Detailled semantic labeling (2D) result


Name B. Yu et al.
Affiliation Chinese Academy of Sciences, China
Abbreviation CAS_Y1
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
0.887
0.053
0.042
0.015
0.003
0.000
building
0.076
0.892
0.028
0.004
0.001
0.000
low_veg
0.051
0.031
0.777
0.141
0.000
0.000
tree
0.020
0.006
0.113
0.861
0.000
0.000
car
0.416
0.056
0.017
0.011
0.499
0.001
clutter
0.379
0.325
0.011
0.008
0.084
0.194
Precision/Correctness
0.849
0.898
0.790
0.845
0.771
0.956
Recall/Completeness
0.887
0.892
0.777
0.861
0.499
0.194
F1
0.868
0.895
0.783
0.853
0.606
0.322

Overall accuracy 0.847

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
0.914
0.044
0.033
0.007
0.002
0.000
building
0.069
0.908
0.021
0.002
0.001
0.000
low_veg
0.039
0.020
0.812
0.128
0.000
0.000
tree
0.009
0.002
0.093
0.895
0.000
0.000
car
0.326
0.056
0.012
0.006
0.599
0.001
clutter
0.346
0.338
0.007
0.002
0.089
0.217
Precision/Correctness
0.879
0.923
0.828
0.872
0.798
0.969
Recall/Completeness
0.914
0.908
0.812
0.895
0.599
0.217
F1
0.896
0.915
0.820
0.883
0.684
0.354

Overall accuracy 0.878
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9334
0.0249
0.0272
0.0110
0.0034
0.0000
building
0.0603
0.9100
0.0271
0.0025
0.0001
0.0000
low_veg
0.0608
0.0300
0.7532
0.1560
0.0000
0.0000
tree
0.0285
0.0046
0.1156
0.8505
0.0002
0.0005
car
0.4970
0.0175
0.0008
0.0033
0.4814
0.0000
clutter
0.2411
0.0012
0.0017
0.0262
0.0021
0.7277
Precision/Correctness
0.830
0.933
0.816
0.833
0.884
0.992
Recall/Completeness
0.933
0.910
0.753
0.851
0.481
0.728
F1
0.878
0.921
0.783
0.842
0.623
0.839

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_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9597
0.0192
0.0163
0.0026
0.0022
0.0000
building
0.0534
0.9282
0.0178
0.0006
0.0001
0.0000
low_veg
0.0449
0.0171
0.7870
0.1509
0.0000
0.0000
tree
0.0131
0.0017
0.1005
0.8844
0.0001
0.0002
car
0.3909
0.0140
0.0000
0.0008
0.5942
0.0000
clutter
0.2463
0.0012
0.0007
0.0075
0.0012
0.7432
Precision/Correctness
0.867
0.959
0.850
0.856
0.921
0.997
Recall/Completeness
0.960
0.928
0.787
0.884
0.594
0.743
F1
0.911
0.943
0.817
0.870
0.722
0.852

Overall accuracy 0.884

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area4_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9196
0.0635
0.0080
0.0048
0.0041
0.0001
building
0.0644
0.9267
0.0074
0.0012
0.0002
0.0000
low_veg
0.1229
0.0925
0.5340
0.2505
0.0001
0.0000
tree
0.0476
0.0157
0.1000
0.8367
0.0000
0.0000
car
0.4675
0.1027
0.0015
0.0031
0.4216
0.0037
clutter
--
--
--
--
--
--
Precision/Correctness
0.841
0.954
0.678
0.751
0.822
--
Recall/Completeness
0.920
0.927
0.534
0.837
0.422
--
F1
0.879
0.940
0.597
0.792
0.557
--

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_area4_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9498
0.0399
0.0046
0.0027
0.0028
0.0001
building
0.0522
0.9409
0.0061
0.0005
0.0003
0.0000
low_veg
0.0918
0.0458
0.5811
0.2814
0.0000
0.0000
tree
0.0199
0.0058
0.0873
0.8869
0.0000
0.0000
car
0.3922
0.0965
0.0011
0.0005
0.5059
0.0037
clutter
--
--
--
--
--
--
Precision/Correctness
0.872
0.974
0.721
0.771
0.854
--
Recall/Completeness
0.950
0.941
0.581
0.887
0.506
--
F1
0.909
0.957
0.643
0.825
0.635
--

