Detailled semantic labeling (2D) result


Name J. R. Bergado et al.
Affiliation University of Twente, ITC
Abbreviation ITC_B1
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
0.906
0.029
0.034
0.023
0.007
0.000
building
0.057
0.901
0.030
0.011
0.001
0.000
low_veg
0.073
0.017
0.675
0.235
0.000
0.000
tree
0.026
0.004
0.061
0.909
0.000
0.000
car
0.244
0.039
0.010
0.006
0.701
0.000
clutter
0.607
0.238
0.032
0.011
0.111
0.000
Precision/Correctness
0.849
0.939
0.822
0.774
0.728
-nan
Recall/Completeness
0.906
0.901
0.675
0.909
0.701
0.000
F1
0.877
0.919
0.741
0.836
0.714
-nan

Overall accuracy 0.845

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
0.929
0.024
0.029
0.013
0.004
0.000
building
0.047
0.923
0.023
0.006
0.001
0.000
low_veg
0.060
0.010
0.711
0.218
0.000
0.000
tree
0.013
0.002
0.049
0.936
0.000
0.000
car
0.155
0.045
0.008
0.004
0.789
0.000
clutter
0.592
0.257
0.032
0.005
0.114
0.000
Precision/Correctness
0.881
0.954
0.855
0.803
0.750
-nan
Recall/Completeness
0.929
0.923
0.711
0.936
0.789
0.000
F1
0.905
0.938
0.776
0.864
0.769
-nan

Overall accuracy 0.874
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9463
0.0142
0.0192
0.0151
0.0053
0.0000
building
0.0512
0.9054
0.0348
0.0078
0.0008
0.0000
low_veg
0.1212
0.0110
0.6154
0.2519
0.0004
0.0000
tree
0.0363
0.0024
0.0725
0.8886
0.0002
0.0000
car
0.3091
0.0056
0.0018
0.0015
0.6820
0.0000
clutter
0.9775
0.0003
0.0000
0.0221
0.0000
0.0000
Precision/Correctness
0.764
0.968
0.831
0.764
0.864
-nan
Recall/Completeness
0.946
0.905
0.615
0.889
0.682
0.000
F1
0.845
0.936
0.707
0.822
0.762
-nan

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_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9666
0.0116
0.0133
0.0051
0.0034
0.0000
building
0.0405
0.9342
0.0213
0.0032
0.0007
0.0000
low_veg
0.1048
0.0062
0.6416
0.2469
0.0004
0.0000
tree
0.0194
0.0008
0.0604
0.9193
0.0001
0.0000
car
0.1937
0.0041
0.0007
0.0006
0.8008
0.0000
clutter
0.9943
0.0001
0.0000
0.0055
0.0000
0.0000
Precision/Correctness
0.795
0.980
0.868
0.789
0.894
-nan
Recall/Completeness
0.967
0.934
0.642
0.919
0.801
0.000
F1
0.872
0.956
0.738
0.849
0.845
-nan

Overall accuracy 0.849

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area4_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9203
0.0545
0.0115
0.0062
0.0074
0.0000
building
0.0722
0.9146
0.0080
0.0034
0.0019
0.0000
low_veg
0.2094
0.0447
0.3670
0.3769
0.0019
0.0000
tree
0.0695
0.0139
0.0332
0.8834
0.0000
0.0000
car
0.3149
0.0244
0.0012
0.0016
0.6579
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.823
0.964
0.634
0.673
0.744
--
Recall/Completeness
0.920
0.915
0.367
0.883
0.658
--
F1
0.869
0.939
0.465
0.764
0.698
--

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_area4_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9412
0.0402
0.0100
0.0031
0.0056
0.0000
building
0.0572
0.9323
0.0068
0.0019
0.0017
0.0000
low_veg
0.1667
0.0231
0.3981
0.4111
0.0010
0.0000
tree
0.0382
0.0064
0.0281
0.9273
0.0000
0.0000
car
0.2167
0.0234
0.0009
0.0005
0.7585
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.858
0.977
0.661
0.702
0.760
--
Recall/Completeness
0.941
0.932
0.398
0.927
0.759
--
F1
0.897
0.954
0.497
0.799
0.759
--

