Detailled semantic labeling (2D) result


Name S. Böck et al.
Affiliation IVFL, Austria
Abbreviation IVFL
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
0.879
0.039
0.061
0.013
0.007
0.000
building
0.073
0.894
0.019
0.011
0.003
0.000
low_veg
0.070
0.030
0.776
0.121
0.002
0.000
tree
0.017
0.011
0.150
0.821
0.000
0.000
car
0.518
0.033
0.039
0.005
0.405
0.000
clutter
0.650
0.171
0.058
0.006
0.114
0.001
Precision/Correctness
0.828
0.915
0.747
0.850
0.549
0.276
Recall/Completeness
0.879
0.894
0.776
0.821
0.405
0.001
F1
0.853
0.904
0.761
0.835
0.466
0.003

Overall accuracy 0.834

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
0.911
0.031
0.046
0.007
0.005
0.000
building
0.066
0.911
0.013
0.008
0.002
0.000
low_veg
0.061
0.020
0.808
0.109
0.002
0.000
tree
0.010
0.007
0.127
0.856
0.000
0.000
car
0.462
0.037
0.032
0.002
0.467
0.000
clutter
0.648
0.178
0.052
0.002
0.119
0.001
Precision/Correctness
0.855
0.938
0.789
0.877
0.556
0.281
Recall/Completeness
0.911
0.911
0.808
0.856
0.467
0.001
F1
0.882
0.924
0.798
0.867
0.507
0.003

Overall accuracy 0.865
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9153
0.0121
0.0591
0.0084
0.0049
0.0001
building
0.0367
0.9386
0.0195
0.0041
0.0010
0.0000
low_veg
0.0966
0.0229
0.7803
0.0981
0.0021
0.0001
tree
0.0286
0.0105
0.1507
0.8102
0.0001
0.0000
car
0.6186
0.0029
0.0251
0.0032
0.3502
0.0000
clutter
0.9566
0.0023
0.0071
0.0257
0.0000
0.0082
Precision/Correctness
0.775
0.950
0.770
0.879
0.733
0.760
Recall/Completeness
0.915
0.939
0.780
0.810
0.350
0.008
F1
0.839
0.944
0.775
0.843
0.474
0.016

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_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9489
0.0076
0.0372
0.0028
0.0034
0.0001
building
0.0282
0.9573
0.0120
0.0017
0.0008
0.0000
low_veg
0.0853
0.0127
0.8060
0.0939
0.0021
0.0000
tree
0.0174
0.0065
0.1289
0.8472
0.0000
0.0000
car
0.5611
0.0017
0.0218
0.0011
0.4143
0.0000
clutter
0.9756
0.0021
0.0039
0.0103
0.0000
0.0081
Precision/Correctness
0.803
0.972
0.813
0.899
0.764
0.797
Recall/Completeness
0.949
0.957
0.806
0.847
0.414
0.008
F1
0.870
0.964
0.809
0.872
0.537
0.016

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_area4_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8765
0.0949
0.0171
0.0049
0.0060
0.0005
building
0.0596
0.9295
0.0064
0.0041
0.0004
0.0000
low_veg
0.2581
0.1017
0.3765
0.2571
0.0036
0.0031
tree
0.0424
0.0260
0.1781
0.7534
0.0002
0.0000
car
0.6194
0.0734
0.0232
0.0010
0.2829
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.820
0.938
0.490
0.704
0.656
--
Recall/Completeness
0.876
0.929
0.377
0.753
0.283
--
F1
0.848
0.934
0.426
0.728
0.395
--

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_area4_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9088
0.0705
0.0125
0.0026
0.0050
0.0006
building
0.0465
0.9452
0.0053
0.0026
0.0004
0.0000
low_veg
0.2433
0.0746
0.4023
0.2735
0.0027
0.0037
tree
0.0197
0.0140
0.1775
0.7888
0.0000
0.0000
car
0.5755
0.0731
0.0212
0.0001
0.3301
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.854
0.958
0.513
0.737
0.675
--
Recall/Completeness
0.909
0.945
0.402
0.789
0.330
--
F1
0.880
0.951
0.451
0.762
0.443
--