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_area6_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8829
0.0739
0.0304
0.0088
0.0040
0.0001
building
0.0635
0.9216
0.0128
0.0018
0.0004
0.0000
low_veg
0.0948
0.0444
0.6965
0.1643
0.0000
0.0000
tree
0.0162
0.0043
0.0713
0.9081
0.0001
0.0000
car
0.5938
0.0551
0.0022
0.0051
0.3437
0.0001
clutter
--
--
--
--
--
--
Precision/Correctness
0.832
0.922
0.695
0.928
0.829
--
Recall/Completeness
0.883
0.922
0.697
0.908
0.344
--
F1
0.857
0.922
0.696
0.918
0.486
--

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_area6_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9174
0.0567
0.0202
0.0022
0.0034
0.0001
building
0.0544
0.9376
0.0072
0.0005
0.0003
0.0000
low_veg
0.0803
0.0280
0.7409
0.1509
0.0000
0.0000
tree
0.0062
0.0014
0.0552
0.9372
0.0000
0.0000
car
0.5222
0.0397
0.0005
0.0015
0.4360
0.0001
clutter
--
--
--
--
--
--
Precision/Correctness
0.868
0.948
0.751
0.948
0.850
--
Recall/Completeness
0.917
0.938
0.741
0.937
0.436
--
F1
0.892
0.943
0.746
0.942
0.576
--

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_area8_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8811
0.0393
0.0688
0.0081
0.0026
0.0000
building
0.0515
0.9247
0.0211
0.0026
0.0001
0.0000
low_veg
0.0489
0.0268
0.8493
0.0746
0.0004
0.0000
tree
0.0256
0.0085
0.1117
0.8542
0.0000
0.0000
car
0.4420
0.0305
0.0252
0.0053
0.4969
0.0001
clutter
--
--
--
--
--
--
Precision/Correctness
0.887
0.914
0.757
0.919
0.902
--
Recall/Completeness
0.881
0.925
0.849
0.854
0.497
--
F1
0.884
0.919
0.801
0.886
0.641
--

Overall accuracy 0.872

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area8_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9076
0.0318
0.0566
0.0022
0.0017
0.0000
building
0.0418
0.9440
0.0132
0.0010
0.0001
0.0000
low_veg
0.0317
0.0169
0.8868
0.0646
0.0000
0.0000
tree
0.0108
0.0040
0.0876
0.8976
0.0000
0.0000
car
0.3509
0.0279
0.0163
0.0029
0.6019
0.0001
clutter
--
--
--
--
--
--
Precision/Correctness
0.924
0.940
0.803
0.941
0.931
--
Recall/Completeness
0.908
0.944
0.887
0.898
0.602
--
F1
0.916
0.942
0.843
0.919
0.731
--

Overall accuracy 0.906

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
0.8134
0.1194
0.0487
0.0157
0.0028
0.0000
building
0.0658
0.8979
0.0253
0.0086
0.0024
0.0000
low_veg
0.0744
0.0494
0.7369
0.1390
0.0002
0.0000
tree
0.0163
0.0085
0.1056
0.8696
0.0000
0.0000
car
0.3818
0.0825
0.0415
0.0012
0.4925
0.0004
clutter
--
--
--
--
--
--
Precision/Correctness
0.898
0.792
0.737
0.847
0.678
--
Recall/Completeness
0.813
0.898
0.737
0.870
0.493
--
F1
0.854
0.841
0.737
0.858
0.571
--

Overall accuracy 0.829

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
0.8436
0.1091
0.0388
0.0066
0.0019
0.0000
building
0.0601
0.9125
0.0192
0.0059
0.0023
0.0000
low_veg
0.0706
0.0371
0.7764
0.1158
0.0002
0.0000
tree
0.0075
0.0037
0.0800
0.9089
0.0000
0.0000
car
0.3024
0.0994
0.0361
0.0000
0.5616
0.0004
clutter
--
--
--
--
--
--
Precision/Correctness
0.917
0.817
0.786
0.885
0.692
--
Recall/Completeness
0.844
0.913
0.776
0.909
0.562
--
F1
0.879
0.862
0.781
0.897
0.620
--

