Detailled semantic labeling (2D) result


Name T. V. Duy
Affiliation Hanoi University of Science and Technology, Vietnam
Abbreviation BKHN_9
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
0.920
0.027
0.036
0.014
0.003
0.000
building
0.055
0.915
0.023
0.007
0.000
0.000
low_veg
0.082
0.019
0.769
0.129
0.000
0.000
tree
0.027
0.006
0.111
0.856
0.000
0.000
car
0.282
0.054
0.007
0.007
0.649
0.001
clutter
0.693
0.236
0.021
0.011
0.037
0.002
Precision/Correctness
0.842
0.938
0.800
0.851
0.859
0.410
Recall/Completeness
0.920
0.915
0.769
0.856
0.649
0.002
F1
0.879
0.926
0.784
0.853
0.739
0.003

Overall accuracy 0.860

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
0.942
0.021
0.029
0.006
0.002
0.000
building
0.046
0.933
0.016
0.004
0.000
0.000
low_veg
0.069
0.013
0.802
0.116
0.000
0.000
tree
0.014
0.003
0.095
0.888
0.000
0.000
car
0.185
0.063
0.004
0.003
0.744
0.001
clutter
0.684
0.252
0.019
0.005
0.038
0.002
Precision/Correctness
0.874
0.954
0.833
0.879
0.885
0.413
Recall/Completeness
0.942
0.933
0.802
0.888
0.744
0.002
F1
0.907
0.944
0.818
0.883
0.809
0.003

Overall accuracy 0.888
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9586
0.0093
0.0165
0.0109
0.0046
0.0000
building
0.0360
0.9418
0.0192
0.0030
0.0000
0.0000
low_veg
0.0975
0.0181
0.7135
0.1708
0.0001
0.0000
tree
0.0386
0.0115
0.0929
0.8566
0.0003
0.0000
car
0.2945
0.0120
0.0002
0.0020
0.6884
0.0029
clutter
0.8165
0.1425
0.0196
0.0214
0.0000
0.0000
Precision/Correctness
0.796
0.946
0.846
0.823
0.896
0.000
Recall/Completeness
0.959
0.942
0.714
0.857
0.688
0.000
F1
0.870
0.944
0.774
0.839
0.778
-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_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9786
0.0056
0.0098
0.0027
0.0033
0.0000
building
0.0269
0.9602
0.0118
0.0011
0.0000
0.0000
low_veg
0.0787
0.0100
0.7464
0.1649
0.0000
0.0000
tree
0.0216
0.0083
0.0812
0.8887
0.0002
0.0000
car
0.1796
0.0102
0.0000
0.0006
0.8054
0.0042
clutter
0.8341
0.1411
0.0194
0.0054
0.0000
0.0000
Precision/Correctness
0.831
0.963
0.874
0.845
0.917
0.000
Recall/Completeness
0.979
0.960
0.746
0.889
0.805
0.000
F1
0.899
0.962
0.805
0.867
0.858
-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_area4_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9279
0.0561
0.0085
0.0051
0.0024
0.0000
building
0.0525
0.9339
0.0121
0.0014
0.0000
0.0000
low_veg
0.1857
0.0463
0.5121
0.2552
0.0008
0.0000
tree
0.0584
0.0189
0.0868
0.8357
0.0002
0.0000
car
0.4133
0.0284
0.0041
0.0007
0.5535
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.853
0.964
0.628
0.746
0.913
--
Recall/Completeness
0.928
0.934
0.512
0.836
0.553
--
F1
0.889
0.949
0.564
0.788
0.689
--

Overall accuracy 0.902

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
0.9522
0.0375
0.0058
0.0030
0.0015
0.0000
building
0.0393
0.9493
0.0107
0.0007
0.0000
0.0000
low_veg
0.1470
0.0177
0.5552
0.2793
0.0009
0.0000
tree
0.0261
0.0079
0.0814
0.8846
0.0000
0.0000
car
0.3142
0.0253
0.0026
0.0000
0.6579
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.890
0.979
0.653
0.770
0.939
--
Recall/Completeness
0.952
0.949
0.555
0.885
0.658
--
F1
0.920
0.964
0.600
0.823
0.774
--

