Detailled semantic labeling (2D) result


Name C. Zou et al.
Affiliation Simon Fraser University, Canada
Abbreviation ZISM2
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
0.825
0.046
0.097
0.027
0.005
0.000
building
0.056
0.890
0.046
0.006
0.002
0.000
low_veg
0.045
0.023
0.637
0.295
0.000
0.000
tree
0.011
0.004
0.069
0.917
0.000
0.000
car
0.436
0.025
0.021
0.004
0.513
0.000
clutter
0.555
0.325
0.077
0.024
0.020
0.000
Precision/Correctness
0.860
0.914
0.714
0.740
0.749
-nan
Recall/Completeness
0.825
0.890
0.637
0.917
0.513
0.000
F1
0.842
0.902
0.673
0.819
0.609
-nan

Overall accuracy 0.811

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
0.861
0.039
0.081
0.017
0.003
0.000
building
0.046
0.914
0.035
0.002
0.002
0.000
low_veg
0.036
0.018
0.665
0.282
0.000
0.000
tree
0.005
0.002
0.051
0.942
0.000
0.000
car
0.369
0.026
0.014
0.002
0.589
0.000
clutter
0.537
0.346
0.078
0.018
0.021
0.000
Precision/Correctness
0.891
0.932
0.762
0.766
0.786
-nan
Recall/Completeness
0.861
0.914
0.665
0.942
0.589
0.000
F1
0.875
0.923
0.710
0.845
0.673
-nan

Overall accuracy 0.842
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8653
0.0147
0.0884
0.0252
0.0063
0.0000
building
0.0590
0.8902
0.0442
0.0050
0.0016
0.0000
low_veg
0.0462
0.0165
0.6185
0.3187
0.0001
0.0000
tree
0.0140
0.0041
0.0705
0.9112
0.0002
0.0000
car
0.4058
0.0087
0.0177
0.0029
0.5649
0.0000
clutter
0.5476
0.0000
0.3355
0.1170
0.0000
0.0000
Precision/Correctness
0.829
0.958
0.729
0.720
0.814
-nan
Recall/Completeness
0.865
0.890
0.619
0.911
0.565
0.000
F1
0.847
0.923
0.669
0.804
0.667
-nan

Overall accuracy 0.802

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
0.9057
0.0103
0.0673
0.0129
0.0039
0.0000
building
0.0495
0.9173
0.0298
0.0017
0.0017
0.0000
low_veg
0.0342
0.0111
0.6407
0.3139
0.0001
0.0000
tree
0.0059
0.0023
0.0549
0.9368
0.0001
0.0000
car
0.3233
0.0081
0.0130
0.0016
0.6540
0.0000
clutter
0.5660
0.0000
0.3439
0.0900
0.0000
0.0000
Precision/Correctness
0.860
0.974
0.776
0.744
0.849
-nan
Recall/Completeness
0.906
0.917
0.641
0.937
0.654
0.000
F1
0.882
0.945
0.702
0.829
0.739
-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_area4_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8560
0.0958
0.0378
0.0052
0.0052
0.0000
building
0.0678
0.9146
0.0151
0.0016
0.0010
0.0000
low_veg
0.1227
0.0476
0.5236
0.3048
0.0012
0.0000
tree
0.0295
0.0093
0.1233
0.8374
0.0005
0.0000
car
0.4901
0.0163
0.0121
0.0011
0.4804
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.828
0.944
0.477
0.715
0.766
--
Recall/Completeness
0.856
0.915
0.524
0.837
0.480
--
F1
0.842
0.929
0.499
0.771
0.590
--

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_area4_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8928
0.0714
0.0306
0.0024
0.0027
0.0000
building
0.0531
0.9331
0.0122
0.0006
0.0010
0.0000
low_veg
0.0899
0.0271
0.5394
0.3432
0.0004
0.0000
tree
0.0118
0.0040
0.0974
0.8864
0.0004
0.0000
car
0.4291
0.0112
0.0098
0.0004
0.5495
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.864
0.962
0.512
0.738
0.813
--
Recall/Completeness
0.893
0.933
0.539
0.886
0.549
--
F1
0.878
0.947
0.525
0.805
0.656
--

