Detailled semantic labeling (2D) result


Name T. V. Duy
Affiliation Hanoi University of Science and Technology, Vietnam
Abbreviation BKHN_4
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
0.910
0.032
0.039
0.015
0.004
0.000
building
0.039
0.939
0.015
0.006
0.000
0.000
low_veg
0.050
0.025
0.798
0.127
0.000
0.000
tree
0.019
0.007
0.093
0.881
0.000
0.000
car
0.192
0.046
0.005
0.005
0.751
0.000
clutter
0.375
0.313
0.024
0.007
0.037
0.244
Precision/Correctness
0.891
0.927
0.827
0.856
0.855
0.968
Recall/Completeness
0.910
0.939
0.798
0.881
0.751
0.244
F1
0.900
0.933
0.813
0.868
0.800
0.390

Overall accuracy 0.879

Overall statistics, reference set: no_boundary


Number of non processed tiles by this participant: 0
↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.935
0.025
0.031
0.007
0.002
0.000
building
0.032
0.954
0.009
0.004
0.000
0.000
low_veg
0.039
0.015
0.834
0.112
0.000
0.000
tree
0.009
0.003
0.076
0.912
0.000
0.000
car
0.092
0.052
0.002
0.002
0.851
0.000
clutter
0.336
0.334
0.020
0.002
0.038
0.269
Precision/Correctness
0.920
0.948
0.861
0.885
0.882
0.978
Recall/Completeness
0.935
0.954
0.834
0.912
0.851
0.269
F1
0.927
0.951
0.847
0.898
0.866
0.422

Overall accuracy 0.907
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9552
0.0116
0.0174
0.0115
0.0043
0.0000
building
0.0222
0.9614
0.0143
0.0020
0.0000
0.0000
low_veg
0.0764
0.0251
0.7354
0.1630
0.0001
0.0000
tree
0.0279
0.0125
0.0943
0.8639
0.0002
0.0012
car
0.2301
0.0017
0.0003
0.0008
0.7670
0.0000
clutter
0.0411
0.0087
0.0000
0.0134
0.0000
0.9367
Precision/Correctness
0.872
0.947
0.853
0.831
0.912
0.983
Recall/Completeness
0.955
0.961
0.735
0.864
0.767
0.937
F1
0.912
0.954
0.790
0.847
0.833
0.959

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_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9767
0.0079
0.0096
0.0029
0.0029
0.0000
building
0.0153
0.9765
0.0080
0.0003
0.0000
0.0000
low_veg
0.0603
0.0151
0.7684
0.1562
0.0001
0.0000
tree
0.0131
0.0087
0.0806
0.8969
0.0001
0.0005
car
0.1088
0.0002
0.0000
0.0002
0.8908
0.0000
clutter
0.0401
0.0069
0.0000
0.0027
0.0000
0.9503
Precision/Correctness
0.911
0.967
0.883
0.854
0.933
0.993
Recall/Completeness
0.977
0.976
0.768
0.897
0.891
0.950
F1
0.943
0.972
0.822
0.875
0.911
0.971

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_area4_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9216
0.0597
0.0088
0.0057
0.0042
0.0000
building
0.0392
0.9512
0.0078
0.0015
0.0003
0.0000
low_veg
0.1363
0.0466
0.5238
0.2925
0.0008
0.0000
tree
0.0472
0.0190
0.0695
0.8639
0.0003
0.0000
car
0.2482
0.0055
0.0007
0.0014
0.7442
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.888
0.963
0.694
0.727
0.884
--
Recall/Completeness
0.922
0.951
0.524
0.864
0.744
--
F1
0.904
0.957
0.597
0.789
0.808
--

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_area4_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9488
0.0399
0.0061
0.0029
0.0024
0.0000
building
0.0281
0.9640
0.0070
0.0007
0.0002
0.0000
low_veg
0.0972
0.0154
0.5702
0.3165
0.0006
0.0000
tree
0.0193
0.0075
0.0637
0.9093
0.0002
0.0000
car
0.1339
0.0012
0.0003
0.0003
0.8643
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.922
0.979
0.721
0.754
0.918
--
Recall/Completeness
0.949
0.964
0.570
0.909
0.864
--
F1
0.935
0.971
0.637
0.824
0.890
--

