Detailled semantic labeling (2D) result


Name Z. Cheng
Affiliation Wuhan University, China
Abbreviation WUH_C3
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
0.905
0.028
0.044
0.018
0.006
0.000
building
0.060
0.919
0.011
0.010
0.001
0.000
low_veg
0.109
0.019
0.703
0.168
0.000
0.000
tree
0.027
0.006
0.111
0.856
0.000
0.000
car
0.434
0.024
0.016
0.005
0.521
0.000
clutter
0.658
0.153
0.015
0.006
0.016
0.152
Precision/Correctness
0.816
0.941
0.790
0.815
0.771
0.980
Recall/Completeness
0.905
0.919
0.703
0.856
0.521
0.152
F1
0.858
0.930
0.744
0.835
0.622
0.264

Overall accuracy 0.842

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
0.933
0.022
0.032
0.010
0.003
0.000
building
0.047
0.940
0.007
0.005
0.000
0.000
low_veg
0.096
0.012
0.738
0.154
0.000
0.000
tree
0.017
0.003
0.093
0.886
0.000
0.000
car
0.374
0.028
0.010
0.003
0.585
0.000
clutter
0.643
0.160
0.009
0.002
0.015
0.171
Precision/Correctness
0.849
0.959
0.831
0.845
0.822
0.989
Recall/Completeness
0.933
0.940
0.738
0.886
0.585
0.171
F1
0.889
0.949
0.781
0.865
0.683
0.291

Overall accuracy 0.873
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9232
0.0120
0.0455
0.0116
0.0077
0.0000
building
0.0549
0.9249
0.0154
0.0048
0.0000
0.0000
low_veg
0.1237
0.0113
0.7348
0.1299
0.0001
0.0000
tree
0.0319
0.0032
0.1474
0.8161
0.0001
0.0012
car
0.4070
0.0001
0.0097
0.0033
0.5799
0.0000
clutter
0.0000
0.0000
0.0150
0.0147
0.0000
0.9702
Precision/Correctness
0.802
0.970
0.776
0.848
0.819
0.983
Recall/Completeness
0.923
0.925
0.735
0.816
0.580
0.970
F1
0.858
0.947
0.755
0.832
0.679
0.977

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_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9554
0.0091
0.0260
0.0046
0.0049
0.0000
building
0.0397
0.9490
0.0095
0.0018
0.0000
0.0000
low_veg
0.1078
0.0057
0.7627
0.1237
0.0000
0.0000
tree
0.0190
0.0016
0.1293
0.8493
0.0000
0.0007
car
0.3359
0.0000
0.0063
0.0012
0.6566
0.0000
clutter
0.0000
0.0000
0.0081
0.0050
0.0000
0.9870
Precision/Correctness
0.843
0.982
0.816
0.871
0.864
0.991
Recall/Completeness
0.955
0.949
0.763
0.849
0.657
0.987
F1
0.895
0.965
0.789
0.860
0.746
0.989

Overall accuracy 0.879

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
0.9290
0.0466
0.0140
0.0060
0.0045
0.0000
building
0.0793
0.9111
0.0048
0.0048
0.0000
0.0000
low_veg
0.3212
0.0358
0.3702
0.2723
0.0005
0.0000
tree
0.0631
0.0140
0.1400
0.7817
0.0011
0.0000
car
0.5167
0.0033
0.0113
0.0007
0.4681
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.796
0.970
0.547
0.693
0.830
--
Recall/Completeness
0.929
0.911
0.370
0.782
0.468
--
F1
0.858
0.940
0.442
0.735
0.599
--

Overall accuracy 0.878

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
0.9550
0.0295
0.0105
0.0029
0.0022
0.0000
building
0.0628
0.9301
0.0040
0.0031
0.0000
0.0000
low_veg
0.2974
0.0175
0.3974
0.2875
0.0002
0.0000
tree
0.0386
0.0067
0.1386
0.8156
0.0005
0.0000
car
0.4570
0.0013
0.0068
0.0001
0.5348
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.830
0.983
0.572
0.730
0.901
--
Recall/Completeness
0.955
0.930
0.397
0.816
0.535
--
F1
0.888
0.956
0.469
0.770
0.671
--