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
0.8434
0.0611
0.0713
0.0169
0.0072
0.0000
building
0.0641
0.8888
0.0408
0.0035
0.0029
0.0000
low_veg
0.0861
0.0218
0.5473
0.3445
0.0003
0.0000
tree
0.0095
0.0020
0.0522
0.9361
0.0002
0.0000
car
0.4987
0.0457
0.0127
0.0014
0.4415
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.839
0.939
0.554
0.865
0.715
--
Recall/Completeness
0.843
0.889
0.547
0.936
0.441
--
F1
0.841
0.913
0.551
0.899
0.546
--

Overall accuracy 0.847

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area6_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8875
0.0435
0.0561
0.0090
0.0040
0.0000
building
0.0520
0.9105
0.0336
0.0012
0.0027
0.0000
low_veg
0.0724
0.0125
0.5798
0.3351
0.0002
0.0000
tree
0.0035
0.0006
0.0355
0.9603
0.0001
0.0000
car
0.4521
0.0352
0.0053
0.0005
0.5069
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.875
0.961
0.609
0.890
0.762
--
Recall/Completeness
0.887
0.911
0.580
0.960
0.507
--
F1
0.881
0.935
0.594
0.924
0.609
--

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_area8_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.7995
0.0450
0.1114
0.0412
0.0029
0.0000
building
0.0470
0.9121
0.0347
0.0047
0.0015
0.0000
low_veg
0.0398
0.0107
0.7281
0.2207
0.0007
0.0000
tree
0.0096
0.0040
0.0623
0.9240
0.0001
0.0000
car
0.4985
0.0042
0.0399
0.0062
0.4512
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.895
0.924
0.710
0.793
0.843
--
Recall/Completeness
0.800
0.912
0.728
0.924
0.451
--
F1
0.845
0.918
0.719
0.854
0.588
--

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_area8_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8375
0.0391
0.0953
0.0269
0.0013
0.0000
building
0.0347
0.9390
0.0229
0.0019
0.0015
0.0000
low_veg
0.0288
0.0055
0.7575
0.2078
0.0004
0.0000
tree
0.0038
0.0017
0.0427
0.9516
0.0001
0.0000
car
0.4230
0.0026
0.0296
0.0049
0.5398
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.928
0.942
0.762
0.823
0.889
--
Recall/Completeness
0.837
0.939
0.758
0.952
0.540
--
F1
0.881
0.941
0.760
0.882
0.672
--

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_area10_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.7417
0.1099
0.1225
0.0233
0.0025
0.0000
building
0.0412
0.9033
0.0444
0.0103
0.0008
0.0000
low_veg
0.0616
0.0249
0.6353
0.2782
0.0000
0.0000
tree
0.0094
0.0053
0.0899
0.8951
0.0003
0.0000
car
0.4277
0.0228
0.0342
0.0002
0.5151
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.916
0.820
0.598
0.754
0.750
--
Recall/Completeness
0.742
0.903
0.635
0.895
0.515
--
F1
0.820
0.860
0.616
0.818
0.611
--

Overall accuracy 0.791

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
0.7727
0.1045
0.1081
0.0132
0.0015
0.0000
building
0.0326
0.9249
0.0351
0.0067
0.0008
0.0000
low_veg
0.0583
0.0180
0.6681
0.2556
0.0000
0.0000
tree
0.0046
0.0029
0.0660
0.9263
0.0002
0.0000
car
0.3617
0.0194
0.0234
0.0000
0.5955
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.935
0.836
0.641
0.788
0.797
--
Recall/Completeness
0.773
0.925
0.668
0.926
0.595
--
F1
0.846
0.878
0.654
0.851
0.682
--