Overall accuracy 0.939

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
0.9019
0.0576
0.0285
0.0082
0.0038
0.0000
building
0.0316
0.9525
0.0132
0.0026
0.0001
0.0000
low_veg
0.0744
0.0367
0.7637
0.1249
0.0003
0.0000
tree
0.0138
0.0048
0.0569
0.9245
0.0001
0.0000
car
0.2274
0.0092
0.0003
0.0013
0.7618
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.898
0.940
0.744
0.942
0.921
--
Recall/Completeness
0.902
0.953
0.764
0.924
0.762
--
F1
0.900
0.946
0.754
0.933
0.834
--

Overall accuracy 0.908

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
0.9363
0.0412
0.0195
0.0016
0.0015
0.0000
building
0.0237
0.9665
0.0091
0.0007
0.0000
0.0000
low_veg
0.0600
0.0203
0.8129
0.1067
0.0000
0.0000
tree
0.0043
0.0017
0.0428
0.9512
0.0000
0.0000
car
0.1265
0.0059
0.0000
0.0001
0.8674
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.933
0.963
0.793
0.962
0.965
--
Recall/Completeness
0.936
0.967
0.813
0.951
0.867
--
F1
0.935
0.965
0.803
0.957
0.914
--

Overall accuracy 0.938

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
0.8868
0.0366
0.0666
0.0069
0.0031
0.0000
building
0.0183
0.9658
0.0122
0.0034
0.0003
0.0000
low_veg
0.0464
0.0150
0.8903
0.0479
0.0003
0.0000
tree
0.0241
0.0073
0.0827
0.8859
0.0001
0.0000
car
0.2297
0.0067
0.0115
0.0052
0.7470
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.924
0.932
0.800
0.944
0.919
--
Recall/Completeness
0.887
0.966
0.890
0.886
0.747
--
F1
0.905
0.949
0.843
0.914
0.824
--

Overall accuracy 0.903

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
0.9108
0.0302
0.0567
0.0010
0.0013
0.0000
building
0.0095
0.9839
0.0051
0.0014
0.0002
0.0000
low_veg
0.0324
0.0065
0.9241
0.0369
0.0001
0.0000
tree
0.0093
0.0031
0.0608
0.9268
0.0000
0.0000
car
0.1207
0.0069
0.0051
0.0038
0.8634
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.958
0.953
0.842
0.966
0.960
--
Recall/Completeness
0.911
0.984
0.924
0.927
0.863
--
F1
0.934
0.968
0.881
0.946
0.909
--

Overall accuracy 0.934

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
0.8456
0.0726
0.0589
0.0193
0.0027
0.0010
building
0.0110
0.9625
0.0156
0.0109
0.0000
0.0000
low_veg
0.0572
0.0408
0.7796
0.1223
0.0001
0.0000
tree
0.0124
0.0104
0.0765
0.9007
0.0000
0.0000
car
0.1381
0.0514
0.0016
0.0029
0.8061
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.951
0.860
0.768
0.855
0.846
--
Recall/Completeness
0.846
0.963
0.780
0.901
0.806
--
F1
0.895
0.909
0.774
0.877
0.826
--

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_area10_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8800
0.0580
0.0518
0.0077
0.0013
0.0011
building
0.0075
0.9732
0.0109
0.0084
0.0000
0.0000
low_veg
0.0553
0.0269
0.8255
0.0923
0.0001
0.0000
tree
0.0053
0.0050
0.0583
0.9314
0.0000
0.0000
car
0.0463
0.0629
0.0000
0.0001
0.8907
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.965
0.893
0.803
0.900
0.899
--
Recall/Completeness
0.880
0.973
0.825
0.931
0.891
--
F1
0.920
0.931
0.814
0.916
0.895
--