Overall accuracy 0.927

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
0.9153
0.0506
0.0244
0.0077
0.0020
0.0000
building
0.0465
0.9343
0.0158
0.0033
0.0001
0.0000
low_veg
0.1086
0.0288
0.7317
0.1306
0.0002
0.0000
tree
0.0192
0.0043
0.1367
0.8397
0.0001
0.0000
car
0.3316
0.0040
0.0007
0.0025
0.6612
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.860
0.947
0.606
0.934
0.949
--
Recall/Completeness
0.915
0.934
0.732
0.840
0.661
--
F1
0.887
0.941
0.663
0.884
0.779
--

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_area6_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9430
0.0384
0.0161
0.0018
0.0007
0.0000
building
0.0346
0.9535
0.0107
0.0011
0.0000
0.0000
low_veg
0.0884
0.0195
0.7791
0.1130
0.0000
0.0000
tree
0.0074
0.0023
0.1274
0.8629
0.0000
0.0000
car
0.2189
0.0014
0.0000
0.0003
0.7794
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.903
0.964
0.625
0.956
0.981
--
Recall/Completeness
0.943
0.954
0.779
0.863
0.779
--
F1
0.922
0.959
0.693
0.907
0.869
--

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_area8_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8954
0.0314
0.0624
0.0085
0.0023
0.0000
building
0.0360
0.9390
0.0208
0.0042
0.0000
0.0000
low_veg
0.0649
0.0112
0.8717
0.0519
0.0003
0.0000
tree
0.0319
0.0056
0.0898
0.8727
0.0001
0.0000
car
0.3175
0.0032
0.0192
0.0062
0.6539
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.892
0.942
0.788
0.937
0.932
--
Recall/Completeness
0.895
0.939
0.872
0.873
0.654
--
F1
0.894
0.940
0.828
0.904
0.768
--

Overall accuracy 0.891

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
0.9172
0.0271
0.0529
0.0019
0.0009
0.0000
building
0.0234
0.9632
0.0113
0.0021
0.0000
0.0000
low_veg
0.0473
0.0045
0.9062
0.0421
0.0000
0.0000
tree
0.0142
0.0025
0.0693
0.9141
0.0000
0.0000
car
0.2202
0.0029
0.0143
0.0031
0.7595
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.932
0.958
0.830
0.959
0.971
--
Recall/Completeness
0.917
0.963
0.906
0.914
0.760
--
F1
0.924
0.961
0.866
0.936
0.852
--

Overall accuracy 0.923

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
0.8774
0.0475
0.0537
0.0186
0.0028
0.0000
building
0.0195
0.9490
0.0195
0.0116
0.0003
0.0000
low_veg
0.0879
0.0236
0.7627
0.1253
0.0005
0.0000
tree
0.0156
0.0064
0.0822
0.8957
0.0001
0.0000
car
0.2160
0.0287
0.0056
0.0058
0.7438
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.930
0.905
0.763
0.853
0.808
--
Recall/Completeness
0.877
0.949
0.763
0.896
0.744
--
F1
0.903
0.927
0.763
0.874
0.775
--

Overall accuracy 0.877

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area10_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9081
0.0377
0.0450
0.0074
0.0019
0.0000
building
0.0132
0.9650
0.0129
0.0087
0.0002
0.0000
low_veg
0.0852
0.0147
0.8035
0.0960
0.0006
0.0000
tree
0.0064
0.0033
0.0627
0.9275
0.0001
0.0000
car
0.1184
0.0325
0.0042
0.0003
0.8446
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.947
0.929
0.805
0.898
0.834
--
Recall/Completeness
0.908
0.965
0.804
0.928
0.845
--
F1
0.927
0.947
0.804
0.912
0.839
--

Overall accuracy 0.908

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9047
0.0249
0.0416
0.0264
0.0023
0.0000
building
0.1085
0.8261
0.0585
0.0062
0.0006
0.0000
low_veg
0.0900
0.0205
0.7636
0.1258
0.0001
0.0000
tree
0.0172
0.0056
0.1416
0.8355
0.0000
0.0000
car
0.1707
0.0000
0.0002
0.0034
0.8258
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.704
0.932
0.761
0.882
0.895
--
Recall/Completeness
0.905
0.826
0.764
0.836
0.826
--
F1
0.792
0.876
0.762
0.858
0.859
--