Overall accuracy 0.822

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
0.8018
0.0280
0.1128
0.0524
0.0049
0.0000
building
0.0568
0.8918
0.0411
0.0090
0.0014
0.0000
low_veg
0.0298
0.0210
0.5589
0.3900
0.0003
0.0000
tree
0.0044
0.0039
0.0531
0.9386
0.0000
0.0000
car
0.2654
0.0023
0.0290
0.0045
0.6988
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.835
0.937
0.788
0.740
0.768
--
Recall/Completeness
0.802
0.892
0.559
0.939
0.699
--
F1
0.818
0.914
0.654
0.827
0.732
--

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_area12_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8394
0.0258
0.0980
0.0345
0.0023
0.0000
building
0.0548
0.9141
0.0267
0.0030
0.0015
0.0000
low_veg
0.0276
0.0147
0.5888
0.3686
0.0003
0.0000
tree
0.0019
0.0015
0.0402
0.9563
0.0000
0.0000
car
0.1833
0.0020
0.0149
0.0004
0.7993
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.858
0.955
0.830
0.764
0.808
--
Recall/Completeness
0.839
0.914
0.589
0.956
0.799
--
F1
0.849
0.934
0.689
0.849
0.804
--

Overall accuracy 0.826

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
0.7447
0.0462
0.1582
0.0456
0.0053
0.0000
building
0.0256
0.9105
0.0571
0.0062
0.0005
0.0000
low_veg
0.0555
0.0360
0.5571
0.3511
0.0003
0.0000
tree
0.0180
0.0082
0.0752
0.8987
0.0000
0.0000
car
0.3786
0.0000
0.0027
0.0041
0.6146
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.870
0.877
0.665
0.749
0.542
--
Recall/Completeness
0.745
0.910
0.557
0.899
0.615
--
F1
0.802
0.893
0.606
0.817
0.576
--

Overall accuracy 0.777

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
0.7690
0.0425
0.1504
0.0336
0.0046
0.0000
building
0.0183
0.9402
0.0385
0.0025
0.0006
0.0000
low_veg
0.0496
0.0267
0.5797
0.3438
0.0003
0.0000
tree
0.0124
0.0042
0.0630
0.9204
0.0000
0.0000
car
0.3033
0.0000
0.0004
0.0006
0.6957
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.898
0.901
0.696
0.769
0.526
--
Recall/Completeness
0.769
0.940
0.580
0.920
0.696
--
F1
0.829
0.920
0.632
0.838
0.599
--

Overall accuracy 0.803

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
0.7239
0.0349
0.1638
0.0738
0.0036
0.0000
building
0.0446
0.8761
0.0644
0.0124
0.0025
0.0000
low_veg
0.0212
0.0123
0.6256
0.3408
0.0001
0.0000
tree
0.0121
0.0028
0.0545
0.9305
0.0000
0.0000
car
0.2832
0.0050
0.0542
0.0013
0.6564
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.853
0.939
0.765
0.748
0.586
--
Recall/Completeness
0.724
0.876
0.626
0.931
0.656
--
F1
0.783
0.907
0.688
0.830
0.619
--

Overall accuracy 0.798

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
0.7675
0.0307
0.1487
0.0509
0.0023
0.0000
building
0.0390
0.9052
0.0483
0.0049
0.0026
0.0000
low_veg
0.0182
0.0084
0.6477
0.3257
0.0000
0.0000
tree
0.0081
0.0009
0.0427
0.9482
0.0000
0.0000
car
0.1908
0.0012
0.0280
0.0004
0.7796
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.881
0.956
0.804
0.768
0.601
--
Recall/Completeness
0.767
0.905
0.648
0.948
0.780
--
F1
0.820
0.930
0.718
0.849
0.679
--

Overall accuracy 0.823

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
0.7558
0.0648
0.1288
0.0477
0.0029
0.0000
building
0.0136
0.9303
0.0485
0.0074
0.0002
0.0000
low_veg
0.0348
0.0258
0.5813
0.3573
0.0008
0.0000
tree
0.0029
0.0011
0.0334
0.9626
0.0000
0.0000
car
0.3746
0.0057
0.0326
0.0218
0.5653
0.0000
clutter
0.0052
0.9662
0.0256
0.0030
0.0000
0.0000
Precision/Correctness
0.928
0.773
0.699
0.831
0.746
-nan
Recall/Completeness
0.756
0.930
0.581
0.963
0.565
0.000
F1
0.833
0.844
0.635
0.892
0.643
-nan