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_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8820
0.0386
0.0488
0.0278
0.0028
0.0000
building
0.1618
0.8215
0.0130
0.0036
0.0001
0.0000
low_veg
0.0472
0.0293
0.7859
0.1373
0.0003
0.0000
tree
0.0093
0.0081
0.1165
0.8660
0.0000
0.0000
car
0.1382
0.0008
0.0008
0.0014
0.8588
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.720
0.902
0.813
0.878
0.892
--
Recall/Completeness
0.882
0.821
0.786
0.866
0.859
--
F1
0.793
0.860
0.799
0.872
0.875
--

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_area12_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9105
0.0351
0.0398
0.0141
0.0004
0.0000
building
0.1711
0.8210
0.0068
0.0010
0.0001
0.0000
low_veg
0.0456
0.0192
0.8204
0.1145
0.0003
0.0000
tree
0.0044
0.0033
0.0988
0.8935
0.0000
0.0000
car
0.0502
0.0001
0.0000
0.0000
0.9497
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.730
0.932
0.842
0.906
0.955
--
Recall/Completeness
0.911
0.821
0.820
0.894
0.950
--
F1
0.811
0.873
0.831
0.899
0.952
--

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_area14_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8394
0.0367
0.0854
0.0324
0.0062
0.0000
building
0.0126
0.9685
0.0138
0.0051
0.0000
0.0000
low_veg
0.0721
0.0510
0.7298
0.1463
0.0008
0.0000
tree
0.0257
0.0121
0.1215
0.8407
0.0000
0.0000
car
0.1253
0.0000
0.0000
0.0032
0.8715
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.867
0.870
0.747
0.861
0.587
--
Recall/Completeness
0.839
0.968
0.730
0.841
0.872
--
F1
0.853
0.917
0.738
0.851
0.701
--

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_area14_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8589
0.0321
0.0813
0.0222
0.0055
0.0000
building
0.0082
0.9844
0.0052
0.0021
0.0000
0.0000
low_veg
0.0673
0.0365
0.7609
0.1345
0.0009
0.0000
tree
0.0176
0.0054
0.1094
0.8675
0.0000
0.0000
car
0.0338
0.0000
0.0000
0.0000
0.9662
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.892
0.903
0.769
0.883
0.558
--
Recall/Completeness
0.859
0.984
0.761
0.868
0.966
--
F1
0.875
0.942
0.765
0.875
0.708
--

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_area16_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8265
0.0273
0.0993
0.0440
0.0029
0.0000
building
0.0204
0.9497
0.0199
0.0098
0.0001
0.0000
low_veg
0.0149
0.0174
0.8595
0.1079
0.0000
0.0003
tree
0.0232
0.0052
0.1133
0.8584
0.0000
0.0000
car
0.0956
0.0003
0.0156
0.0050
0.8836
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.884
0.937
0.808
0.886
0.806
--
Recall/Completeness
0.827
0.950
0.859
0.858
0.884
--
F1
0.854
0.943
0.833
0.872
0.843
--

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_area16_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8607
0.0229
0.0887
0.0263
0.0014
0.0000
building
0.0177
0.9685
0.0095
0.0042
0.0001
0.0000
low_veg
0.0111
0.0110
0.8839
0.0938
0.0000
0.0003
tree
0.0158
0.0016
0.0972
0.8854
0.0000
0.0000
car
0.0245
0.0000
0.0045
0.0004
0.9705
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.913
0.960
0.838
0.909
0.873
--
Recall/Completeness
0.861
0.969
0.884
0.885
0.971
--
F1
0.886
0.964
0.860
0.897
0.919
--

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_area20_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8481
0.0385
0.0693
0.0386
0.0056
0.0000
building
0.0141
0.9520
0.0221
0.0118
0.0000
0.0000
low_veg
0.0478
0.0191
0.7888
0.1436
0.0008
0.0000
tree
0.0062
0.0019
0.0518
0.9400
0.0000
0.0000
car
0.1241
0.0234
0.0193
0.0147
0.8185
0.0000
clutter
0.0247
0.9107
0.0645
0.0001
0.0000
0.0000
Precision/Correctness
0.918
0.808
0.790
0.911
0.723
-nan
Recall/Completeness
0.848
0.952
0.789
0.940
0.819
0.000
F1
0.882
0.874
0.789
0.925
0.768
-nan