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_area12_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9296
0.0230
0.0334
0.0138
0.0002
0.0000
building
0.1094
0.8345
0.0519
0.0035
0.0007
0.0000
low_veg
0.0870
0.0147
0.7935
0.1047
0.0001
0.0000
tree
0.0104
0.0021
0.1240
0.8635
0.0000
0.0000
car
0.0630
0.0000
0.0000
0.0000
0.9370
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.726
0.952
0.787
0.909
0.950
--
Recall/Completeness
0.930
0.835
0.793
0.864
0.937
--
F1
0.815
0.889
0.790
0.885
0.944
--

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_area14_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8609
0.0298
0.0717
0.0321
0.0054
0.0000
building
0.0174
0.9563
0.0206
0.0057
0.0000
0.0000
low_veg
0.0930
0.0423
0.7163
0.1475
0.0009
0.0000
tree
0.0358
0.0081
0.1386
0.8175
0.0000
0.0000
car
0.1537
0.0000
0.0000
0.0046
0.8416
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.835
0.892
0.733
0.857
0.601
--
Recall/Completeness
0.861
0.956
0.716
0.817
0.842
--
F1
0.848
0.923
0.724
0.837
0.702
--

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: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8788
0.0268
0.0674
0.0221
0.0049
0.0000
building
0.0102
0.9800
0.0079
0.0019
0.0000
0.0000
low_veg
0.0868
0.0321
0.7439
0.1362
0.0010
0.0000
tree
0.0264
0.0036
0.1265
0.8435
0.0000
0.0000
car
0.0484
0.0000
0.0000
0.0017
0.9499
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.864
0.917
0.755
0.879
0.574
--
Recall/Completeness
0.879
0.980
0.744
0.844
0.950
--
F1
0.871
0.947
0.750
0.861
0.716
--

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_area16_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8307
0.0262
0.0969
0.0432
0.0030
0.0000
building
0.0266
0.9374
0.0264
0.0095
0.0001
0.0000
low_veg
0.0471
0.0122
0.8313
0.1089
0.0002
0.0003
tree
0.0283
0.0032
0.1495
0.8191
0.0000
0.0000
car
0.1393
0.0001
0.0067
0.0077
0.8462
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.814
0.950
0.768
0.881
0.773
--
Recall/Completeness
0.831
0.937
0.831
0.819
0.846
--
F1
0.822
0.944
0.798
0.849
0.808
--

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_area16_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8614
0.0236
0.0874
0.0263
0.0014
0.0000
building
0.0215
0.9645
0.0105
0.0034
0.0000
0.0000
low_veg
0.0438
0.0085
0.8506
0.0965
0.0002
0.0003
tree
0.0194
0.0007
0.1337
0.8462
0.0000
0.0000
car
0.0729
0.0000
0.0039
0.0015
0.9217
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.843
0.965
0.797
0.903
0.841
--
Recall/Completeness
0.861
0.965
0.851
0.846
0.922
--
F1
0.852
0.965
0.823
0.874
0.880
--

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_area20_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8862
0.0178
0.0583
0.0352
0.0025
0.0000
building
0.0204
0.9442
0.0219
0.0135
0.0000
0.0000
low_veg
0.0818
0.0131
0.7935
0.1115
0.0001
0.0000
tree
0.0111
0.0010
0.0753
0.9126
0.0000
0.0000
car
0.2054
0.0002
0.0534
0.0239
0.7170
0.0000
clutter
0.6385
0.3598
0.0002
0.0015
0.0000
0.0000
Precision/Correctness
0.810
0.905
0.768
0.924
0.846
-nan
Recall/Completeness
0.886
0.944
0.793
0.913
0.717
0.000
F1
0.846
0.924
0.780
0.918
0.776
-nan

Overall accuracy 0.864

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
0.9126
0.0123
0.0547
0.0192
0.0012
0.0000
building
0.0169
0.9600
0.0137
0.0094
0.0000
0.0000
low_veg
0.0742
0.0061
0.8341
0.0854
0.0001
0.0000
tree
0.0049
0.0001
0.0605
0.9345
0.0000
0.0000
car
0.1267
0.0000
0.0544
0.0142
0.8046
0.0000
clutter
0.6281
0.3713
0.0000
0.0006
0.0000
0.0000
Precision/Correctness
0.833
0.919
0.799
0.948
0.902
-nan
Recall/Completeness
0.913
0.960
0.834
0.934
0.805
0.000
F1
0.871
0.939
0.816
0.941
0.850
-nan