Overall accuracy 0.898

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
0.8445
0.0864
0.0475
0.0092
0.0123
0.0000
building
0.0357
0.9397
0.0152
0.0074
0.0020
0.0000
low_veg
0.0669
0.0601
0.6728
0.1993
0.0010
0.0000
tree
0.0101
0.0106
0.0786
0.9007
0.0001
0.0000
car
0.4726
0.0344
0.0203
0.0028
0.4700
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.879
0.907
0.641
0.909
0.662
--
Recall/Completeness
0.845
0.940
0.673
0.901
0.470
--
F1
0.862
0.923
0.657
0.905
0.550
--

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_area6_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8891
0.0653
0.0332
0.0029
0.0095
0.0000
building
0.0276
0.9560
0.0112
0.0035
0.0017
0.0000
low_veg
0.0586
0.0456
0.7078
0.1874
0.0006
0.0000
tree
0.0043
0.0061
0.0627
0.9268
0.0000
0.0000
car
0.4172
0.0296
0.0130
0.0006
0.5395
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.911
0.935
0.690
0.932
0.690
--
Recall/Completeness
0.889
0.956
0.708
0.927
0.540
--
F1
0.900
0.945
0.699
0.929
0.605
--

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_area8_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8689
0.0592
0.0548
0.0123
0.0049
0.0000
building
0.0288
0.9523
0.0107
0.0077
0.0005
0.0000
low_veg
0.0875
0.0235
0.8334
0.0543
0.0012
0.0000
tree
0.0219
0.0135
0.1319
0.8324
0.0001
0.0000
car
0.5084
0.0314
0.0313
0.0070
0.4219
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.878
0.891
0.760
0.924
0.788
--
Recall/Completeness
0.869
0.952
0.833
0.832
0.422
--
F1
0.874
0.920
0.795
0.876
0.549
--

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_area8_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9007
0.0508
0.0391
0.0060
0.0035
0.0000
building
0.0180
0.9718
0.0049
0.0049
0.0004
0.0000
low_veg
0.0774
0.0131
0.8635
0.0451
0.0009
0.0000
tree
0.0109
0.0077
0.1090
0.8723
0.0001
0.0000
car
0.4418
0.0331
0.0196
0.0062
0.4993
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.911
0.918
0.808
0.946
0.823
--
Recall/Completeness
0.901
0.972
0.864
0.872
0.499
--
F1
0.906
0.944
0.835
0.908
0.621
--

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_area10_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8447
0.0692
0.0650
0.0163
0.0048
0.0000
building
0.0265
0.9430
0.0138
0.0148
0.0019
0.0000
low_veg
0.0972
0.0424
0.7414
0.1169
0.0021
0.0000
tree
0.0158
0.0106
0.1492
0.8244
0.0000
0.0000
car
0.4906
0.0461
0.0496
0.0009
0.4128
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.913
0.861
0.690
0.849
0.526
--
Recall/Completeness
0.845
0.943
0.741
0.824
0.413
--
F1
0.878
0.900
0.715
0.836
0.462
--

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_area10_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8798
0.0573
0.0512
0.0077
0.0039
0.0000
building
0.0196
0.9604
0.0078
0.0107
0.0015
0.0000
low_veg
0.0966
0.0320
0.7745
0.0950
0.0020
0.0000
tree
0.0100
0.0057
0.1193
0.8650
0.0000
0.0000
car
0.4391
0.0458
0.0414
0.0000
0.4737
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.930
0.889
0.741
0.889
0.532
--
Recall/Completeness
0.880
0.960
0.774
0.865
0.474
--
F1
0.904
0.924
0.758
0.877
0.501
--