Overall accuracy 0.911

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area6_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9010
0.0451
0.0323
0.0113
0.0103
0.0000
building
0.0534
0.9081
0.0251
0.0129
0.0004
0.0000
low_veg
0.0843
0.0210
0.6254
0.2685
0.0007
0.0000
tree
0.0182
0.0026
0.0366
0.9421
0.0005
0.0000
car
0.2531
0.0091
0.0001
0.0006
0.7371
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.864
0.953
0.711
0.883
0.802
--
Recall/Completeness
0.901
0.908
0.625
0.942
0.737
--
F1
0.882
0.930
0.666
0.912
0.768
--

Overall accuracy 0.883

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
0.9301
0.0341
0.0253
0.0039
0.0065
0.0000
building
0.0411
0.9302
0.0192
0.0092
0.0003
0.0000
low_veg
0.0639
0.0125
0.6738
0.2495
0.0002
0.0000
tree
0.0068
0.0008
0.0271
0.9650
0.0002
0.0000
car
0.1584
0.0058
0.0000
0.0000
0.8358
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.905
0.970
0.758
0.910
0.848
--
Recall/Completeness
0.930
0.930
0.674
0.965
0.836
--
F1
0.917
0.949
0.713
0.937
0.842
--

Overall accuracy 0.914

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
0.9008
0.0169
0.0663
0.0095
0.0065
0.0000
building
0.0367
0.9316
0.0232
0.0080
0.0006
0.0000
low_veg
0.0609
0.0114
0.8265
0.1005
0.0007
0.0000
tree
0.0311
0.0046
0.0651
0.8990
0.0002
0.0000
car
0.2510
0.0079
0.0111
0.0037
0.7263
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.898
0.961
0.795
0.897
0.839
--
Recall/Completeness
0.901
0.932
0.827
0.899
0.726
--
F1
0.899
0.946
0.810
0.898
0.779
--

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
0.9237
0.0117
0.0577
0.0032
0.0037
0.0000
building
0.0251
0.9555
0.0145
0.0045
0.0004
0.0000
low_veg
0.0417
0.0051
0.8660
0.0871
0.0001
0.0000
tree
0.0135
0.0018
0.0480
0.9366
0.0001
0.0000
car
0.1624
0.0086
0.0062
0.0018
0.8209
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.937
0.978
0.835
0.922
0.891
--
Recall/Completeness
0.924
0.955
0.866
0.937
0.821
--
F1
0.930
0.967
0.850
0.929
0.855
--

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
0.8439
0.0868
0.0372
0.0270
0.0051
0.0000
building
0.0268
0.9353
0.0189
0.0184
0.0006
0.0000
low_veg
0.0880
0.0288
0.6106
0.2719
0.0007
0.0000
tree
0.0188
0.0058
0.0385
0.9369
0.0000
0.0000
car
0.2529
0.0417
0.0062
0.0046
0.6947
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.920
0.850
0.803
0.756
0.693
--
Recall/Completeness
0.844
0.935
0.611
0.937
0.695
--
F1
0.880
0.890
0.694
0.836
0.694
--

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
0.8727
0.0781
0.0306
0.0149
0.0037
0.0000
building
0.0197
0.9522
0.0147
0.0129
0.0004
0.0000
low_veg
0.0855
0.0170
0.6541
0.2427
0.0008
0.0000
tree
0.0086
0.0025
0.0277
0.9612
0.0000
0.0000
car
0.1778
0.0488
0.0042
0.0012
0.7679
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.939
0.872
0.841
0.794
0.711
--
Recall/Completeness
0.873
0.952
0.654
0.961
0.768
--
F1
0.905
0.911
0.736
0.870
0.739
--