Overall accuracy 0.814

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area20_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.7952
0.0573
0.1152
0.0305
0.0018
0.0000
building
0.0087
0.9500
0.0380
0.0030
0.0002
0.0000
low_veg
0.0305
0.0191
0.6169
0.3326
0.0009
0.0000
tree
0.0011
0.0002
0.0220
0.9767
0.0000
0.0000
car
0.3010
0.0056
0.0165
0.0134
0.6634
0.0000
clutter
0.0022
0.9779
0.0188
0.0011
0.0000
0.0000
Precision/Correctness
0.950
0.787
0.744
0.857
0.774
-nan
Recall/Completeness
0.795
0.950
0.617
0.977
0.663
0.000
F1
0.866
0.861
0.674
0.913
0.714
-nan

Overall accuracy 0.841

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
0.8175
0.0304
0.1001
0.0468
0.0051
0.0000
building
0.0302
0.9170
0.0411
0.0100
0.0016
0.0000
low_veg
0.0707
0.0305
0.5664
0.3310
0.0013
0.0000
tree
0.0111
0.0023
0.0499
0.9364
0.0002
0.0000
car
0.4699
0.0103
0.0251
0.0155
0.4791
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.903
0.907
0.679
0.763
0.702
--
Recall/Completeness
0.818
0.917
0.566
0.936
0.479
--
F1
0.858
0.912
0.618
0.841
0.569
--

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_area22_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8569
0.0246
0.0854
0.0299
0.0032
0.0000
building
0.0208
0.9463
0.0268
0.0047
0.0014
0.0000
low_veg
0.0680
0.0229
0.6014
0.3065
0.0012
0.0000
tree
0.0045
0.0010
0.0325
0.9620
0.0001
0.0000
car
0.4039
0.0135
0.0181
0.0085
0.5559
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.928
0.931
0.736
0.797
0.745
--
Recall/Completeness
0.857
0.946
0.601
0.962
0.556
--
F1
0.891
0.938
0.662
0.872
0.637
--

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_area24_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.7201
0.0428
0.1574
0.0725
0.0072
0.0000
building
0.0510
0.8625
0.0768
0.0091
0.0006
0.0000
low_veg
0.0171
0.0125
0.7768
0.1930
0.0006
0.0000
tree
0.0082
0.0052
0.0861
0.9005
0.0000
0.0000
car
0.3886
0.0000
0.0152
0.0141
0.5821
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.839
0.927
0.843
0.714
0.612
--
Recall/Completeness
0.720
0.862
0.777
0.900
0.582
--
F1
0.775
0.894
0.809
0.796
0.597
--

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_area24_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.7572
0.0358
0.1449
0.0570
0.0051
0.0000
building
0.0461
0.8822
0.0659
0.0052
0.0006
0.0000
low_veg
0.0145
0.0090
0.8011
0.1748
0.0005
0.0000
tree
0.0051
0.0028
0.0717
0.9204
0.0000
0.0000
car
0.3209
0.0000
0.0108
0.0097
0.6586
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.864
0.946
0.867
0.736
0.624
--
Recall/Completeness
0.757
0.882
0.801
0.920
0.659
--
F1
0.807
0.913
0.833
0.818
0.641
--

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_area27_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8842
0.0427
0.0543
0.0081
0.0107
0.0000
building
0.0843
0.8741
0.0367
0.0033
0.0016
0.0000
low_veg
0.0749
0.0202
0.5547
0.3495
0.0006
0.0000
tree
0.0095
0.0041
0.0651
0.9213
0.0000
0.0000
car
0.4716
0.0099
0.0115
0.0032
0.5039
0.0000
clutter
0.5660
0.2577
0.1756
0.0007
0.0000
0.0000
Precision/Correctness
0.820
0.942
0.743
0.561
0.801
-nan
Recall/Completeness
0.884
0.874
0.555
0.921
0.504
0.000
F1
0.851
0.907
0.635
0.697
0.619
-nan