Overall accuracy 0.905

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
0.8789
0.0669
0.0337
0.0128
0.0076
0.0000
building
0.0527
0.9290
0.0093
0.0085
0.0005
0.0000
low_veg
0.1287
0.0397
0.5604
0.2711
0.0001
0.0000
tree
0.0138
0.0061
0.0578
0.9222
0.0001
0.0000
car
0.4831
0.0070
0.0113
0.0044
0.4942
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.839
0.930
0.677
0.883
0.792
--
Recall/Completeness
0.879
0.929
0.560
0.922
0.494
--
F1
0.858
0.929
0.613
0.902
0.609
--

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
0.9175
0.0503
0.0226
0.0053
0.0042
0.0000
building
0.0418
0.9474
0.0069
0.0037
0.0003
0.0000
low_veg
0.1175
0.0248
0.5993
0.2584
0.0000
0.0000
tree
0.0057
0.0033
0.0455
0.9455
0.0000
0.0000
car
0.4328
0.0022
0.0077
0.0012
0.5561
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.875
0.953
0.730
0.910
0.856
--
Recall/Completeness
0.918
0.947
0.599
0.945
0.556
--
F1
0.896
0.950
0.658
0.927
0.674
--

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
0.8911
0.0461
0.0461
0.0124
0.0043
0.0000
building
0.0393
0.9420
0.0089
0.0098
0.0000
0.0000
low_veg
0.1035
0.0163
0.7883
0.0906
0.0013
0.0000
tree
0.0234
0.0100
0.0957
0.8708
0.0002
0.0000
car
0.4811
0.0015
0.0189
0.0045
0.4940
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.866
0.916
0.796
0.896
0.836
--
Recall/Completeness
0.891
0.942
0.788
0.871
0.494
--
F1
0.879
0.929
0.792
0.883
0.621
--

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_area8_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9205
0.0391
0.0335
0.0047
0.0023
0.0000
building
0.0247
0.9652
0.0041
0.0060
0.0000
0.0000
low_veg
0.0871
0.0084
0.8261
0.0779
0.0006
0.0000
tree
0.0122
0.0056
0.0757
0.9064
0.0001
0.0000
car
0.4159
0.0005
0.0118
0.0036
0.5683
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.903
0.938
0.843
0.923
0.896
--
Recall/Completeness
0.920
0.965
0.826
0.906
0.568
--
F1
0.911
0.952
0.835
0.915
0.696
--

Overall accuracy 0.905

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
0.8667
0.0604
0.0459
0.0234
0.0036
0.0000
building
0.0228
0.9470
0.0120
0.0172
0.0009
0.0000
low_veg
0.1347
0.0300
0.6661
0.1689
0.0003
0.0000
tree
0.0129
0.0079
0.0945
0.8847
0.0001
0.0000
car
0.3964
0.0534
0.0159
0.0048
0.5295
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.904
0.882
0.747
0.810
0.696
--
Recall/Completeness
0.867
0.947
0.666
0.885
0.529
--
F1
0.885
0.913
0.704
0.846
0.601
--

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_area10_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9015
0.0491
0.0352
0.0120
0.0023
0.0000
building
0.0152
0.9641
0.0082
0.0118
0.0007
0.0000
low_veg
0.1322
0.0208
0.7066
0.1400
0.0004
0.0000
tree
0.0070
0.0039
0.0736
0.9155
0.0000
0.0000
car
0.3326
0.0602
0.0128
0.0018
0.5925
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.922
0.908
0.798
0.855
0.740
--
Recall/Completeness
0.902
0.964
0.707
0.915
0.593
--
F1
0.912
0.935
0.749
0.884
0.658
--