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_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8329
0.0299
0.1034
0.0297
0.0041
0.0000
building
0.1644
0.7929
0.0302
0.0095
0.0031
0.0000
low_veg
0.0505
0.0276
0.7310
0.1876
0.0032
0.0000
tree
0.0071
0.0086
0.1645
0.8197
0.0001
0.0000
car
0.5238
0.0000
0.0473
0.0006
0.4282
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.697
0.908
0.722
0.834
0.502
--
Recall/Completeness
0.833
0.793
0.731
0.820
0.428
--
F1
0.759
0.846
0.727
0.827
0.462
--

Overall accuracy 0.789

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
0.8673
0.0269
0.0845
0.0183
0.0030
0.0000
building
0.1720
0.8003
0.0211
0.0035
0.0031
0.0000
low_veg
0.0494
0.0192
0.7597
0.1683
0.0033
0.0000
tree
0.0035
0.0046
0.1450
0.8468
0.0000
0.0000
car
0.4731
0.0000
0.0419
0.0000
0.4850
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.710
0.934
0.754
0.861
0.477
--
Recall/Completeness
0.867
0.800
0.760
0.847
0.485
--
F1
0.781
0.862
0.757
0.854
0.481
--

Overall accuracy 0.815

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
0.8515
0.0340
0.0839
0.0274
0.0031
0.0000
building
0.0231
0.9432
0.0239
0.0097
0.0001
0.0000
low_veg
0.0892
0.0569
0.7251
0.1239
0.0048
0.0000
tree
0.0266
0.0175
0.1759
0.7799
0.0001
0.0000
car
0.3703
0.0000
0.0188
0.0105
0.6004
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.842
0.855
0.691
0.869
0.444
--
Recall/Completeness
0.852
0.943
0.725
0.780
0.600
--
F1
0.847
0.897
0.708
0.822
0.511
--

Overall accuracy 0.811

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
0.8754
0.0303
0.0729
0.0189
0.0024
0.0000
building
0.0157
0.9658
0.0130
0.0055
0.0000
0.0000
low_veg
0.0839
0.0440
0.7533
0.1137
0.0051
0.0000
tree
0.0200
0.0112
0.1619
0.8068
0.0001
0.0000
car
0.2882
0.0000
0.0114
0.0062
0.6941
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.868
0.885
0.717
0.890
0.423
--
Recall/Completeness
0.875
0.966
0.753
0.807
0.694
--
F1
0.872
0.924
0.735
0.846
0.526
--

Overall accuracy 0.837

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
0.7705
0.0237
0.1549
0.0452
0.0058
0.0000
building
0.0263
0.9162
0.0416
0.0147
0.0011
0.0000
low_veg
0.0273
0.0179
0.7648
0.1863
0.0035
0.0002
tree
0.0144
0.0076
0.1704
0.8066
0.0010
0.0000
car
0.2283
0.0000
0.0533
0.0093
0.7091
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.865
0.933
0.707
0.820
0.392
--
Recall/Completeness
0.770
0.916
0.765
0.807
0.709
--
F1
0.815
0.924
0.735
0.813
0.505
--

Overall accuracy 0.808

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
0.8088
0.0202
0.1381
0.0287
0.0043
0.0000
building
0.0214
0.9392
0.0317
0.0069
0.0009
0.0000
low_veg
0.0237
0.0114
0.7846
0.1766
0.0035
0.0002
tree
0.0095
0.0041
0.1539
0.8315
0.0010
0.0000
car
0.1637
0.0000
0.0350
0.0015
0.7998
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.893
0.955
0.737
0.841
0.366
--
Recall/Completeness
0.809
0.939
0.785
0.832
0.800
--
F1
0.849
0.947
0.760
0.836
0.502
--

Overall accuracy 0.833

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
0.8128
0.0311
0.1219
0.0306
0.0036
0.0000
building
0.0150
0.9375
0.0357
0.0117
0.0000
0.0000
low_veg
0.0411
0.0226
0.7867
0.1464
0.0032
0.0000
tree
0.0070
0.0028
0.0928
0.8975
0.0000
0.0000
car
0.4275
0.0301
0.0293
0.0148
0.4982
0.0000
clutter
0.8228
0.0158
0.1589
0.0001
0.0024
0.0000
Precision/Correctness
0.814
0.926
0.676
0.910
0.589
-nan
Recall/Completeness
0.813
0.938
0.787
0.897
0.498
0.000
F1
0.814
0.931
0.727
0.904
0.540
-nan