Overall accuracy 0.889

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
0.8992
0.0239
0.0431
0.0286
0.0051
0.0000
building
0.0217
0.9529
0.0187
0.0066
0.0001
0.0000
low_veg
0.1165
0.0368
0.7291
0.1174
0.0001
0.0000
tree
0.0234
0.0032
0.0755
0.8977
0.0001
0.0000
car
0.2971
0.0137
0.0097
0.0164
0.6631
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.885
0.913
0.791
0.883
0.810
--
Recall/Completeness
0.899
0.953
0.729
0.898
0.663
--
F1
0.892
0.933
0.759
0.890
0.729
--

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_area22_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9293
0.0190
0.0354
0.0129
0.0034
0.0000
building
0.0144
0.9749
0.0078
0.0028
0.0000
0.0000
low_veg
0.1127
0.0288
0.7677
0.0908
0.0000
0.0000
tree
0.0096
0.0008
0.0587
0.9309
0.0000
0.0000
car
0.2113
0.0176
0.0075
0.0063
0.7573
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.912
0.936
0.834
0.922
0.847
--
Recall/Completeness
0.929
0.975
0.768
0.931
0.757
--
F1
0.921
0.955
0.800
0.927
0.800
--

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_area24_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8067
0.0292
0.1282
0.0319
0.0040
0.0000
building
0.0645
0.8773
0.0472
0.0110
0.0000
0.0000
low_veg
0.0276
0.0165
0.8855
0.0703
0.0002
0.0000
tree
0.0218
0.0051
0.1809
0.7921
0.0000
0.0000
car
0.2894
0.0000
0.0247
0.0040
0.6819
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.796
0.930
0.832
0.849
0.797
--
Recall/Completeness
0.807
0.877
0.885
0.792
0.682
--
F1
0.801
0.903
0.858
0.820
0.735
--

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_area24_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8357
0.0213
0.1174
0.0222
0.0034
0.0000
building
0.0620
0.8936
0.0360
0.0085
0.0000
0.0000
low_veg
0.0242
0.0136
0.9010
0.0611
0.0002
0.0000
tree
0.0151
0.0020
0.1575
0.8254
0.0000
0.0000
car
0.1840
0.0000
0.0170
0.0008
0.7982
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.820
0.949
0.857
0.872
0.795
--
Recall/Completeness
0.836
0.894
0.901
0.825
0.798
--
F1
0.828
0.920
0.878
0.848
0.797
--

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_area27_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9533
0.0196
0.0156
0.0066
0.0049
0.0000
building
0.0669
0.9132
0.0153
0.0046
0.0001
0.0000
low_veg
0.1270
0.0202
0.6508
0.2016
0.0004
0.0001
tree
0.0193
0.0066
0.0416
0.9322
0.0002
0.0000
car
0.3004
0.0070
0.0057
0.0076
0.6786
0.0007
clutter
0.7696
0.0778
0.0551
0.0228
0.0744
0.0004
Precision/Correctness
0.831
0.966
0.896
0.683
0.920
0.025
Recall/Completeness
0.953
0.913
0.651
0.932
0.679
0.000
F1
0.888
0.939
0.754
0.788
0.781
0.001

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_area27_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9743
0.0123
0.0103
0.0021
0.0011
0.0000
building
0.0533
0.9352
0.0093
0.0021
0.0001
0.0000
low_veg
0.1105
0.0101
0.6898
0.1893
0.0003
0.0001
tree
0.0101
0.0027
0.0269
0.9603
0.0000
0.0000
car
0.1981
0.0076
0.0029
0.0054
0.7851
0.0009
clutter
0.8059
0.0633
0.0402
0.0180
0.0721
0.0005
Precision/Correctness
0.866
0.982
0.933
0.715
0.972
0.027
Recall/Completeness
0.974
0.935
0.690
0.960
0.785
0.001
F1
0.917
0.958
0.793
0.819
0.868
0.001

