Detailled semantic labeling (2D) result


Name C. Lyu and J. Jiang
Affiliation Beihang University, China
Abbreviation BUAA
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
0.911
0.028
0.040
0.016
0.004
0.000
building
0.057
0.918
0.020
0.005
0.000
0.000
low_veg
0.059
0.025
0.783
0.133
0.000
0.000
tree
0.022
0.006
0.097
0.875
0.000
0.000
car
0.244
0.033
0.005
0.006
0.713
0.000
clutter
0.676
0.262
0.024
0.011
0.027
0.000
Precision/Correctness
0.858
0.932
0.814
0.851
0.859
-nan
Recall/Completeness
0.911
0.918
0.783
0.875
0.713
0.000
F1
0.884
0.925
0.798
0.863
0.779
-nan

Overall accuracy 0.866

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
0.936
0.021
0.033
0.008
0.002
0.000
building
0.048
0.936
0.013
0.002
0.000
0.000
low_veg
0.047
0.016
0.819
0.118
0.000
0.000
tree
0.010
0.002
0.080
0.907
0.000
0.000
car
0.144
0.039
0.002
0.003
0.811
0.000
clutter
0.663
0.282
0.022
0.005
0.028
0.000
Precision/Correctness
0.889
0.952
0.848
0.880
0.894
-nan
Recall/Completeness
0.936
0.936
0.819
0.907
0.811
0.000
F1
0.912
0.944
0.833
0.894
0.851
-nan

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
0.9565
0.0081
0.0184
0.0123
0.0046
0.0000
building
0.0500
0.9257
0.0204
0.0038
0.0000
0.0000
low_veg
0.0783
0.0202
0.7448
0.1567
0.0001
0.0000
tree
0.0305
0.0036
0.0882
0.8775
0.0002
0.0000
car
0.2652
0.0009
0.0001
0.0016
0.7323
0.0000
clutter
0.9533
0.0000
0.0195
0.0262
0.0010
0.0000
Precision/Correctness
0.800
0.964
0.853
0.835
0.901
-nan
Recall/Completeness
0.957
0.926
0.745
0.878
0.732
0.000
F1
0.871
0.945
0.795
0.856
0.808
-nan

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_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9786
0.0048
0.0094
0.0037
0.0034
0.0000
building
0.0409
0.9476
0.0107
0.0007
0.0000
0.0000
low_veg
0.0598
0.0131
0.7779
0.1491
0.0000
0.0000
tree
0.0144
0.0015
0.0743
0.9097
0.0001
0.0000
car
0.1319
0.0001
0.0000
0.0008
0.8672
0.0000
clutter
0.9713
0.0000
0.0202
0.0076
0.0010
0.0000
Precision/Correctness
0.833
0.979
0.887
0.860
0.919
-nan
Recall/Completeness
0.979
0.948
0.778
0.910
0.867
0.000
F1
0.900
0.963
0.829
0.884
0.893
-nan

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_area4_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9282
0.0515
0.0122
0.0047
0.0033
0.0000
building
0.0685
0.9197
0.0106
0.0011
0.0001
0.0000
low_veg
0.1449
0.0625
0.4888
0.3032
0.0006
0.0000
tree
0.0514
0.0195
0.0778
0.8512
0.0001
0.0000
car
0.3224
0.0103
0.0016
0.0050
0.6607
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.839
0.965
0.621
0.724
0.898
--
Recall/Completeness
0.928
0.920
0.489
0.851
0.661
--
F1
0.881
0.942
0.547
0.782
0.761
--

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: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9564
0.0307
0.0093
0.0020
0.0017
0.0000
building
0.0544
0.9359
0.0093
0.0003
0.0001
0.0000
low_veg
0.1060
0.0344
0.5230
0.3365
0.0001
0.0000
tree
0.0222
0.0083
0.0710
0.8985
0.0000
0.0000
car
0.2090
0.0062
0.0002
0.0029
0.7816
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.873
0.981
0.647
0.748
0.940
--
Recall/Completeness
0.956
0.936
0.523
0.898
0.782
--
F1
0.913
0.958
0.578
0.816
0.854
--