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_area20_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8472
0.0257
0.1071
0.0171
0.0029
0.0000
building
0.0113
0.9548
0.0291
0.0048
0.0000
0.0000
low_veg
0.0364
0.0140
0.8248
0.1213
0.0035
0.0000
tree
0.0036
0.0012
0.0750
0.9201
0.0000
0.0000
car
0.3434
0.0323
0.0148
0.0063
0.6032
0.0000
clutter
0.8349
0.0160
0.1470
0.0000
0.0020
0.0000
Precision/Correctness
0.830
0.948
0.711
0.935
0.579
-nan
Recall/Completeness
0.847
0.955
0.825
0.920
0.603
0.000
F1
0.839
0.951
0.764
0.928
0.591
-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_area22_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8463
0.0398
0.0794
0.0284
0.0061
0.0000
building
0.0320
0.9398
0.0182
0.0100
0.0000
0.0000
low_veg
0.0977
0.0474
0.7056
0.1455
0.0037
0.0000
tree
0.0176
0.0079
0.1049
0.8695
0.0001
0.0000
car
0.5680
0.0488
0.0705
0.0081
0.3046
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.880
0.870
0.705
0.862
0.550
--
Recall/Completeness
0.846
0.940
0.706
0.870
0.305
--
F1
0.863
0.903
0.705
0.866
0.392
--

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_area22_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8826
0.0323
0.0644
0.0152
0.0054
0.0000
building
0.0255
0.9595
0.0102
0.0048
0.0000
0.0000
low_veg
0.0964
0.0350
0.7403
0.1244
0.0039
0.0000
tree
0.0086
0.0044
0.0806
0.9064
0.0000
0.0000
car
0.5130
0.0645
0.0566
0.0045
0.3614
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.905
0.901
0.757
0.896
0.536
--
Recall/Completeness
0.883
0.960
0.740
0.906
0.361
--
F1
0.894
0.929
0.749
0.901
0.432
--

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_area24_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.7902
0.0462
0.1299
0.0249
0.0089
0.0000
building
0.0530
0.8895
0.0342
0.0221
0.0011
0.0000
low_veg
0.0355
0.0191
0.8663
0.0779
0.0012
0.0000
tree
0.0141
0.0098
0.2119
0.7637
0.0004
0.0000
car
0.4868
0.0058
0.0377
0.0015
0.4682
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.793
0.907
0.818
0.830
0.457
--
Recall/Completeness
0.790
0.889
0.866
0.764
0.468
--
F1
0.792
0.898
0.841
0.795
0.463
--

Overall accuracy 0.832

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
0.8225
0.0385
0.1152
0.0167
0.0072
0.0000
building
0.0490
0.9045
0.0269
0.0189
0.0007
0.0000
low_veg
0.0322
0.0141
0.8848
0.0677
0.0011
0.0000
tree
0.0093
0.0061
0.1917
0.7925
0.0004
0.0000
car
0.4136
0.0026
0.0235
0.0003
0.5599
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.817
0.930
0.842
0.852
0.472
--
Recall/Completeness
0.823
0.905
0.885
0.792
0.560
--
F1
0.820
0.917
0.863
0.821
0.512
--

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_area27_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9156
0.0362
0.0318
0.0050
0.0113
0.0001
building
0.0644
0.9186
0.0110
0.0044
0.0014
0.0001
low_veg
0.1268
0.0474
0.7066
0.1175
0.0016
0.0000
tree
0.0133
0.0253
0.1027
0.8587
0.0000
0.0000
car
0.5788
0.0098
0.0209
0.0033
0.3872
0.0000
clutter
0.6428
0.0928
0.0808
0.0015
0.1821
0.0000
Precision/Correctness
0.809
0.931
0.846
0.766
0.721
0.000
Recall/Completeness
0.916
0.919
0.707
0.859
0.387
0.000
F1
0.859
0.925
0.770
0.810
0.504
-nan