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_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8942
0.0174
0.0445
0.0407
0.0031
0.0000
building
0.1852
0.7950
0.0068
0.0126
0.0004
0.0000
low_veg
0.1446
0.0228
0.5716
0.2605
0.0004
0.0000
tree
0.0246
0.0055
0.1046
0.8652
0.0000
0.0000
car
0.3938
0.0000
0.0027
0.0002
0.6034
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.590
0.932
0.781
0.793
0.822
--
Recall/Completeness
0.894
0.795
0.572
0.865
0.603
--
F1
0.711
0.858
0.660
0.827
0.696
--

Overall accuracy 0.769

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
0.9242
0.0151
0.0334
0.0259
0.0013
0.0000
building
0.1882
0.8028
0.0037
0.0048
0.0004
0.0000
low_veg
0.1418
0.0156
0.6030
0.2390
0.0005
0.0000
tree
0.0174
0.0028
0.0927
0.8871
0.0000
0.0000
car
0.2943
0.0000
0.0011
0.0000
0.7046
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.610
0.953
0.811
0.820
0.863
--
Recall/Completeness
0.924
0.803
0.603
0.887
0.705
--
F1
0.735
0.872
0.692
0.852
0.776
--

Overall accuracy 0.794

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
0.8537
0.0275
0.0784
0.0369
0.0036
0.0000
building
0.0323
0.9483
0.0075
0.0119
0.0000
0.0000
low_veg
0.1440
0.0451
0.6056
0.2049
0.0004
0.0000
tree
0.0390
0.0129
0.1087
0.8394
0.0000
0.0000
car
0.2793
0.0000
0.0225
0.0106
0.6876
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.777
0.883
0.734
0.818
0.665
--
Recall/Completeness
0.854
0.948
0.606
0.839
0.688
--
F1
0.814
0.914
0.664
0.828
0.676
--

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_area14_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8764
0.0238
0.0708
0.0261
0.0029
0.0000
building
0.0200
0.9705
0.0038
0.0056
0.0000
0.0000
low_veg
0.1381
0.0329
0.6370
0.1918
0.0003
0.0000
tree
0.0309
0.0077
0.0986
0.8628
0.0000
0.0000
car
0.2037
0.0000
0.0172
0.0088
0.7703
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.808
0.912
0.758
0.842
0.669
--
Recall/Completeness
0.876
0.971
0.637
0.863
0.770
--
F1
0.841
0.940
0.692
0.852
0.716
--

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_area16_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8496
0.0225
0.0667
0.0589
0.0023
0.0000
building
0.0434
0.9303
0.0091
0.0172
0.0000
0.0000
low_veg
0.0687
0.0154
0.6394
0.2760
0.0002
0.0003
tree
0.0447
0.0063
0.1124
0.8365
0.0001
0.0000
car
0.2808
0.0000
0.0470
0.0070
0.6652
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.744
0.941
0.781
0.765
0.771
--
Recall/Completeness
0.850
0.930
0.639
0.837
0.665
--
F1
0.793
0.936
0.703
0.799
0.714
--

Overall accuracy 0.796

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
0.8843
0.0191
0.0551
0.0403
0.0011
0.0000
building
0.0323
0.9561
0.0039
0.0077
0.0000
0.0000
low_veg
0.0614
0.0101
0.6601
0.2679
0.0002
0.0002
tree
0.0358
0.0031
0.1023
0.8587
0.0001
0.0000
car
0.2158
0.0000
0.0362
0.0004
0.7476
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.780
0.961
0.808
0.784
0.831
--
Recall/Completeness
0.884
0.956
0.660
0.859
0.748
--
F1
0.829
0.958
0.726
0.820
0.787
--

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_area20_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8261
0.0208
0.1142
0.0379
0.0011
0.0000
building
0.0194
0.9317
0.0357
0.0132
0.0000
0.0000
low_veg
0.0697
0.0130
0.7196
0.1974
0.0003
0.0000
tree
0.0062
0.0012
0.0629
0.9298
0.0000
0.0000
car
0.4406
0.0026
0.0460
0.0069
0.5039
0.0000
clutter
0.9718
0.0000
0.0279
0.0004
0.0000
0.0000
Precision/Correctness
0.779
0.955
0.715
0.888
0.881
-nan
Recall/Completeness
0.826
0.932
0.720
0.930
0.504
0.000
F1
0.802
0.943
0.717
0.909
0.641
-nan