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
0.9146
0.0425
0.0299
0.0091
0.0039
0.0000
building
0.0503
0.9308
0.0159
0.0028
0.0002
0.0000
low_veg
0.0935
0.0322
0.7173
0.1567
0.0003
0.0000
tree
0.0217
0.0041
0.0620
0.9120
0.0002
0.0000
car
0.3126
0.0172
0.0000
0.0017
0.6685
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.860
0.951
0.713
0.929
0.904
--
Recall/Completeness
0.915
0.931
0.717
0.912
0.669
--
F1
0.886
0.941
0.715
0.921
0.769
--

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_area6_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9483
0.0253
0.0217
0.0028
0.0019
0.0000
building
0.0401
0.9473
0.0119
0.0006
0.0001
0.0000
low_veg
0.0774
0.0155
0.7697
0.1374
0.0001
0.0000
tree
0.0108
0.0011
0.0488
0.9393
0.0001
0.0000
car
0.2097
0.0126
0.0000
0.0002
0.7775
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.897
0.975
0.757
0.951
0.949
--
Recall/Completeness
0.948
0.947
0.770
0.939
0.778
--
F1
0.922
0.961
0.764
0.945
0.855
--

Overall accuracy 0.926

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area8_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8891
0.0245
0.0739
0.0093
0.0033
0.0000
building
0.0354
0.9448
0.0160
0.0038
0.0000
0.0000
low_veg
0.0512
0.0161
0.8666
0.0657
0.0003
0.0000
tree
0.0247
0.0067
0.0968
0.8718
0.0000
0.0000
car
0.2523
0.0112
0.0174
0.0048
0.7142
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.908
0.945
0.772
0.925
0.917
--
Recall/Completeness
0.889
0.945
0.867
0.872
0.714
--
F1
0.898
0.945
0.817
0.898
0.803
--

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
0.9162
0.0171
0.0630
0.0023
0.0014
0.0000
building
0.0256
0.9645
0.0086
0.0013
0.0000
0.0000
low_veg
0.0357
0.0082
0.9005
0.0556
0.0000
0.0000
tree
0.0102
0.0027
0.0758
0.9114
0.0000
0.0000
car
0.1452
0.0097
0.0102
0.0036
0.8314
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.943
0.968
0.813
0.949
0.960
--
Recall/Completeness
0.916
0.965
0.900
0.911
0.831
--
F1
0.929
0.966
0.855
0.930
0.891
--

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
0.8285
0.0630
0.0880
0.0178
0.0027
0.0000
building
0.0441
0.9262
0.0197
0.0098
0.0001
0.0000
low_veg
0.0666
0.0347
0.7732
0.1254
0.0001
0.0000
tree
0.0136
0.0080
0.1010
0.8774
0.0000
0.0000
car
0.2188
0.0320
0.0049
0.0029
0.7414
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.922
0.874
0.699
0.853
0.831
--
Recall/Completeness
0.828
0.926
0.773
0.877
0.741
--
F1
0.873
0.899
0.734
0.865
0.784
--

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_area10_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8560
0.0537
0.0818
0.0074
0.0011
0.0000
building
0.0383
0.9391
0.0152
0.0073
0.0001
0.0000
low_veg
0.0640
0.0234
0.8135
0.0990
0.0001
0.0000
tree
0.0050
0.0035
0.0783
0.9132
0.0000
0.0000
car
0.1403
0.0378
0.0022
0.0003
0.8193
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.938
0.899
0.730
0.895
0.903
--
Recall/Completeness
0.856
0.939
0.814
0.913
0.819
--
F1
0.895
0.919
0.770
0.904
0.859
--