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_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8362
0.0373
0.0623
0.0597
0.0044
0.0000
building
0.1321
0.8233
0.0293
0.0151
0.0002
0.0000
low_veg
0.0399
0.0209
0.6372
0.3016
0.0004
0.0000
tree
0.0081
0.0052
0.0556
0.9311
0.0001
0.0000
car
0.1932
0.0016
0.0015
0.0132
0.7905
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.745
0.922
0.841
0.777
0.834
--
Recall/Completeness
0.836
0.823
0.637
0.931
0.790
--
F1
0.788
0.870
0.725
0.847
0.811
--

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_area12_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8658
0.0355
0.0562
0.0410
0.0015
0.0000
building
0.1383
0.8347
0.0208
0.0060
0.0002
0.0000
low_veg
0.0369
0.0158
0.6724
0.2745
0.0004
0.0000
tree
0.0035
0.0019
0.0435
0.9510
0.0000
0.0000
car
0.1002
0.0012
0.0008
0.0097
0.8881
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.760
0.941
0.871
0.806
0.897
--
Recall/Completeness
0.866
0.835
0.672
0.951
0.888
--
F1
0.810
0.884
0.759
0.873
0.893
--

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_area14_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8710
0.0339
0.0518
0.0372
0.0061
0.0000
building
0.0192
0.9471
0.0200
0.0128
0.0009
0.0000
low_veg
0.0852
0.0461
0.6480
0.2198
0.0009
0.0000
tree
0.0345
0.0085
0.0841
0.8728
0.0001
0.0000
car
0.1626
0.0000
0.0000
0.0015
0.8359
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.844
0.882
0.791
0.814
0.548
--
Recall/Completeness
0.871
0.947
0.648
0.873
0.836
--
F1
0.857
0.913
0.712
0.842
0.662
--

Overall accuracy 0.828

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
0.8898
0.0301
0.0487
0.0259
0.0056
0.0000
building
0.0124
0.9684
0.0120
0.0064
0.0008
0.0000
low_veg
0.0783
0.0333
0.6808
0.2068
0.0009
0.0000
tree
0.0251
0.0036
0.0737
0.8975
0.0001
0.0000
car
0.0520
0.0000
0.0000
0.0002
0.9478
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.873
0.911
0.815
0.838
0.526
--
Recall/Completeness
0.890
0.968
0.681
0.898
0.948
--
F1
0.881
0.939
0.742
0.867
0.676
--

Overall accuracy 0.854

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area16_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.7789
0.0170
0.1185
0.0827
0.0030
0.0000
building
0.0286
0.8996
0.0487
0.0225
0.0007
0.0000
low_veg
0.0245
0.0108
0.7385
0.2262
0.0001
0.0000
tree
0.0145
0.0022
0.0811
0.9022
0.0000
0.0000
car
0.1302
0.0005
0.0235
0.0381
0.8077
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.870
0.960
0.794
0.798
0.751
--
Recall/Completeness
0.779
0.900
0.738
0.902
0.808
--
F1
0.822
0.929
0.765
0.847
0.778
--

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_area16_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8163
0.0140
0.1117
0.0571
0.0010
0.0000
building
0.0247
0.9280
0.0362
0.0105
0.0006
0.0000
low_veg
0.0209
0.0072
0.7632
0.2087
0.0001
0.0000
tree
0.0087
0.0007
0.0698
0.9208
0.0000
0.0000
car
0.0675
0.0003
0.0203
0.0300
0.8819
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.898
0.974
0.822
0.824
0.838
--
Recall/Completeness
0.816
0.928
0.763
0.921
0.882
--
F1
0.855
0.950
0.792
0.870
0.859
--

Overall accuracy 0.859

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
0.7909
0.0752
0.0649
0.0644
0.0046
0.0000
building
0.0204
0.9287
0.0354
0.0144
0.0011
0.0000
low_veg
0.0640
0.0185
0.6525
0.2641
0.0010
0.0000
tree
0.0095
0.0011
0.0358
0.9536
0.0000
0.0000
car
0.2433
0.0046
0.0391
0.0146
0.6985
0.0000
clutter
0.1297
0.8581
0.0038
0.0027
0.0058
0.0000
Precision/Correctness
0.868
0.782
0.789
0.855
0.665
-nan
Recall/Completeness
0.791
0.929
0.652
0.954
0.699
0.000
F1
0.828
0.849
0.714
0.901
0.681
-nan