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_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8755
0.0370
0.0603
0.0264
0.0008
0.0000
building
0.1178
0.8562
0.0223
0.0035
0.0001
0.0000
low_veg
0.0315
0.0251
0.7678
0.1755
0.0001
0.0000
tree
0.0108
0.0078
0.1205
0.8609
0.0000
0.0000
car
0.4052
0.0049
0.0094
0.0138
0.5667
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.768
0.914
0.795
0.852
0.940
--
Recall/Completeness
0.875
0.856
0.768
0.861
0.567
--
F1
0.818
0.884
0.781
0.856
0.707
--

Overall accuracy 0.834

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
0.9025
0.0337
0.0507
0.0130
0.0002
0.0000
building
0.1223
0.8645
0.0120
0.0011
0.0002
0.0000
low_veg
0.0283
0.0148
0.8017
0.1550
0.0001
0.0000
tree
0.0053
0.0030
0.1004
0.8913
0.0000
0.0000
car
0.2771
0.0011
0.0059
0.0044
0.7115
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.787
0.943
0.829
0.878
0.969
--
Recall/Completeness
0.902
0.864
0.802
0.891
0.712
--
F1
0.841
0.902
0.815
0.885
0.821
--

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_area14_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8159
0.0807
0.0711
0.0293
0.0029
0.0000
building
0.0409
0.9326
0.0217
0.0046
0.0002
0.0000
low_veg
0.0736
0.0567
0.7231
0.1464
0.0003
0.0000
tree
0.0258
0.0117
0.1425
0.8201
0.0000
0.0000
car
0.2497
0.0057
0.0002
0.0109
0.7334
0.0001
clutter
--
--
--
--
--
--
Precision/Correctness
0.842
0.816
0.730
0.860
0.715
--
Recall/Completeness
0.816
0.933
0.723
0.820
0.733
--
F1
0.829
0.871
0.727
0.839
0.724
--

Overall accuracy 0.814

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
0.8342
0.0786
0.0651
0.0198
0.0023
0.0000
building
0.0368
0.9495
0.0118
0.0018
0.0001
0.0000
low_veg
0.0681
0.0395
0.7549
0.1372
0.0003
0.0000
tree
0.0181
0.0051
0.1281
0.8486
0.0000
0.0000
car
0.1209
0.0037
0.0000
0.0065
0.8690
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.867
0.847
0.756
0.880
0.732
--
Recall/Completeness
0.834
0.950
0.755
0.849
0.869
--
F1
0.851
0.895
0.755
0.864
0.794
--

Overall accuracy 0.840

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
0.8043
0.0456
0.0976
0.0506
0.0019
0.0000
building
0.0659
0.8705
0.0571
0.0061
0.0003
0.0000
low_veg
0.0200
0.0221
0.7995
0.1569
0.0007
0.0009
tree
0.0207
0.0049
0.1276
0.8467
0.0001
0.0000
car
0.2470
0.0085
0.0716
0.0108
0.6621
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.828
0.909
0.767
0.848
0.719
--
Recall/Completeness
0.804
0.871
0.800
0.847
0.662
--
F1
0.816
0.890
0.783
0.848
0.689
--

Overall accuracy 0.830

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
0.8405
0.0402
0.0870
0.0315
0.0009
0.0000
building
0.0647
0.8882
0.0448
0.0021
0.0002
0.0000
low_veg
0.0155
0.0160
0.8212
0.1457
0.0006
0.0010
tree
0.0139
0.0016
0.1114
0.8731
0.0000
0.0000
car
0.1634
0.0017
0.0660
0.0025
0.7665
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.855
0.933
0.797
0.869
0.768
--
Recall/Completeness
0.840
0.888
0.821
0.873
0.766
--
F1
0.847
0.910
0.809
0.871
0.767
--