Overall accuracy 0.868

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area20_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8817
0.0302
0.0641
0.0206
0.0034
0.0000
building
0.0122
0.9618
0.0170
0.0090
0.0000
0.0000
low_veg
0.0421
0.0085
0.8332
0.1152
0.0009
0.0000
tree
0.0021
0.0005
0.0383
0.9591
0.0000
0.0000
car
0.0727
0.0301
0.0058
0.0047
0.8867
0.0000
clutter
0.0198
0.9225
0.0577
0.0000
0.0000
0.0000
Precision/Correctness
0.939
0.825
0.822
0.937
0.751
-nan
Recall/Completeness
0.882
0.962
0.833
0.959
0.887
0.000
F1
0.910
0.888
0.827
0.948
0.813
-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_area22_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8923
0.0274
0.0430
0.0314
0.0059
0.0000
building
0.0153
0.9712
0.0080
0.0054
0.0001
0.0000
low_veg
0.0935
0.0372
0.7449
0.1242
0.0002
0.0000
tree
0.0182
0.0035
0.0629
0.9152
0.0001
0.0000
car
0.2108
0.0172
0.0058
0.0098
0.7563
0.0001
clutter
--
--
--
--
--
--
Precision/Correctness
0.907
0.908
0.818
0.879
0.807
--
Recall/Completeness
0.892
0.971
0.745
0.915
0.756
--
F1
0.900
0.939
0.780
0.897
0.781
--

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_area22_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9255
0.0196
0.0363
0.0148
0.0039
0.0000
building
0.0114
0.9839
0.0023
0.0024
0.0000
0.0000
low_veg
0.0919
0.0234
0.7887
0.0958
0.0001
0.0000
tree
0.0066
0.0008
0.0456
0.9469
0.0001
0.0000
car
0.1098
0.0200
0.0027
0.0025
0.8650
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.929
0.940
0.859
0.919
0.844
--
Recall/Completeness
0.925
0.984
0.789
0.947
0.865
--
F1
0.927
0.962
0.822
0.933
0.854
--

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_area24_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8080
0.0446
0.1092
0.0325
0.0057
0.0000
building
0.0534
0.9055
0.0291
0.0120
0.0000
0.0000
low_veg
0.0186
0.0240
0.8838
0.0733
0.0003
0.0000
tree
0.0161
0.0067
0.1508
0.8264
0.0000
0.0000
car
0.1636
0.0003
0.0001
0.0063
0.8297
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.840
0.904
0.859
0.849
0.768
--
Recall/Completeness
0.808
0.906
0.884
0.826
0.830
--
F1
0.824
0.905
0.871
0.838
0.798
--

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_area24_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8383
0.0347
0.1000
0.0226
0.0045
0.0000
building
0.0520
0.9174
0.0207
0.0098
0.0000
0.0000
low_veg
0.0155
0.0191
0.9026
0.0625
0.0003
0.0000
tree
0.0095
0.0031
0.1282
0.8593
0.0000
0.0000
car
0.0551
0.0002
0.0000
0.0015
0.9432
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.864
0.928
0.882
0.873
0.771
--
Recall/Completeness
0.838
0.917
0.903
0.859
0.943
--
F1
0.851
0.922
0.892
0.866
0.848
--

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_area27_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9413
0.0258
0.0194
0.0070
0.0063
0.0001
building
0.0489
0.9343
0.0134
0.0032
0.0003
0.0000
low_veg
0.0664
0.0285
0.7049
0.1998
0.0003
0.0000
tree
0.0121
0.0068
0.0438
0.9371
0.0001
0.0000
car
0.2043
0.0073
0.0029
0.0050
0.7800
0.0005
clutter
0.7006
0.1011
0.1021
0.0100
0.0862
0.0000
Precision/Correctness
0.883
0.956
0.898
0.688
0.913
0.000
Recall/Completeness
0.941
0.934
0.705
0.937
0.780
0.000
F1
0.911
0.945
0.790
0.793
0.841
-nan