Overall accuracy 0.842

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
0.8601
0.0158
0.1008
0.0228
0.0005
0.0000
building
0.0143
0.9503
0.0297
0.0057
0.0000
0.0000
low_veg
0.0641
0.0062
0.7616
0.1678
0.0004
0.0000
tree
0.0027
0.0001
0.0485
0.9487
0.0000
0.0000
car
0.3740
0.0004
0.0242
0.0027
0.5986
0.0000
clutter
0.9825
0.0000
0.0175
0.0001
0.0000
0.0000
Precision/Correctness
0.796
0.973
0.753
0.916
0.916
-nan
Recall/Completeness
0.860
0.950
0.762
0.949
0.599
0.000
F1
0.827
0.962
0.757
0.932
0.724
-nan

Overall accuracy 0.869

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area22_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8789
0.0220
0.0584
0.0356
0.0052
0.0000
building
0.0280
0.9450
0.0155
0.0114
0.0001
0.0000
low_veg
0.1475
0.0260
0.6224
0.2036
0.0004
0.0000
tree
0.0208
0.0028
0.0642
0.9120
0.0001
0.0000
car
0.4615
0.0195
0.0285
0.0157
0.4748
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.860
0.927
0.757
0.828
0.743
--
Recall/Completeness
0.879
0.945
0.622
0.912
0.475
--
F1
0.869
0.936
0.683
0.868
0.579
--

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_area22_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9135
0.0165
0.0475
0.0192
0.0032
0.0000
building
0.0164
0.9704
0.0084
0.0048
0.0000
0.0000
low_veg
0.1465
0.0173
0.6607
0.1752
0.0004
0.0000
tree
0.0102
0.0011
0.0479
0.9408
0.0000
0.0000
car
0.4086
0.0224
0.0221
0.0074
0.5395
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.887
0.950
0.807
0.867
0.795
--
Recall/Completeness
0.914
0.970
0.661
0.941
0.540
--
F1
0.900
0.960
0.727
0.902
0.643
--

Overall accuracy 0.879

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
0.7633
0.0334
0.1616
0.0381
0.0036
0.0000
building
0.0516
0.8791
0.0394
0.0299
0.0000
0.0000
low_veg
0.0264
0.0128
0.8566
0.1039
0.0003
0.0000
tree
0.0114
0.0085
0.1965
0.7836
0.0000
0.0000
car
0.2932
0.0000
0.0553
0.0020
0.6496
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.819
0.931
0.813
0.787
0.788
--
Recall/Completeness
0.763
0.879
0.857
0.784
0.650
--
F1
0.790
0.904
0.834
0.785
0.712
--

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_area24_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8015
0.0253
0.1439
0.0270
0.0022
0.0000
building
0.0489
0.8942
0.0308
0.0262
0.0000
0.0000
low_veg
0.0245
0.0088
0.8742
0.0921
0.0003
0.0000
tree
0.0068
0.0057
0.1782
0.8092
0.0000
0.0000
car
0.2050
0.0000
0.0382
0.0004
0.7564
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.840
0.951
0.837
0.810
0.819
--
Recall/Completeness
0.802
0.894
0.874
0.809
0.756
--
F1
0.820
0.922
0.855
0.810
0.786
--