Overall accuracy 0.855

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
0.8203
0.0680
0.0682
0.0412
0.0024
0.0000
building
0.0251
0.9315
0.0372
0.0062
0.0000
0.0000
low_veg
0.0403
0.0389
0.7499
0.1708
0.0000
0.0000
tree
0.0070
0.0019
0.0594
0.9316
0.0000
0.0000
car
0.3218
0.0463
0.0693
0.0419
0.5208
0.0000
clutter
0.0007
0.9983
0.0007
0.0004
0.0000
0.0000
Precision/Correctness
0.911
0.756
0.765
0.900
0.818
0.000
Recall/Completeness
0.820
0.932
0.750
0.932
0.521
0.000
F1
0.863
0.835
0.758
0.915
0.636
-nan

Overall accuracy 0.847

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
0.8534
0.0569
0.0644
0.0237
0.0016
0.0000
building
0.0234
0.9438
0.0304
0.0024
0.0000
0.0000
low_veg
0.0352
0.0266
0.7950
0.1432
0.0000
0.0000
tree
0.0028
0.0005
0.0454
0.9514
0.0000
0.0000
car
0.2430
0.0450
0.0586
0.0353
0.6182
0.0000
clutter
0.0000
0.9999
0.0001
0.0001
0.0000
0.0000
Precision/Correctness
0.933
0.778
0.798
0.926
0.850
0.000
Recall/Completeness
0.853
0.944
0.795
0.951
0.618
0.000
F1
0.891
0.853
0.797
0.939
0.716
-nan

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_area22_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8874
0.0343
0.0455
0.0300
0.0028
0.0000
building
0.0663
0.9161
0.0134
0.0038
0.0004
0.0000
low_veg
0.0724
0.0498
0.7431
0.1346
0.0001
0.0000
tree
0.0206
0.0045
0.0826
0.8923
0.0000
0.0000
car
0.4537
0.0036
0.0242
0.0283
0.4880
0.0022
clutter
--
--
--
--
--
--
Precision/Correctness
0.884
0.880
0.785
0.872
0.844
--
Recall/Completeness
0.887
0.916
0.743
0.892
0.488
--
F1
0.885
0.897
0.764
0.882
0.618
--

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_area22_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9202
0.0254
0.0377
0.0149
0.0019
0.0000
building
0.0607
0.9307
0.0070
0.0012
0.0004
0.0000
low_veg
0.0691
0.0349
0.7864
0.1095
0.0001
0.0000
tree
0.0083
0.0013
0.0626
0.9278
0.0000
0.0000
car
0.3613
0.0019
0.0205
0.0163
0.5984
0.0017
clutter
--
--
--
--
--
--
Precision/Correctness
0.909
0.916
0.829
0.909
0.875
--
Recall/Completeness
0.920
0.931
0.786
0.928
0.598
--
F1
0.915
0.923
0.807
0.918
0.711
--

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_area24_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.7988
0.0491
0.1186
0.0310
0.0026
0.0000
building
0.0742
0.8647
0.0518
0.0092
0.0001
0.0000
low_veg
0.0267
0.0213
0.8821
0.0690
0.0009
0.0000
tree
0.0133
0.0078
0.1909
0.7879
0.0000
0.0000
car
0.3562
0.0024
0.0219
0.0057
0.6138
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.797
0.901
0.828
0.852
0.752
--
Recall/Completeness
0.799
0.865
0.882
0.788
0.614
--
F1
0.798
0.882
0.854
0.819
0.676
--

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_area24_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8311
0.0369
0.1100
0.0211
0.0009
0.0000
building
0.0728
0.8749
0.0453
0.0068
0.0001
0.0000
low_veg
0.0242
0.0151
0.9005
0.0593
0.0009
0.0000
tree
0.0070
0.0038
0.1679
0.8212
0.0000
0.0000
car
0.2706
0.0020
0.0099
0.0025
0.7150
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.818
0.930
0.850
0.876
0.779
--
Recall/Completeness
0.831
0.875
0.900
0.821
0.715
--
F1
0.824
0.902
0.875
0.848
0.746
--