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_area27_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9669
0.0161
0.0132
0.0023
0.0016
0.0001
building
0.0388
0.9525
0.0076
0.0010
0.0002
0.0000
low_veg
0.0511
0.0153
0.7449
0.1885
0.0001
0.0000
tree
0.0055
0.0023
0.0266
0.9655
0.0000
0.0000
car
0.0994
0.0048
0.0012
0.0038
0.8906
0.0002
clutter
0.7203
0.0979
0.0736
0.0082
0.1000
0.0000
Precision/Correctness
0.916
0.976
0.936
0.719
0.964
0.000
Recall/Completeness
0.967
0.952
0.745
0.966
0.891
0.000
F1
0.941
0.964
0.829
0.824
0.926
-nan

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_area29_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9413
0.0171
0.0229
0.0130
0.0057
0.0000
building
0.0300
0.9558
0.0087
0.0055
0.0000
0.0000
low_veg
0.0491
0.0259
0.6381
0.2868
0.0002
0.0000
tree
0.0050
0.0024
0.0200
0.9727
0.0000
0.0000
car
0.2233
0.0020
0.0008
0.0108
0.7631
0.0000
clutter
0.5365
0.3609
0.0295
0.0144
0.0520
0.0066
Precision/Correctness
0.920
0.922
0.862
0.680
0.720
0.993
Recall/Completeness
0.941
0.956
0.638
0.973
0.763
0.007
F1
0.930
0.938
0.733
0.801
0.741
0.013

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_area29_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9630
0.0106
0.0165
0.0054
0.0044
0.0000
building
0.0253
0.9678
0.0044
0.0025
0.0000
0.0000
low_veg
0.0306
0.0127
0.6840
0.2727
0.0000
0.0000
tree
0.0012
0.0006
0.0134
0.9847
0.0000
0.0000
car
0.1399
0.0003
0.0001
0.0083
0.8514
0.0000
clutter
0.5221
0.3829
0.0252
0.0056
0.0563
0.0079
Precision/Correctness
0.939
0.942
0.899
0.721
0.716
0.993
Recall/Completeness
0.963
0.968
0.684
0.985
0.851
0.008
F1
0.951
0.955
0.777
0.832
0.778
0.016

Overall accuracy 0.901

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
0.9729
0.0110
0.0090
0.0034
0.0036
0.0001
building
0.0450
0.9417
0.0094
0.0019
0.0018
0.0002
low_veg
0.0346
0.0054
0.9285
0.0314
0.0001
0.0001
tree
0.0339
0.0043
0.0923
0.8691
0.0004
0.0000
car
0.1317
0.2077
0.0062
0.0049
0.6484
0.0012
clutter
0.4496
0.3276
0.0271
0.0088
0.0457
0.1412
Precision/Correctness
0.901
0.915
0.887
0.934
0.871
0.972
Recall/Completeness
0.973
0.942
0.929
0.869
0.648
0.141
F1
0.936
0.928
0.907
0.900
0.743
0.247

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_area31_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9850
0.0070
0.0059
0.0004
0.0017
0.0000
building
0.0339
0.9600
0.0044
0.0002
0.0013
0.0002
low_veg
0.0166
0.0031
0.9551
0.0252
0.0000
0.0000
tree
0.0113
0.0010
0.0720
0.9157
0.0000
0.0000
car
0.0519
0.2298
0.0016
0.0014
0.7138
0.0016
clutter
0.3906
0.3669
0.0248
0.0026
0.0505
0.1645
Precision/Correctness
0.935
0.930
0.921
0.961
0.889
0.978
Recall/Completeness
0.985
0.960
0.955
0.916
0.714
0.165
F1
0.959
0.945
0.938
0.938
0.792
0.282