Overall accuracy 0.880

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
0.8855
0.0390
0.0399
0.0331
0.0025
0.0000
building
0.0963
0.8893
0.0095
0.0050
0.0000
0.0000
low_veg
0.0478
0.0287
0.7552
0.1681
0.0001
0.0000
tree
0.0107
0.0082
0.1043
0.8767
0.0000
0.0000
car
0.1953
0.0004
0.0000
0.0056
0.7987
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.772
0.909
0.826
0.856
0.912
--
Recall/Completeness
0.886
0.889
0.755
0.877
0.799
--
F1
0.825
0.899
0.789
0.866
0.851
--

Overall accuracy 0.845

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
0.9117
0.0360
0.0325
0.0194
0.0004
0.0000
building
0.0994
0.8957
0.0035
0.0014
0.0000
0.0000
low_veg
0.0444
0.0196
0.7900
0.1460
0.0000
0.0000
tree
0.0051
0.0034
0.0864
0.9050
0.0000
0.0000
car
0.0904
0.0000
0.0000
0.0016
0.9080
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.792
0.936
0.857
0.883
0.982
--
Recall/Completeness
0.912
0.896
0.790
0.905
0.908
--
F1
0.848
0.915
0.822
0.894
0.944
--

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_area14_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8183
0.0374
0.1043
0.0337
0.0063
0.0000
building
0.0225
0.9611
0.0125
0.0039
0.0000
0.0000
low_veg
0.0798
0.0509
0.7208
0.1479
0.0006
0.0000
tree
0.0221
0.0152
0.1245
0.8381
0.0000
0.0000
car
0.1033
0.0000
0.0006
0.0017
0.8943
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.855
0.864
0.730
0.859
0.596
--
Recall/Completeness
0.818
0.961
0.721
0.838
0.894
--
F1
0.836
0.910
0.725
0.849
0.715
--

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
0.8379
0.0327
0.0999
0.0242
0.0053
0.0000
building
0.0181
0.9760
0.0048
0.0011
0.0000
0.0000
low_veg
0.0747
0.0359
0.7507
0.1381
0.0006
0.0000
tree
0.0142
0.0079
0.1121
0.8657
0.0000
0.0000
car
0.0258
0.0000
0.0000
0.0000
0.9742
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.880
0.898
0.751
0.879
0.581
--
Recall/Completeness
0.838
0.976
0.751
0.866
0.974
--
F1
0.859
0.936
0.751
0.872
0.728
--

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_area16_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8460
0.0312
0.0651
0.0543
0.0033
0.0000
building
0.0445
0.9272
0.0156
0.0126
0.0001
0.0000
low_veg
0.0203
0.0148
0.8399
0.1251
0.0000
0.0000
tree
0.0253
0.0049
0.1003
0.8696
0.0000
0.0000
car
0.1399
0.0003
0.0000
0.0011
0.8588
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.848
0.937
0.834
0.870
0.783
--
Recall/Completeness
0.846
0.927
0.840
0.870
0.859
--
F1
0.847
0.932
0.837
0.870
0.819
--

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_area16_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8797
0.0264
0.0580
0.0343
0.0016
0.0000
building
0.0410
0.9479
0.0060
0.0051
0.0000
0.0000
low_veg
0.0156
0.0090
0.8652
0.1102
0.0000
0.0000
tree
0.0173
0.0017
0.0864
0.8945
0.0000
0.0000
car
0.0776
0.0000
0.0000
0.0000
0.9224
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.878
0.959
0.861
0.894
0.861
--
Recall/Completeness
0.880
0.948
0.865
0.895
0.922
--
F1
0.879
0.953
0.863
0.894
0.890
--

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_area20_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8850
0.0318
0.0411
0.0374
0.0047
0.0000
building
0.0153
0.9689
0.0106
0.0053
0.0000
0.0000
low_veg
0.0519
0.0382
0.7425
0.1673
0.0001
0.0000
tree
0.0092
0.0019
0.0485
0.9404
0.0000
0.0000
car
0.1495
0.0053
0.0057
0.0138
0.8257
0.0000
clutter
0.0154
0.9846
0.0000
0.0000
0.0000
0.0000
Precision/Correctness
0.911
0.793
0.828
0.904
0.779
-nan
Recall/Completeness
0.885
0.969
0.743
0.940
0.826
0.000
F1
0.898
0.872
0.783
0.922
0.802
-nan