Overall accuracy 0.805

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
0.9182
0.0310
0.0416
0.0043
0.0050
0.0000
building
0.0718
0.8976
0.0279
0.0012
0.0015
0.0000
low_veg
0.0585
0.0127
0.5762
0.3523
0.0002
0.0000
tree
0.0040
0.0020
0.0455
0.9485
0.0000
0.0000
car
0.4076
0.0066
0.0073
0.0022
0.5764
0.0000
clutter
0.6019
0.2466
0.1515
0.0000
0.0000
0.0000
Precision/Correctness
0.857
0.962
0.794
0.575
0.867
-nan
Recall/Completeness
0.918
0.898
0.576
0.948
0.576
0.000
F1
0.886
0.928
0.668
0.716
0.692
-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_area29_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8806
0.0360
0.0638
0.0152
0.0044
0.0000
building
0.0367
0.9336
0.0215
0.0060
0.0021
0.0000
low_veg
0.0438
0.0180
0.5076
0.4303
0.0003
0.0000
tree
0.0028
0.0019
0.0338
0.9615
0.0000
0.0000
car
0.4448
0.0030
0.0231
0.0067
0.5223
0.0000
clutter
0.4128
0.5102
0.0379
0.0158
0.0233
0.0000
Precision/Correctness
0.914
0.884
0.664
0.593
0.689
-nan
Recall/Completeness
0.881
0.934
0.508
0.962
0.522
0.000
F1
0.897
0.908
0.575
0.733
0.594
-nan

Overall accuracy 0.817

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
0.9091
0.0293
0.0507
0.0081
0.0028
0.0000
building
0.0291
0.9521
0.0137
0.0029
0.0022
0.0000
low_veg
0.0300
0.0089
0.5238
0.4371
0.0002
0.0000
tree
0.0006
0.0007
0.0206
0.9781
0.0000
0.0000
car
0.3787
0.0015
0.0211
0.0031
0.5956
0.0000
clutter
0.3887
0.5505
0.0290
0.0076
0.0242
0.0000
Precision/Correctness
0.936
0.903
0.713
0.618
0.706
-nan
Recall/Completeness
0.909
0.952
0.524
0.978
0.596
0.000
F1
0.923
0.927
0.604
0.757
0.646
-nan

Overall accuracy 0.848

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
0.9180
0.0245
0.0432
0.0049
0.0093
0.0000
building
0.0658
0.9120
0.0155
0.0035
0.0032
0.0000
low_veg
0.0640
0.0065
0.8166
0.1128
0.0001
0.0000
tree
0.0260
0.0045
0.0987
0.8702
0.0006
0.0000
car
0.3404
0.0878
0.0190
0.0033
0.5495
0.0000
clutter
0.6099
0.3006
0.0411
0.0096
0.0387
0.0000
Precision/Correctness
0.849
0.912
0.780
0.831
0.771
-nan
Recall/Completeness
0.918
0.912
0.817
0.870
0.550
0.000
F1
0.882
0.912
0.798
0.850
0.642
-nan

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_area31_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9391
0.0198
0.0341
0.0020
0.0050
0.0000
building
0.0538
0.9336
0.0087
0.0008
0.0031
0.0000
low_veg
0.0444
0.0046
0.8481
0.1029
0.0000
0.0000
tree
0.0090
0.0024
0.0690
0.9194
0.0002
0.0000
car
0.2817
0.1002
0.0105
0.0013
0.6063
0.0000
clutter
0.5774
0.3381
0.0363
0.0051
0.0431
0.0000
Precision/Correctness
0.882
0.926
0.837
0.858
0.807
-nan
Recall/Completeness
0.939
0.934
0.848
0.919
0.606
0.000
F1
0.910
0.930
0.842
0.888
0.692
-nan