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_area27_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9221
0.0446
0.0205
0.0055
0.0073
0.0000
building
0.1278
0.8486
0.0194
0.0038
0.0004
0.0000
low_veg
0.0875
0.0343
0.6889
0.1891
0.0001
0.0000
tree
0.0161
0.0056
0.0751
0.9031
0.0000
0.0000
car
0.4310
0.0220
0.0081
0.0072
0.5316
0.0000
clutter
0.4052
0.4313
0.1265
0.0179
0.0191
0.0000
Precision/Correctness
0.790
0.927
0.863
0.692
0.871
0.000
Recall/Completeness
0.922
0.849
0.689
0.903
0.532
0.000
F1
0.851
0.886
0.766
0.783
0.660
-nan

Overall accuracy 0.834

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
0.9477
0.0345
0.0127
0.0021
0.0029
0.0000
building
0.1172
0.8666
0.0138
0.0021
0.0003
0.0000
low_veg
0.0713
0.0193
0.7275
0.1819
0.0000
0.0000
tree
0.0076
0.0018
0.0540
0.9366
0.0000
0.0000
car
0.3424
0.0192
0.0048
0.0049
0.6287
0.0000
clutter
0.4276
0.4306
0.1037
0.0114
0.0268
0.0000
Precision/Correctness
0.820
0.951
0.904
0.718
0.934
-nan
Recall/Completeness
0.948
0.867
0.728
0.937
0.629
0.000
F1
0.879
0.907
0.806
0.813
0.751
-nan

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: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9211
0.0395
0.0254
0.0113
0.0027
0.0000
building
0.0284
0.9534
0.0146
0.0035
0.0000
0.0000
low_veg
0.0588
0.0280
0.6556
0.2573
0.0003
0.0000
tree
0.0055
0.0027
0.0525
0.9391
0.0002
0.0000
car
0.4187
0.0249
0.0027
0.0074
0.5461
0.0002
clutter
0.4042
0.4749
0.0174
0.0121
0.0825
0.0089
Precision/Correctness
0.919
0.879
0.822
0.699
0.666
0.978
Recall/Completeness
0.921
0.953
0.656
0.939
0.546
0.009
F1
0.920
0.915
0.729
0.802
0.600
0.018

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
0.9434
0.0319
0.0181
0.0051
0.0015
0.0000
building
0.0226
0.9674
0.0084
0.0015
0.0000
0.0000
low_veg
0.0363
0.0134
0.7038
0.2464
0.0001
0.0000
tree
0.0014
0.0007
0.0409
0.9570
0.0000
0.0000
car
0.3192
0.0209
0.0006
0.0052
0.6542
0.0000
clutter
0.3830
0.5003
0.0121
0.0040
0.0906
0.0100
Precision/Correctness
0.942
0.903
0.866
0.736
0.683
1.000
Recall/Completeness
0.943
0.967
0.704
0.957
0.654
0.010
F1
0.943
0.934
0.777
0.832
0.668
0.020

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_area31_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9460
0.0348
0.0092
0.0039
0.0061
0.0001
building
0.1320
0.8506
0.0122
0.0012
0.0030
0.0010
low_veg
0.0523
0.0092
0.8980
0.0403
0.0002
0.0000
tree
0.0357
0.0047
0.0980
0.8614
0.0001
0.0000
car
0.2323
0.1655
0.0108
0.0231
0.5681
0.0002
clutter
0.5206
0.2140
0.0171
0.0064
0.1522
0.0897
Precision/Correctness
0.832
0.892
0.875
0.917
0.711
0.904
Recall/Completeness
0.946
0.851
0.898
0.861
0.568
0.090
F1
0.885
0.871
0.887
0.888
0.631
0.163

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_area31_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9605
0.0300
0.0058
0.0005
0.0031
0.0000
building
0.1228
0.8679
0.0060
0.0001
0.0023
0.0009
low_veg
0.0334
0.0046
0.9284
0.0336
0.0000
0.0000
tree
0.0137
0.0009
0.0742
0.9112
0.0000
0.0000
car
0.1504
0.1699
0.0053
0.0135
0.6609
0.0000
clutter
0.4802
0.2289
0.0134
0.0013
0.1703
0.1060
Precision/Correctness
0.860
0.912
0.916
0.946
0.731
0.925
Recall/Completeness
0.961
0.868
0.928
0.911
0.661
0.106
F1
0.907
0.889
0.922
0.928
0.694
0.190