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_area20_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9158
0.0233
0.0377
0.0202
0.0029
0.0000
building
0.0121
0.9803
0.0062
0.0014
0.0000
0.0000
low_veg
0.0455
0.0270
0.7889
0.1385
0.0000
0.0000
tree
0.0038
0.0003
0.0365
0.9594
0.0000
0.0000
car
0.0849
0.0032
0.0003
0.0048
0.9067
0.0000
clutter
0.0080
0.9920
0.0000
0.0000
0.0000
0.0000
Precision/Correctness
0.936
0.812
0.859
0.931
0.821
-nan
Recall/Completeness
0.916
0.980
0.789
0.959
0.907
0.000
F1
0.926
0.888
0.823
0.945
0.862
-nan

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_area22_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9030
0.0235
0.0358
0.0321
0.0055
0.0000
building
0.0492
0.9349
0.0095
0.0059
0.0004
0.0000
low_veg
0.1094
0.0425
0.7080
0.1394
0.0007
0.0000
tree
0.0214
0.0037
0.0668
0.9079
0.0002
0.0000
car
0.2345
0.0177
0.0032
0.0164
0.7283
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.879
0.906
0.815
0.869
0.798
--
Recall/Completeness
0.903
0.935
0.708
0.908
0.728
--
F1
0.891
0.920
0.758
0.888
0.762
--

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_area22_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9329
0.0172
0.0297
0.0167
0.0035
0.0000
building
0.0418
0.9523
0.0033
0.0023
0.0003
0.0000
low_veg
0.1062
0.0297
0.7508
0.1125
0.0007
0.0000
tree
0.0088
0.0010
0.0495
0.9406
0.0001
0.0000
car
0.1352
0.0196
0.0006
0.0074
0.8373
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.904
0.936
0.857
0.906
0.833
--
Recall/Completeness
0.933
0.952
0.751
0.941
0.837
--
F1
0.918
0.944
0.800
0.923
0.835
--

Overall accuracy 0.902

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area24_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8149
0.0509
0.0966
0.0310
0.0066
0.0000
building
0.0687
0.8756
0.0389
0.0168
0.0000
0.0000
low_veg
0.0307
0.0204
0.8778
0.0709
0.0002
0.0000
tree
0.0206
0.0070
0.1551
0.8173
0.0000
0.0000
car
0.1570
0.0081
0.0027
0.0028
0.8293
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.791
0.903
0.856
0.849
0.750
--
Recall/Completeness
0.815
0.876
0.878
0.817
0.829
--
F1
0.803
0.889
0.867
0.833
0.787
--

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_area24_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8433
0.0420
0.0888
0.0210
0.0049
0.0000
building
0.0663
0.8865
0.0329
0.0142
0.0000
0.0000
low_veg
0.0275
0.0150
0.8970
0.0604
0.0002
0.0000
tree
0.0135
0.0034
0.1320
0.8511
0.0000
0.0000
car
0.0707
0.0092
0.0000
0.0003
0.9197
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.813
0.928
0.878
0.873
0.759
--
Recall/Completeness
0.843
0.887
0.897
0.851
0.920
--
F1
0.828
0.907
0.888
0.862
0.832
--

Overall accuracy 0.876

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
0.9386
0.0265
0.0222
0.0073
0.0055
0.0000
building
0.0758
0.9015
0.0190
0.0034
0.0003
0.0000
low_veg
0.0865
0.0236
0.6890
0.2001
0.0008
0.0000
tree
0.0144
0.0062
0.0446
0.9347
0.0002
0.0000
car
0.2525
0.0072
0.0027
0.0046
0.7329
0.0000
clutter
0.5197
0.2891
0.1040
0.0227
0.0645
0.0000
Precision/Correctness
0.847
0.956
0.879
0.686
0.916
-nan
Recall/Completeness
0.939
0.901
0.689
0.935
0.733
0.000
F1
0.890
0.928
0.773
0.791
0.814
-nan