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_area20_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8170
0.0720
0.0616
0.0468
0.0026
0.0000
building
0.0171
0.9458
0.0300
0.0059
0.0012
0.0000
low_veg
0.0581
0.0100
0.6969
0.2340
0.0010
0.0000
tree
0.0044
0.0002
0.0260
0.9694
0.0000
0.0000
car
0.1823
0.0038
0.0358
0.0036
0.7744
0.0000
clutter
0.1147
0.8763
0.0018
0.0012
0.0060
0.0000
Precision/Correctness
0.895
0.793
0.819
0.883
0.679
-nan
Recall/Completeness
0.817
0.946
0.697
0.969
0.774
0.000
F1
0.854
0.863
0.753
0.924
0.724
-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_area22_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9033
0.0172
0.0329
0.0394
0.0071
0.0000
building
0.0669
0.9007
0.0199
0.0115
0.0010
0.0000
low_veg
0.1133
0.0234
0.6135
0.2490
0.0008
0.0000
tree
0.0267
0.0026
0.0374
0.9328
0.0005
0.0000
car
0.2760
0.0196
0.0009
0.0086
0.6949
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.864
0.935
0.833
0.805
0.733
--
Recall/Completeness
0.903
0.901
0.614
0.933
0.695
--
F1
0.883
0.917
0.707
0.864
0.713
--

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_area22_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9320
0.0123
0.0280
0.0231
0.0046
0.0000
building
0.0596
0.9222
0.0127
0.0048
0.0008
0.0000
low_veg
0.1096
0.0124
0.6584
0.2189
0.0007
0.0000
tree
0.0123
0.0008
0.0263
0.9604
0.0003
0.0000
car
0.1905
0.0226
0.0001
0.0038
0.7829
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.890
0.961
0.872
0.843
0.774
--
Recall/Completeness
0.932
0.922
0.658
0.960
0.783
--
F1
0.911
0.941
0.750
0.898
0.779
--

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_area24_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8244
0.0219
0.0894
0.0560
0.0083
0.0000
building
0.0567
0.8755
0.0497
0.0175
0.0006
0.0000
low_veg
0.0331
0.0160
0.8048
0.1456
0.0005
0.0000
tree
0.0185
0.0054
0.1149
0.8613
0.0000
0.0000
car
0.1900
0.0000
0.0020
0.0029
0.8051
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.802
0.937
0.865
0.754
0.667
--
Recall/Completeness
0.824
0.876
0.805
0.861
0.805
--
F1
0.813
0.905
0.834
0.804
0.729
--

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_area24_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8548
0.0141
0.0811
0.0436
0.0063
0.0000
building
0.0526
0.8923
0.0417
0.0127
0.0007
0.0000
low_veg
0.0301
0.0122
0.8248
0.1324
0.0005
0.0000
tree
0.0119
0.0025
0.0965
0.8891
0.0000
0.0000
car
0.0949
0.0000
0.0000
0.0009
0.9042
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.826
0.957
0.888
0.776
0.664
--
Recall/Completeness
0.855
0.892
0.825
0.889
0.904
--
F1
0.840
0.923
0.855
0.829
0.766
--

Overall accuracy 0.858

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
0.9440
0.0244
0.0126
0.0096
0.0095
0.0000
building
0.0806
0.8907
0.0197
0.0081
0.0009
0.0000
low_veg
0.1252
0.0161
0.5372
0.3213
0.0002
0.0000
tree
0.0227
0.0035
0.0258
0.9479
0.0001
0.0000
car
0.2427
0.0108
0.0058
0.0049
0.7357
0.0000
clutter
0.6007
0.1815
0.1208
0.0184
0.0785
0.0000
Precision/Correctness
0.824
0.963
0.883
0.579
0.870
-nan
Recall/Completeness
0.944
0.891
0.537
0.948
0.736
0.000
F1
0.880
0.925
0.668
0.719
0.797
-nan

