820
0.855
0.872
--
Recall/Completeness
0.893
0.950
0.727
0.916
0.553
--
F1
0.898
0.925
0.771
0.885
0.676
--

Overall accuracy 0.873

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
0.9267
0.0202
0.0329
0.0193
0.0009
0.0000
building
0.0204
0.9688
0.0070
0.0038
0.0000
0.0000
low_veg
0.0704
0.0254
0.7772
0.1270
0.0000
0.0000
tree
0.0084
0.0011
0.0431
0.9474
0.0000
0.0000
car
0.3093
0.0129
0.0126
0.0074
0.6578
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.931
0.937
0.861
0.895
0.948
--
Recall/Completeness
0.927
0.969
0.777
0.947
0.658
--
F1
0.929
0.952
0.817
0.921
0.777
--

Overall accuracy 0.909

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
0.8111
0.0504
0.0930
0.0415
0.0040
0.0000
building
0.0608
0.8710
0.0612
0.0070
0.0000
0.0000
low_veg
0.0201
0.0198
0.8807
0.0793
0.0000
0.0000
tree
0.0129
0.0066
0.1452
0.8352
0.0000
0.0000
car
0.3369
0.0000
0.0069
0.0042
0.6521
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.829
0.905
0.854
0.841
0.804
--
Recall/Completeness
0.811
0.871
0.881
0.835
0.652
--
F1
0.820
0.888
0.867
0.838
0.720
--

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
0.8435
0.0402
0.0850
0.0290
0.0023
0.0000
building
0.0578
0.8840
0.0542
0.0040
0.0000
0.0000
low_veg
0.0167
0.0148
0.9009
0.0676
0.0000
0.0000
tree
0.0069
0.0027
0.1229
0.8674
0.0000
0.0000
car
0.2234
0.0000
0.0024
0.0016
0.7726
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.856
0.931
0.876
0.867
0.857
--
Recall/Completeness
0.843
0.884
0.901
0.867
0.773
--
F1
0.850
0.907
0.888
0.867
0.813
--

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_area27_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9314
0.0279
0.0238
0.0071
0.0097
0.0000
building
0.0778
0.8958
0.0219
0.0042
0.0002
0.0000
low_veg
0.0913
0.0296
0.6672
0.2118
0.0001
0.0000
tree
0.0139
0.0053
0.0349
0.9458
0.0001
0.0000
car
0.4156
0.0102
0.0070
0.0048
0.5624
0.0000
clutter
0.6571
0.1469
0.1948
0.0012
0.0000
0.0000
Precision/Correctness
0.828
0.952
0.870
0.676
0.850
-nan
Recall/Completeness
0.931
0.896
0.667
0.946
0.562
0.000
F1
0.877
0.923
0.755
0.789
0.677
-nan

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_area27_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9584
0.0181
0.0169
0.0027
0.0038
0.0000
building
0.0651
0.9165
0.0168
0.0015
0.0002
0.0000
low_veg
0.0718
0.0143
0.7128
0.2011
0.0000
0.0000
tree
0.0055
0.0017
0.0224
0.9703
0.0000
0.0000
car
0.3281
0.0094
0.0051
0.0035
0.6539
0.0000
clutter
0.6757
0.1447
0.1796
0.0000
0.0000
0.0000
Precision/Correctness
0.866
0.973
0.905
0.706
0.926
-nan
Recall/Completeness
0.958
0.916
0.713
0.970
0.654
0.000
F1
0.910
0.944
0.797
0.817
0.767
-nan

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_area29_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9332
0.0244
0.0258
0.0131
0.0036
0.0000
building
0.0306
0.9505
0.0126
0.0062
0.0000
0.0000
low_veg
0.0702
0.0260
0.6243
0.2793
0.0002
0.0000
tree
0.0050
0.0035
0.0231
0.9684
0.0000
0.0000
car
0.3236
0.0006
0.0088
0.0122
0.6549
0.0000
clutter
0.5528
0.3756
0.0260
0.0115
0.0143
0.0198
Precision/Correctness
0.908
0.909
0.839
0.684
0.817
1.000
Recall/Completeness
0.933
0.951
0.624
0.968
0.655
0.020
F1
0.921
0.930
0.716
0.801
0.727
0.039

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_area29_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9550
0.0172
0.0199
0.0061
0.0019
0.0000
building
0.0242
0.9648
0.0077
0.0033
0.0000
0.0000
low_veg
0.0453
0.0113
0.6745
0.2688
0.0000
0.0000
tree
0.0010
0.0010
0.0163
0.9817
0.0000
0.0000
car
0.2330
0.0000
0.0097
0.0097
0.7476
0.0000
clutter
0.5376
0.3980
0.0209
0.0041
0.0157
0.0237
Precision/Correctness
0.932
0.932
0.875
0.720
0.858
1.000
Recall/Completeness
0.955
0.965
0.674
0.982
0.748
0.024
F1
0.943
0.948
0.762
0.831
0.799
0.046