Overall accuracy 0.867

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area27_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9639
0.0169
0.0156
0.0027
0.0009
0.0000
building
0.0641
0.9217
0.0131
0.0010
0.0002
0.0000
low_veg
0.0683
0.0113
0.7311
0.1886
0.0007
0.0000
tree
0.0063
0.0024
0.0284
0.9628
0.0000
0.0000
car
0.1452
0.0060
0.0008
0.0033
0.8447
0.0000
clutter
0.5262
0.2802
0.0980
0.0159
0.0797
0.0000
Precision/Correctness
0.881
0.976
0.916
0.718
0.970
-nan
Recall/Completeness
0.964
0.922
0.731
0.963
0.845
0.000
F1
0.920
0.948
0.813
0.822
0.903
-nan

Overall accuracy 0.899

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
0.9494
0.0130
0.0200
0.0129
0.0047
0.0000
building
0.0516
0.9296
0.0113
0.0068
0.0007
0.0000
low_veg
0.0684
0.0229
0.6190
0.2894
0.0003
0.0000
tree
0.0068
0.0018
0.0296
0.9618
0.0000
0.0000
car
0.2577
0.0024
0.0065
0.0148
0.7186
0.0000
clutter
0.5259
0.4020
0.0245
0.0119
0.0357
0.0000
Precision/Correctness
0.902
0.923
0.854
0.675
0.746
-nan
Recall/Completeness
0.949
0.930
0.619
0.962
0.719
0.000
F1
0.925
0.926
0.718
0.793
0.732
-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: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9689
0.0075
0.0144
0.0057
0.0036
0.0000
building
0.0448
0.9446
0.0065
0.0034
0.0007
0.0000
low_veg
0.0459
0.0111
0.6647
0.2781
0.0002
0.0000
tree
0.0021
0.0006
0.0210
0.9764
0.0000
0.0000
car
0.1685
0.0003
0.0068
0.0130
0.8114
0.0000
clutter
0.5045
0.4337
0.0173
0.0055
0.0390
0.0000
Precision/Correctness
0.924
0.941
0.894
0.713
0.746
-nan
Recall/Completeness
0.969
0.945
0.665
0.976
0.811
0.000
F1
0.946
0.943
0.762
0.824
0.778
-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_area31_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9768
0.0051
0.0097
0.0037
0.0047
0.0000
building
0.0688
0.9179
0.0099
0.0021
0.0013
0.0000
low_veg
0.0458
0.0025
0.9297
0.0219
0.0001
0.0000
tree
0.0439
0.0026
0.0840
0.8685
0.0010
0.0000
car
0.2069
0.1516
0.0049
0.0087
0.6279
0.0000
clutter
0.7797
0.1172
0.0576
0.0155
0.0299
0.0000
Precision/Correctness
0.855
0.955
0.884
0.941
0.873
-nan
Recall/Completeness
0.977
0.918
0.930
0.868
0.628
0.000
F1
0.912
0.936
0.906
0.904
0.730
-nan

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_area31_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9866
0.0037
0.0071
0.0008
0.0019
0.0000
building
0.0540
0.9399
0.0049
0.0003
0.0010
0.0000
low_veg
0.0256
0.0008
0.9581
0.0154
0.0000
0.0000
tree
0.0157
0.0005
0.0669
0.9167
0.0002
0.0000
car
0.1309
0.1817
0.0004
0.0043
0.6827
0.0000
clutter
0.7612
0.1371
0.0611
0.0086
0.0321
0.0000
Precision/Correctness
0.889
0.961
0.915
0.970
0.907
-nan
Recall/Completeness
0.987
0.940
0.958
0.917
0.683
0.000
F1
0.935
0.950
0.936
0.943
0.779
-nan