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_area27_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9668
0.0170
0.0087
0.0045
0.0031
0.0000
building
0.0653
0.9154
0.0143
0.0042
0.0008
0.0000
low_veg
0.1040
0.0075
0.5729
0.3156
0.0000
0.0000
tree
0.0117
0.0010
0.0164
0.9710
0.0000
0.0000
car
0.1464
0.0124
0.0047
0.0035
0.8330
0.0000
clutter
0.5988
0.1831
0.1218
0.0082
0.0881
0.0000
Precision/Correctness
0.862
0.978
0.916
0.602
0.934
-nan
Recall/Completeness
0.967
0.915
0.573
0.971
0.833
0.000
F1
0.911
0.946
0.705
0.743
0.880
-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_area29_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9407
0.0116
0.0209
0.0193
0.0074
0.0000
building
0.0211
0.9494
0.0181
0.0114
0.0001
0.0000
low_veg
0.0776
0.0171
0.4566
0.4483
0.0004
0.0000
tree
0.0116
0.0061
0.0077
0.9746
0.0000
0.0000
car
0.2750
0.0058
0.0017
0.0083
0.7093
0.0000
clutter
0.6081
0.2268
0.0130
0.0174
0.1346
0.0000
Precision/Correctness
0.908
0.945
0.818
0.577
0.568
-nan
Recall/Completeness
0.941
0.949
0.457
0.975
0.709
0.000
F1
0.924
0.947
0.586
0.725
0.631
-nan

Overall accuracy 0.844

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area29_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9607
0.0066
0.0163
0.0107
0.0057
0.0000
building
0.0139
0.9668
0.0129
0.0063
0.0000
0.0000
low_veg
0.0523
0.0078
0.4952
0.4445
0.0002
0.0000
tree
0.0052
0.0050
0.0049
0.9848
0.0000
0.0000
car
0.1944
0.0031
0.0017
0.0048
0.7961
0.0000
clutter
0.5974
0.2398
0.0104
0.0079
0.1445
0.0000
Precision/Correctness
0.933
0.961
0.855
0.608
0.560
-nan
Recall/Completeness
0.961
0.967
0.495
0.985
0.796
0.000
F1
0.947
0.964
0.627
0.752
0.657
-nan

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_area31_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9576
0.0142
0.0085
0.0071
0.0126
0.0000
building
0.0680
0.9082
0.0135
0.0042
0.0061
0.0000
low_veg
0.0588
0.0042
0.8754
0.0611
0.0006
0.0000
tree
0.0417
0.0042
0.0612
0.8917
0.0012
0.0000
car
0.1512
0.1822
0.0266
0.0115
0.6285
0.0000
clutter
0.5302
0.2169
0.1230
0.0148
0.1151
0.0000
Precision/Correctness
0.870
0.925
0.872
0.879
0.679
-nan
Recall/Completeness
0.958
0.908
0.875
0.892
0.628
0.000
F1
0.912
0.916
0.874
0.885
0.653
-nan

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_area31_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9718
0.0114
0.0065
0.0027
0.0076
0.0000
building
0.0576
0.9266
0.0098
0.0012
0.0048
0.0000
low_veg
0.0365
0.0021
0.9129
0.0483
0.0002
0.0000
tree
0.0168
0.0013
0.0505
0.9308
0.0006
0.0000
car
0.0891
0.2031
0.0235
0.0074
0.6769
0.0000
clutter
0.4955
0.2422
0.1373
0.0073
0.1178
0.0000
Precision/Correctness
0.901
0.937
0.897
0.918
0.709
-nan
Recall/Completeness
0.972
0.927
0.913
0.931
0.677
0.000
F1
0.935
0.932
0.905
0.924
0.692
-nan