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_area33_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9318
0.0502
0.0136
0.0028
0.0010
0.0007
building
0.1473
0.7664
0.0810
0.0039
0.0013
0.0000
low_veg
0.0571
0.0319
0.8288
0.0816
0.0006
0.0000
tree
0.0388
0.0057
0.1767
0.7788
0.0000
0.0001
car
0.5197
0.0752
0.0024
0.0062
0.3803
0.0163
clutter
0.5297
0.1268
0.0031
0.0003
0.1272
0.2129
Precision/Correctness
0.798
0.872
0.729
0.846
0.387
0.960
Recall/Completeness
0.932
0.766
0.829
0.779
0.380
0.213
F1
0.860
0.816
0.776
0.811
0.383
0.349

Overall accuracy 0.806

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
0.9464
0.0445
0.0078
0.0006
0.0004
0.0003
building
0.1411
0.7748
0.0806
0.0023
0.0012
0.0000
low_veg
0.0303
0.0205
0.8670
0.0818
0.0005
0.0000
tree
0.0155
0.0015
0.1610
0.8219
0.0000
0.0001
car
0.4409
0.0748
0.0002
0.0029
0.4648
0.0164
clutter
0.4902
0.1268
0.0020
0.0001
0.1408
0.2401
Precision/Correctness
0.824
0.895
0.750
0.863
0.378
0.977
Recall/Completeness
0.946
0.775
0.867
0.822
0.465
0.240
F1
0.881
0.830
0.804
0.842
0.417
0.385

Overall accuracy 0.830

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
0.8276
0.0855
0.0691
0.0169
0.0009
0.0000
building
0.0601
0.9154
0.0208
0.0034
0.0000
0.0003
low_veg
0.0462
0.0191
0.7162
0.2184
0.0001
0.0000
tree
0.0287
0.0074
0.1324
0.8312
0.0003
0.0000
car
0.4824
0.0557
0.0028
0.0065
0.4525
0.0001
clutter
--
--
--
--
--
--
Precision/Correctness
0.846
0.896
0.767
0.766
0.915
--
Recall/Completeness
0.828
0.915
0.716
0.831
0.452
--
F1
0.837
0.906
0.741
0.797
0.605
--

Overall accuracy 0.821

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
0.8729
0.0777
0.0447
0.0046
0.0002
0.0000
building
0.0517
0.9371
0.0105
0.0004
0.0000
0.0003
low_veg
0.0318
0.0089
0.7466
0.2127
0.0000
0.0000
tree
0.0091
0.0020
0.1022
0.8866
0.0001
0.0000
car
0.4007
0.0480
0.0009
0.0018
0.5486
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.889
0.923
0.831
0.792
0.978
--
Recall/Completeness
0.873
0.937
0.747
0.887
0.549
--
F1
0.881
0.930
0.786
0.836
0.703
--

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_area38_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9054
0.0330
0.0468
0.0125
0.0022
0.0000
building
0.0622
0.8749
0.0562
0.0047
0.0020
0.0000
low_veg
0.0335
0.0260
0.8300
0.1102
0.0003
0.0000
tree
0.0226
0.0034
0.1294
0.8445
0.0001
0.0000
car
0.4167
0.0226
0.0772
0.0173
0.4662
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.879
0.929
0.815
0.822
0.791
--
Recall/Completeness
0.905
0.875
0.830
0.845
0.466
--
F1
0.892
0.901
0.822
0.833
0.587
--

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_area38_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9338
0.0283
0.0324
0.0043
0.0013
0.0000
building
0.0555
0.8996
0.0414
0.0019
0.0016
0.0000
low_veg
0.0180
0.0195
0.8647
0.0976
0.0001
0.0000
tree
0.0080
0.0009
0.1031
0.8879
0.0000
0.0000
car
0.3250
0.0238
0.0653
0.0113
0.5746
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.914
0.947
0.858
0.854
0.837
--
Recall/Completeness
0.934
0.900
0.865
0.888
0.575
--
F1
0.924
0.923
0.861
0.871
0.682
--

Overall accuracy 0.895

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image