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: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9277
0.0293
0.0194
0.0071
0.0165
0.0000
building
0.0650
0.9188
0.0085
0.0069
0.0008
0.0000
low_veg
0.1579
0.0278
0.6264
0.1871
0.0009
0.0000
tree
0.0232
0.0089
0.0685
0.8994
0.0001
0.0000
car
0.4054
0.0023
0.0127
0.0041
0.5755
0.0000
clutter
0.7450
0.1770
0.0483
0.0098
0.0199
0.0000
Precision/Correctness
0.807
0.952
0.881
0.685
0.764
-nan
Recall/Completeness
0.928
0.919
0.626
0.899
0.576
0.000
F1
0.863
0.935
0.732
0.778
0.657
-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_area27_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9568
0.0199
0.0114
0.0030
0.0090
0.0000
building
0.0500
0.9407
0.0054
0.0034
0.0005
0.0000
low_veg
0.1400
0.0174
0.6668
0.1751
0.0006
0.0000
tree
0.0128
0.0054
0.0501
0.9317
0.0000
0.0000
car
0.3543
0.0005
0.0089
0.0026
0.6337
0.0000
clutter
0.7839
0.1668
0.0291
0.0059
0.0144
0.0000
Precision/Correctness
0.844
0.970
0.922
0.720
0.829
-nan
Recall/Completeness
0.957
0.941
0.667
0.932
0.634
0.000
F1
0.897
0.955
0.774
0.812
0.718
-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_area29_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9526
0.0126
0.0185
0.0125
0.0038
0.0000
building
0.0909
0.8973
0.0031
0.0088
0.0000
0.0000
low_veg
0.1272
0.0194
0.5837
0.2696
0.0000
0.0000
tree
0.0155
0.0031
0.0487
0.9327
0.0000
0.0000
car
0.5035
0.0028
0.0190
0.0044
0.4703
0.0000
clutter
0.7331
0.2091
0.0158
0.0086
0.0334
0.0000
Precision/Correctness
0.846
0.943
0.854
0.681
0.709
-nan
Recall/Completeness
0.953
0.897
0.584
0.933
0.470
0.000
F1
0.896
0.919
0.694
0.787
0.566
-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
0.9727
0.0079
0.0109
0.0063
0.0022
0.0000
building
0.0826
0.9119
0.0009
0.0046
0.0000
0.0000
low_veg
0.1066
0.0084
0.6256
0.2593
0.0000
0.0000
tree
0.0087
0.0015
0.0389
0.9509
0.0000
0.0000
car
0.4588
0.0010
0.0158
0.0016
0.5228
0.0000
clutter
0.7299
0.2250
0.0090
0.0033
0.0329
0.0000
Precision/Correctness
0.869
0.960
0.900
0.719
0.744
-nan
Recall/Completeness
0.973
0.912
0.626
0.951
0.523
0.000
F1
0.918
0.935
0.738
0.819
0.614
-nan

Overall accuracy 0.874

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
0.9654
0.0075
0.0140
0.0032
0.0098
0.0000
building
0.0630
0.9276
0.0050
0.0034
0.0010
0.0000
low_veg
0.1082
0.0033
0.8578
0.0300
0.0008
0.0000
tree
0.0538
0.0035
0.1196
0.8229
0.0002
0.0000
car
0.3303
0.1081
0.0118
0.0079
0.5418
0.0000
clutter
0.5661
0.3830
0.0119
0.0052
0.0338
0.0000
Precision/Correctness
0.842
0.926
0.857
0.930
0.784
-nan
Recall/Completeness
0.965
0.928
0.858
0.823
0.542
0.000
F1
0.899
0.927
0.858
0.873
0.641
-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: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9798
0.0054
0.0089
0.0009
0.0051
0.0000
building
0.0458
0.9505
0.0022
0.0007
0.0007
0.0000
low_veg
0.0834
0.0012
0.8913
0.0237
0.0005
0.0000
tree
0.0307
0.0012
0.0930
0.8751
0.0000
0.0000
car
0.2665
0.1303
0.0068
0.0046
0.5918
0.0000
clutter
0.5194
0.4397
0.0065
0.0015
0.0329
0.0000
Precision/Correctness
0.879
0.934
0.901
0.957
0.839
-nan
Recall/Completeness
0.980
0.950
0.891
0.875
0.592
0.000
F1
0.927
0.942
0.896
0.914
0.694
-nan