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_area33_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9840
0.0045
0.0036
0.0026
0.0052
0.0000
building
0.0624
0.8874
0.0285
0.0192
0.0025
0.0000
low_veg
0.1191
0.0076
0.6591
0.2137
0.0005
0.0000
tree
0.0674
0.0163
0.0976
0.8186
0.0001
0.0000
car
0.2626
0.0011
0.0010
0.0017
0.7336
0.0000
clutter
0.7125
0.0705
0.0020
0.0025
0.2124
0.0000
Precision/Correctness
0.816
0.968
0.835
0.684
0.397
-nan
Recall/Completeness
0.984
0.887
0.659
0.819
0.734
0.000
F1
0.892
0.926
0.737
0.745
0.515
-nan

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_area33_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9915
0.0028
0.0018
0.0005
0.0034
0.0000
building
0.0497
0.9060
0.0249
0.0174
0.0021
0.0000
low_veg
0.0825
0.0044
0.6899
0.2230
0.0002
0.0000
tree
0.0373
0.0146
0.0909
0.8572
0.0000
0.0000
car
0.1647
0.0015
0.0002
0.0002
0.8333
0.0000
clutter
0.6921
0.0736
0.0012
0.0013
0.2318
0.0000
Precision/Correctness
0.850
0.975
0.856
0.691
0.379
-nan
Recall/Completeness
0.992
0.906
0.690
0.857
0.833
0.000
F1
0.915
0.939
0.764
0.765
0.521
-nan

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_area35_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9054
0.0273
0.0464
0.0181
0.0028
0.0000
building
0.0833
0.8677
0.0387
0.0095
0.0009
0.0000
low_veg
0.0721
0.0097
0.6076
0.3104
0.0002
0.0000
tree
0.0470
0.0025
0.0954
0.8547
0.0004
0.0000
car
0.2876
0.0022
0.0008
0.0018
0.7076
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.810
0.959
0.773
0.704
0.834
--
Recall/Completeness
0.905
0.868
0.608
0.855
0.708
--
F1
0.855
0.911
0.680
0.772
0.765
--

Overall accuracy 0.809

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
0.9349
0.0252
0.0328
0.0056
0.0015
0.0000
building
0.0690
0.9022
0.0251
0.0029
0.0008
0.0000
low_veg
0.0516
0.0055
0.6350
0.3078
0.0001
0.0000
tree
0.0191
0.0005
0.0787
0.9015
0.0002
0.0000
car
0.1957
0.0024
0.0005
0.0003
0.8011
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.860
0.971
0.824
0.726
0.878
--
Recall/Completeness
0.935
0.902
0.635
0.902
0.801
--
F1
0.896
0.935
0.717
0.805
0.838
--

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_area38_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9152
0.0230
0.0327
0.0234
0.0057
0.0000
building
0.0409
0.8636
0.0805
0.0139
0.0011
0.0000
low_veg
0.0565
0.0081
0.7468
0.1884
0.0003
0.0000
tree
0.0314
0.0025
0.0541
0.9120
0.0000
0.0000
car
0.2622
0.0332
0.0248
0.0097
0.6701
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.876
0.959
0.840
0.740
0.774
--
Recall/Completeness
0.915
0.864
0.747
0.912
0.670
--
F1
0.895
0.909
0.791
0.817
0.719
--

Overall accuracy 0.852

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area38_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9388
0.0216
0.0237
0.0116
0.0043
0.0000
building
0.0316
0.8918
0.0685
0.0070
0.0011
0.0000
low_veg
0.0394
0.0041
0.7886
0.1677
0.0002
0.0000
tree
0.0159
0.0009
0.0402
0.9430
0.0000
0.0000
car
0.1797
0.0364
0.0163
0.0056
0.7620
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.914
0.970
0.871
0.777
0.787
--
Recall/Completeness
0.939
0.892
0.789
0.943
0.762
--
F1
0.926
0.929
0.828
0.852
0.774
--

Overall accuracy 0.885

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image