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_area33_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9112
0.0290
0.0511
0.0060
0.0027
0.0000
building
0.0685
0.7780
0.1465
0.0048
0.0022
0.0000
low_veg
0.0519
0.1270
0.7262
0.0948
0.0000
0.0000
tree
0.0244
0.0032
0.1490
0.8234
0.0000
0.0000
car
0.5068
0.0288
0.0123
0.0023
0.4498
0.0000
clutter
0.9034
0.0673
0.0028
0.0008
0.0257
0.0000
Precision/Correctness
0.804
0.865
0.589
0.825
0.655
-nan
Recall/Completeness
0.911
0.778
0.726
0.823
0.450
0.000
F1
0.854
0.819
0.650
0.824
0.533
-nan

Overall accuracy 0.780

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
0.9324
0.0242
0.0391
0.0027
0.0017
0.0000
building
0.0589
0.7925
0.1438
0.0026
0.0021
0.0000
low_veg
0.0315
0.1356
0.7428
0.0901
0.0000
0.0000
tree
0.0095
0.0012
0.1290
0.8603
0.0000
0.0000
car
0.4456
0.0241
0.0096
0.0014
0.5193
0.0000
clutter
0.9062
0.0643
0.0011
0.0004
0.0281
0.0000
Precision/Correctness
0.831
0.877
0.611
0.851
0.658
-nan
Recall/Completeness
0.932
0.793
0.743
0.860
0.519
0.000
F1
0.879
0.833
0.670
0.855
0.580
-nan

Overall accuracy 0.803

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
0.7132
0.0562
0.1825
0.0463
0.0018
0.0000
building
0.0502
0.8916
0.0481
0.0086
0.0016
0.0000
low_veg
0.0197
0.0102
0.5482
0.4216
0.0003
0.0000
tree
0.0140
0.0042
0.0935
0.8883
0.0000
0.0000
car
0.4773
0.0053
0.0487
0.0029
0.4657
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.877
0.931
0.627
0.637
0.787
--
Recall/Completeness
0.713
0.892
0.548
0.888
0.466
--
F1
0.787
0.911
0.585
0.742
0.585
--

Overall accuracy 0.759

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
0.7735
0.0530
0.1477
0.0249
0.0009
0.0000
building
0.0386
0.9277
0.0291
0.0029
0.0017
0.0000
low_veg
0.0128
0.0055
0.5638
0.4175
0.0003
0.0000
tree
0.0048
0.0016
0.0650
0.9287
0.0000
0.0000
car
0.4034
0.0032
0.0374
0.0000
0.5560
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.916
0.947
0.698
0.660
0.811
--
Recall/Completeness
0.774
0.928
0.564
0.929
0.556
--
F1
0.839
0.937
0.624
0.772
0.660
--

Overall accuracy 0.800

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
0.8161
0.0284
0.1254
0.0261
0.0040
0.0000
building
0.0652
0.8633
0.0615
0.0064
0.0036
0.0000
low_veg
0.0471
0.0207
0.7132
0.2185
0.0004
0.0000
tree
0.0112
0.0021
0.0909
0.8957
0.0000
0.0000
car
0.4421
0.0160
0.0278
0.0042
0.5099
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.858
0.940
0.748
0.714
0.701
--
Recall/Completeness
0.816
0.863
0.713
0.896
0.510
--
F1
0.837
0.900
0.730
0.795
0.590
--

Overall accuracy 0.812

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
0.8572
0.0263
0.0998
0.0144
0.0022
0.0000
building
0.0533
0.8959
0.0445
0.0028
0.0036
0.0000
low_veg
0.0356
0.0182
0.7439
0.2020
0.0003
0.0000
tree
0.0040
0.0007
0.0655
0.9298
0.0000
0.0000
car
0.3721
0.0148
0.0160
0.0012
0.5959
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.894
0.950
0.801
0.745
0.727
--
Recall/Completeness
0.857
0.896
0.744
0.930
0.596
--
F1
0.875
0.922
0.771
0.827
0.655
--

Overall accuracy 0.848

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image