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_area33_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9796
0.0088
0.0079
0.0025
0.0012
0.0000
building
0.0601
0.9303
0.0045
0.0043
0.0008
0.0000
low_veg
0.1233
0.0161
0.8128
0.0477
0.0001
0.0000
tree
0.0573
0.0038
0.1853
0.7536
0.0000
0.0000
car
0.6408
0.0001
0.0055
0.0020
0.3516
0.0000
clutter
0.8795
0.1039
0.0059
0.0022
0.0085
0.0000
Precision/Correctness
0.794
0.958
0.838
0.890
0.797
-nan
Recall/Completeness
0.980
0.930
0.813
0.754
0.352
0.000
F1
0.877
0.944
0.825
0.816
0.488
-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_area33_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9903
0.0055
0.0025
0.0010
0.0006
0.0000
building
0.0497
0.9449
0.0021
0.0024
0.0008
0.0000
low_veg
0.0883
0.0095
0.8548
0.0474
0.0000
0.0000
tree
0.0318
0.0011
0.1696
0.7975
0.0000
0.0000
car
0.5813
0.0000
0.0045
0.0006
0.4136
0.0000
clutter
0.8777
0.1072
0.0041
0.0019
0.0091
0.0000
Precision/Correctness
0.824
0.969
0.871
0.907
0.816
-nan
Recall/Completeness
0.990
0.945
0.855
0.798
0.414
0.000
F1
0.900
0.957
0.863
0.849
0.549
-nan

Overall accuracy 0.881

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area35_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8840
0.0265
0.0675
0.0205
0.0016
0.0000
building
0.0646
0.9159
0.0116
0.0078
0.0000
0.0000
low_veg
0.1010
0.0111
0.6605
0.2272
0.0002
0.0000
tree
0.0302
0.0045
0.1507
0.8145
0.0001
0.0000
car
0.5454
0.0325
0.0080
0.0102
0.4038
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.806
0.958
0.747
0.750
0.871
--
Recall/Completeness
0.884
0.916
0.660
0.815
0.404
--
F1
0.843
0.936
0.701
0.781
0.552
--

Overall accuracy 0.818

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
0.9305
0.0238
0.0371
0.0076
0.0010
0.0000
building
0.0434
0.9502
0.0041
0.0024
0.0000
0.0000
low_veg
0.0846
0.0067
0.6881
0.2204
0.0002
0.0000
tree
0.0141
0.0018
0.1183
0.8658
0.0000
0.0000
car
0.4730
0.0404
0.0071
0.0055
0.4741
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.855
0.970
0.819
0.778
0.908
--
Recall/Completeness
0.931
0.950
0.688
0.866
0.474
--
F1
0.891
0.960
0.748
0.819
0.623
--

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
0.9111
0.0257
0.0453
0.0115
0.0064
0.0000
building
0.0390
0.9305
0.0154
0.0129
0.0023
0.0000
low_veg
0.0931
0.0119
0.8021
0.0921
0.0008
0.0000
tree
0.0346
0.0061
0.1482
0.8110
0.0001
0.0000
car
0.4498
0.0207
0.0269
0.0049
0.4977
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.839
0.953
0.832
0.831
0.653
--
Recall/Completeness
0.911
0.931
0.802
0.811
0.498
--
F1
0.873
0.942
0.817
0.821
0.565
--

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_area38_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9409
0.0242
0.0259
0.0046
0.0044
0.0000
building
0.0234
0.9592
0.0089
0.0066
0.0019
0.0000
low_veg
0.0755
0.0066
0.8403
0.0770
0.0007
0.0000
tree
0.0230
0.0031
0.1193
0.8545
0.0000
0.0000
car
0.4014
0.0231
0.0150
0.0022
0.5584
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.880
0.965
0.879
0.870
0.683
--
Recall/Completeness
0.941
0.959
0.840
0.855
0.558
--
F1
0.910
0.962
0.859
0.862
0.614
--

Overall accuracy 0.899

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image