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_area31_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9628
0.0162
0.0103
0.0045
0.0061
0.0001
building
0.0798
0.9070
0.0091
0.0024
0.0017
0.0000
low_veg
0.0697
0.0067
0.8901
0.0333
0.0003
0.0000
tree
0.0470
0.0040
0.0740
0.8739
0.0011
0.0000
car
0.2919
0.1914
0.0060
0.0055
0.5051
0.0001
clutter
0.5973
0.2067
0.0321
0.0179
0.0226
0.1234
Precision/Correctness
0.845
0.921
0.891
0.924
0.828
0.987
Recall/Completeness
0.963
0.907
0.890
0.874
0.505
0.123
F1
0.900
0.914
0.891
0.898
0.627
0.219

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_area31_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9767
0.0119
0.0081
0.0010
0.0023
0.0001
building
0.0676
0.9262
0.0043
0.0005
0.0015
0.0000
low_veg
0.0463
0.0039
0.9241
0.0257
0.0000
0.0000
tree
0.0183
0.0012
0.0580
0.9222
0.0004
0.0000
car
0.2121
0.2210
0.0027
0.0014
0.5629
0.0001
clutter
0.5610
0.2300
0.0281
0.0089
0.0261
0.1460
Precision/Correctness
0.881
0.935
0.922
0.956
0.883
0.995
Recall/Completeness
0.977
0.926
0.924
0.922
0.563
0.146
F1
0.926
0.931
0.923
0.939
0.687
0.255

Overall accuracy 0.911

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area33_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9677
0.0196
0.0087
0.0029
0.0009
0.0003
building
0.0761
0.8133
0.1040
0.0048
0.0002
0.0016
low_veg
0.0900
0.0219
0.8280
0.0598
0.0004
0.0000
tree
0.0487
0.0111
0.1270
0.8132
0.0000
0.0000
car
0.4067
0.0560
0.0044
0.0015
0.5313
0.0000
clutter
0.6753
0.0437
0.0021
0.0010
0.0045
0.2734
Precision/Correctness
0.818
0.940
0.731
0.879
0.906
0.963
Recall/Completeness
0.968
0.813
0.828
0.813
0.531
0.273
F1
0.887
0.872
0.776
0.845
0.670
0.426

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_area33_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9804
0.0137
0.0047
0.0008
0.0002
0.0001
building
0.0674
0.8246
0.1038
0.0023
0.0002
0.0017
low_veg
0.0575
0.0127
0.8701
0.0595
0.0002
0.0000
tree
0.0202
0.0077
0.1160
0.8561
0.0000
0.0000
car
0.2985
0.0585
0.0015
0.0002
0.6413
0.0000
clutter
0.6386
0.0417
0.0010
0.0003
0.0052
0.3131
Precision/Correctness
0.851
0.959
0.745
0.897
0.937
0.966
Recall/Completeness
0.980
0.825
0.870
0.856
0.641
0.313
F1
0.911
0.887
0.803
0.876
0.762
0.473

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_area35_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8422
0.0430
0.0847
0.0285
0.0016
0.0000
building
0.0442
0.9243
0.0243
0.0071
0.0001
0.0000
low_veg
0.0388
0.0152
0.7197
0.2263
0.0000
0.0000
tree
0.0319
0.0040
0.1056
0.8584
0.0001
0.0000
car
0.4237
0.0043
0.0055
0.0080
0.5585
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.868
0.941
0.773
0.755
0.901
--
Recall/Completeness
0.842
0.924
0.720
0.858
0.558
--
F1
0.855
0.932
0.745
0.803
0.689
--

Overall accuracy 0.835

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area35_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8928
0.0343
0.0616
0.0108
0.0004
0.0000
building
0.0353
0.9502
0.0126
0.0018
0.0001
0.0000
low_veg
0.0258
0.0056
0.7524
0.2162
0.0000
0.0000
tree
0.0115
0.0008
0.0803
0.9073
0.0000
0.0000
car
0.3154
0.0037
0.0028
0.0023
0.6757
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.914
0.964
0.832
0.787
0.965
--
Recall/Completeness
0.893
0.950
0.752
0.907
0.676
--
F1
0.903
0.957
0.790
0.843
0.795
--

Overall accuracy 0.877

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
0.9103
0.0224
0.0488
0.0162
0.0022
0.0000
building
0.0409
0.8921
0.0617
0.0046
0.0007
0.0000
low_veg
0.0451
0.0550
0.8179
0.0819
0.0002
0.0000
tree
0.0227
0.0024
0.1227
0.8522
0.0000
0.0000
car
0.3466
0.0205
0.0483
0.0127
0.5719
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.888
0.911
0.812
0.853
0.870
--
Recall/Completeness
0.910
0.892
0.818
0.852
0.572
--
F1
0.899
0.901
0.815
0.853
0.690
--

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: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9388
0.0186
0.0354
0.0063
0.0009
0.0000
building
0.0337
0.9181
0.0458
0.0018
0.0006
0.0000
low_veg
0.0281
0.0531
0.8537
0.0650
0.0001
0.0000
tree
0.0070
0.0005
0.0982
0.8944
0.0000
0.0000
car
0.2396
0.0231
0.0429
0.0070
0.6873
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.927
0.924
0.853
0.894
0.923
--
Recall/Completeness
0.939
0.918
0.854
0.894
0.687
--
F1
0.933
0.921
0.854
0.894
0.788
--

Overall accuracy 0.900

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image