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_area27_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9429
0.0263
0.0218
0.0021
0.0069
0.0001
building
0.0511
0.9391
0.0064
0.0022
0.0011
0.0001
low_veg
0.1142
0.0327
0.7443
0.1074
0.0014
0.0000
tree
0.0069
0.0181
0.0773
0.8977
0.0000
0.0000
car
0.5302
0.0080
0.0182
0.0015
0.4421
0.0000
clutter
0.6597
0.0831
0.0506
0.0000
0.2065
0.0000
Precision/Correctness
0.845
0.954
0.890
0.801
0.768
0.000
Recall/Completeness
0.943
0.939
0.744
0.898
0.442
0.000
F1
0.891
0.946
0.811
0.846
0.561
-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_area29_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9245
0.0199
0.0413
0.0095
0.0047
0.0001
building
0.0804
0.9003
0.0098
0.0070
0.0024
0.0000
low_veg
0.0509
0.0381
0.6814
0.2292
0.0003
0.0000
tree
0.0092
0.0179
0.0570
0.9159
0.0000
0.0000
car
0.5645
0.0135
0.0454
0.0064
0.3702
0.0000
clutter
0.5923
0.2334
0.0391
0.0078
0.1275
0.0000
Precision/Correctness
0.876
0.914
0.782
0.714
0.434
0.000
Recall/Completeness
0.925
0.900
0.681
0.916
0.370
0.000
F1
0.900
0.907
0.728
0.802
0.400
-nan

Overall accuracy 0.846

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
0.9491
0.0137
0.0293
0.0045
0.0033
0.0001
building
0.0759
0.9124
0.0052
0.0040
0.0024
0.0000
low_veg
0.0350
0.0226
0.7208
0.2215
0.0001
0.0000
tree
0.0054
0.0142
0.0419
0.9384
0.0000
0.0000
car
0.5228
0.0083
0.0388
0.0047
0.4254
0.0000
clutter
0.5846
0.2421
0.0309
0.0025
0.1399
0.0000
Precision/Correctness
0.895
0.937
0.833
0.749
0.424
0.000
Recall/Completeness
0.949
0.912
0.721
0.938
0.425
0.000
F1
0.922
0.925
0.773
0.833
0.425
-nan

Overall accuracy 0.875

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area31_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9503
0.0105
0.0258
0.0030
0.0104
0.0000
building
0.3031
0.6648
0.0142
0.0029
0.0150
0.0000
low_veg
0.0486
0.0054
0.9137
0.0305
0.0018
0.0000
tree
0.0235
0.0057
0.1353
0.8351
0.0004
0.0000
car
0.3337
0.0783
0.0357
0.0070
0.5453
0.0000
clutter
0.3805
0.3590
0.0958
0.0029
0.1618
0.0000
Precision/Correctness
0.757
0.900
0.801
0.932
0.585
-nan
Recall/Completeness
0.950
0.665
0.914
0.835
0.545
0.000
F1
0.843
0.765
0.854
0.881
0.564
-nan

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_area31_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9698
0.0075
0.0169
0.0006
0.0052
0.0000
building
0.3025
0.6739
0.0094
0.0005
0.0136
0.0000
low_veg
0.0291
0.0025
0.9442
0.0235
0.0007
0.0000
tree
0.0094
0.0016
0.1037
0.8851
0.0001
0.0000
car
0.2727
0.0943
0.0283
0.0022
0.6026
0.0000
clutter
0.3300
0.4138
0.0854
0.0005
0.1703
0.0000
Precision/Correctness
0.773
0.913
0.855
0.961
0.607
-nan
Recall/Completeness
0.970
0.674
0.944
0.885
0.603
0.000
F1
0.860
0.775
0.897
0.921
0.605
-nan