Overall accuracy 0.933

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
0.9829
0.0056
0.0064
0.0030
0.0017
0.0003
building
0.1020
0.8399
0.0130
0.0416
0.0035
0.0001
low_veg
0.0618
0.0121
0.8585
0.0669
0.0004
0.0003
tree
0.0391
0.0050
0.1465
0.8094
0.0000
0.0000
car
0.2061
0.0444
0.0018
0.0018
0.7459
0.0000
clutter
0.5640
0.1382
0.0027
0.0009
0.0565
0.2377
Precision/Correctness
0.832
0.951
0.859
0.783
0.666
0.985
Recall/Completeness
0.983
0.840
0.858
0.809
0.746
0.238
F1
0.901
0.892
0.859
0.796
0.704
0.383

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_area33_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9929
0.0028
0.0025
0.0008
0.0011
0.0000
building
0.0973
0.8487
0.0092
0.0415
0.0032
0.0001
low_veg
0.0338
0.0047
0.8935
0.0674
0.0003
0.0003
tree
0.0153
0.0011
0.1340
0.8497
0.0000
0.0000
car
0.0937
0.0552
0.0000
0.0003
0.8507
0.0000
clutter
0.5314
0.1460
0.0015
0.0002
0.0612
0.2597
Precision/Correctness
0.858
0.963
0.885
0.791
0.653
0.995
Recall/Completeness
0.993
0.849
0.893
0.850
0.851
0.260
F1
0.920
0.902
0.889
0.819
0.739
0.412

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_area35_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8915
0.0395
0.0524
0.0159
0.0007
0.0001
building
0.0331
0.9480
0.0149
0.0035
0.0005
0.0000
low_veg
0.0473
0.0131
0.7250
0.2144
0.0002
0.0000
tree
0.0269
0.0063
0.1100
0.8566
0.0001
0.0000
car
0.2170
0.0396
0.0024
0.0084
0.7326
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.887
0.944
0.807
0.775
0.934
--
Recall/Completeness
0.891
0.948
0.725
0.857
0.733
--
F1
0.889
0.946
0.764
0.814
0.821
--

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_area35_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9294
0.0346
0.0333
0.0026
0.0000
0.0001
building
0.0228
0.9711
0.0051
0.0005
0.0005
0.0000
low_veg
0.0330
0.0058
0.7516
0.2093
0.0002
0.0000
tree
0.0087
0.0017
0.0832
0.9064
0.0000
0.0000
car
0.0977
0.0469
0.0004
0.0021
0.8529
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.931
0.963
0.865
0.799
0.962
--
Recall/Completeness
0.929
0.971
0.752
0.906
0.853
--
F1
0.930
0.967
0.804
0.849
0.904
--

Overall accuracy 0.892

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area38_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9222
0.0295
0.0339
0.0115
0.0029
0.0000
building
0.0171
0.9468
0.0301
0.0053
0.0008
0.0000
low_veg
0.0348
0.0176
0.8755
0.0719
0.0001
0.0000
tree
0.0185
0.0052
0.1118
0.8645
0.0000
0.0000
car
0.1587
0.0490
0.0217
0.0055
0.7634
0.0016
clutter
--
--
--
--
--
--
Precision/Correctness
0.928
0.944
0.864
0.873
0.878
--
Recall/Completeness
0.922
0.947
0.876
0.864
0.763
--
F1
0.925
0.945
0.870
0.869
0.817
--

Overall accuracy 0.903

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
0.9468
0.0266
0.0219
0.0032
0.0015
0.0000
building
0.0108
0.9665
0.0191
0.0029
0.0007
0.0000
low_veg
0.0202
0.0112
0.9111
0.0575
0.0001
0.0000
tree
0.0057
0.0020
0.0884
0.9040
0.0000
0.0000
car
0.0616
0.0591
0.0114
0.0014
0.8643
0.0023
clutter
--
--
--
--
--
--
Precision/Correctness
0.962
0.959
0.901
0.907
0.915
--
Recall/Completeness
0.947
0.966
0.911
0.904
0.864
--
F1
0.955
0.962
0.906
0.906
0.889
--

Overall accuracy 0.934

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image