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
0.9779
0.0092
0.0071
0.0036
0.0022
0.0000
building
0.0994
0.8431
0.0493
0.0055
0.0027
0.0000
low_veg
0.0722
0.0562
0.7988
0.0727
0.0000
0.0000
tree
0.0477
0.0028
0.1412
0.8082
0.0001
0.0000
car
0.2358
0.0160
0.0040
0.0057
0.7384
0.0000
clutter
0.9035
0.0400
0.0055
0.0041
0.0469
0.0000
Precision/Correctness
0.796
0.943
0.793
0.854
0.694
-nan
Recall/Completeness
0.978
0.843
0.799
0.808
0.738
0.000
F1
0.877
0.890
0.796
0.831
0.716
-nan

Overall accuracy 0.838

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
0.9868
0.0072
0.0037
0.0013
0.0011
0.0000
building
0.0879
0.8585
0.0480
0.0033
0.0024
0.0000
low_veg
0.0399
0.0532
0.8338
0.0730
0.0000
0.0000
tree
0.0206
0.0003
0.1309
0.8482
0.0000
0.0000
car
0.1285
0.0219
0.0004
0.0043
0.8450
0.0000
clutter
0.8983
0.0426
0.0051
0.0039
0.0502
0.0000
Precision/Correctness
0.825
0.951
0.810
0.872
0.696
-nan
Recall/Completeness
0.987
0.858
0.834
0.848
0.845
0.000
F1
0.898
0.903
0.822
0.860
0.763
-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_area35_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8817
0.0328
0.0655
0.0193
0.0006
0.0000
building
0.0617
0.9166
0.0162
0.0051
0.0003
0.0000
low_veg
0.0482
0.0121
0.7408
0.1989
0.0000
0.0000
tree
0.0348
0.0060
0.1291
0.8301
0.0001
0.0000
car
0.3074
0.0022
0.0002
0.0056
0.6846
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.851
0.951
0.783
0.778
0.953
--
Recall/Completeness
0.882
0.917
0.741
0.830
0.685
--
F1
0.866
0.933
0.761
0.803
0.797
--

Overall accuracy 0.843

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
0.9174
0.0303
0.0465
0.0057
0.0000
0.0000
building
0.0482
0.9444
0.0062
0.0010
0.0002
0.0000
low_veg
0.0326
0.0052
0.7704
0.1918
0.0000
0.0000
tree
0.0130
0.0016
0.1020
0.8834
0.0000
0.0000
car
0.1995
0.0009
0.0000
0.0015
0.7980
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.898
0.967
0.838
0.806
0.983
--
Recall/Completeness
0.917
0.944
0.770
0.883
0.798
--
F1
0.908
0.956
0.803
0.843
0.881
--

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_area38_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9218
0.0261
0.0361
0.0131
0.0028
0.0000
building
0.0400
0.9162
0.0391
0.0047
0.0000
0.0000
low_veg
0.0489
0.0155
0.8601
0.0753
0.0002
0.0000
tree
0.0229
0.0041
0.1403
0.8327
0.0001
0.0000
car
0.2070
0.0195
0.0162
0.0072
0.7502
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.891
0.949
0.836
0.863
0.895
--
Recall/Completeness
0.922
0.916
0.860
0.833
0.750
--
F1
0.906
0.933
0.848
0.847
0.816
--

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_area38_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9471
0.0232
0.0237
0.0050
0.0010
0.0000
building
0.0318
0.9397
0.0265
0.0020
0.0000
0.0000
low_veg
0.0322
0.0093
0.8975
0.0608
0.0001
0.0000
tree
0.0073
0.0011
0.1157
0.8758
0.0000
0.0000
car
0.1179
0.0228
0.0087
0.0024
0.8482
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.929
0.964
0.875
0.899
0.951
--
Recall/Completeness
0.947
0.940
0.898
0.876
0.848
--
F1
0.938
0.952
0.886
0.887
0.897
--

Overall accuracy 0.917

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image