Overall accuracy 0.831

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
0.9621
0.0098
0.0171
0.0013
0.0097
0.0000
building
0.2461
0.6831
0.0045
0.0622
0.0041
0.0000
low_veg
0.0945
0.0208
0.8568
0.0253
0.0027
0.0000
tree
0.0415
0.0328
0.2182
0.7074
0.0001
0.0000
car
0.6885
0.0049
0.0180
0.0011
0.2875
0.0000
clutter
0.6319
0.1657
0.0132
0.0001
0.1890
0.0000
Precision/Correctness
0.736
0.911
0.806
0.768
0.191
-nan
Recall/Completeness
0.962
0.683
0.857
0.707
0.288
0.000
F1
0.834
0.781
0.831
0.736
0.230
-nan

Overall accuracy 0.778

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
0.9752
0.0063
0.0096
0.0002
0.0087
0.0000
building
0.2439
0.6876
0.0016
0.0632
0.0037
0.0000
low_veg
0.0646
0.0138
0.8953
0.0248
0.0015
0.0000
tree
0.0218
0.0249
0.1988
0.7544
0.0000
0.0000
car
0.6492
0.0050
0.0151
0.0004
0.3303
0.0000
clutter
0.6028
0.1758
0.0129
0.0000
0.2084
0.0000
Precision/Correctness
0.755
0.929
0.842
0.772
0.179
-nan
Recall/Completeness
0.975
0.688
0.895
0.754
0.330
0.000
F1
0.851
0.790
0.868
0.763
0.232
-nan

Overall accuracy 0.799

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
0.8425
0.0448
0.0963
0.0101
0.0064
0.0000
building
0.0423
0.9274
0.0241
0.0045
0.0018
0.0000
low_veg
0.0728
0.0216
0.7498
0.1539
0.0019
0.0000
tree
0.0273
0.0092
0.2173
0.7462
0.0001
0.0000
car
0.5702
0.0735
0.0186
0.0075
0.3302
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.841
0.928
0.695
0.806
0.492
--
Recall/Completeness
0.843
0.927
0.750
0.746
0.330
--
F1
0.842
0.927
0.721
0.775
0.395
--

Overall accuracy 0.816

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
0.8933
0.0392
0.0598
0.0024
0.0054
0.0000
building
0.0274
0.9563
0.0136
0.0012
0.0015
0.0000
low_veg
0.0601
0.0137
0.7747
0.1499
0.0016
0.0000
tree
0.0122
0.0042
0.1760
0.8076
0.0000
0.0000
car
0.5055
0.0896
0.0103
0.0022
0.3924
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.886
0.949
0.763
0.831
0.518
--
Recall/Completeness
0.893
0.956
0.775
0.808
0.392
--
F1
0.890
0.953
0.769
0.819
0.447
--

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_area38_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8771
0.0289
0.0734
0.0112
0.0094
0.0000
building
0.0237
0.9196
0.0398
0.0115
0.0055
0.0000
low_veg
0.0538
0.0209
0.8425
0.0798
0.0030
0.0000
tree
0.0147
0.0129
0.1865
0.7857
0.0002
0.0000
car
0.5032
0.0252
0.1297
0.0079
0.3340
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.891
0.934
0.778
0.844
0.403
--
Recall/Completeness
0.877
0.920
0.843
0.786
0.334
--
F1
0.884
0.927
0.809
0.814
0.365
--

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_area38_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9139
0.0246
0.0493
0.0038
0.0083
0.0000
building
0.0151
0.9448
0.0286
0.0071
0.0044
0.0000
low_veg
0.0419
0.0128
0.8762
0.0664
0.0026
0.0000
tree
0.0065
0.0090
0.1542
0.8303
0.0001
0.0000
car
0.4588
0.0292
0.1150
0.0039
0.3931
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.924
0.954
0.826
0.881
0.408
--
Recall/Completeness
0.914
0.945
0.876
0.830
0.393
--
F1
0.919
0.949
0.851
0.855
0.401
--

Overall accuracy 0.892

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image