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_area29_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9560
0.0126
0.0173
0.0105
0.0037
0.0000
building
0.0663
0.9144
0.0132
0.0060
0.0000
0.0000
low_veg
0.1164
0.0221
0.5912
0.2703
0.0000
0.0000
tree
0.0124
0.0059
0.0334
0.9484
0.0000
0.0000
car
0.2882
0.0041
0.0009
0.0082
0.6986
0.0000
clutter
0.6887
0.2221
0.0196
0.0157
0.0537
0.0002
Precision/Correctness
0.869
0.940
0.852
0.690
0.748
0.788
Recall/Completeness
0.956
0.914
0.591
0.948
0.699
0.000
F1
0.911
0.927
0.698
0.799
0.722
0.000

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_area29_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9734
0.0078
0.0121
0.0040
0.0026
0.0000
building
0.0610
0.9276
0.0085
0.0029
0.0000
0.0000
low_veg
0.0948
0.0111
0.6369
0.2572
0.0000
0.0000
tree
0.0065
0.0041
0.0270
0.9623
0.0000
0.0000
car
0.1938
0.0029
0.0001
0.0048
0.7984
0.0000
clutter
0.6870
0.2326
0.0168
0.0061
0.0572
0.0002
Precision/Correctness
0.891
0.957
0.889
0.729
0.753
0.793
Recall/Completeness
0.973
0.928
0.637
0.962
0.798
0.000
F1
0.930
0.942
0.742
0.830
0.775
0.000

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_area31_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9732
0.0124
0.0098
0.0025
0.0021
0.0000
building
0.1471
0.8261
0.0242
0.0017
0.0009
0.0000
low_veg
0.0649
0.0036
0.8977
0.0334
0.0005
0.0000
tree
0.0502
0.0032
0.0892
0.8569
0.0005
0.0000
car
0.2194
0.2744
0.0106
0.0077
0.4866
0.0012
clutter
0.5735
0.3253
0.0385
0.0167
0.0436
0.0023
Precision/Correctness
0.820
0.896
0.857
0.930
0.868
0.621
Recall/Completeness
0.973
0.826
0.898
0.857
0.487
0.002
F1
0.890
0.860
0.877
0.892
0.624
0.005

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_area31_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9821
0.0090
0.0077
0.0003
0.0008
0.0000
building
0.1369
0.8441
0.0181
0.0002
0.0007
0.0000
low_veg
0.0428
0.0022
0.9281
0.0266
0.0003
0.0000
tree
0.0215
0.0007
0.0745
0.9031
0.0001
0.0000
car
0.1383
0.3120
0.0038
0.0036
0.5406
0.0017
clutter
0.5281
0.3745
0.0372
0.0102
0.0473
0.0028
Precision/Correctness
0.848
0.910
0.887
0.956
0.885
0.624
Recall/Completeness
0.982
0.844
0.928
0.903
0.541
0.003
F1
0.910
0.876
0.907
0.929
0.671
0.006

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_area33_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9796
0.0100
0.0064
0.0024
0.0016
0.0000
building
0.1214
0.7996
0.0379
0.0387
0.0025
0.0000
low_veg
0.1062
0.0108
0.7103
0.1713
0.0014
0.0000
tree
0.0557
0.0132
0.1394
0.7917
0.0000
0.0000
car
0.3019
0.0050
0.0017
0.0035
0.6851
0.0028
clutter
0.7442
0.1727
0.0191
0.0014
0.0590
0.0036
Precision/Correctness
0.788
0.934
0.790
0.682
0.650
0.837
Recall/Completeness
0.980
0.800
0.710
0.792
0.685
0.004
F1
0.873
0.862
0.748
0.733
0.667
0.007

Overall accuracy 0.810

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
0.9876
0.0075
0.0039
0.0004
0.0006
0.0000
building
0.1156
0.8082
0.0355
0.0384
0.0024
0.0000
low_veg
0.0706
0.0048
0.7433
0.1800
0.0012
0.0000
tree
0.0264
0.0099
0.1304
0.8334
0.0000
0.0000
car
0.2066
0.0069
0.0002
0.0020
0.7803
0.0039
clutter
0.7285
0.1847
0.0172
0.0013
0.0641
0.0042
Precision/Correctness
0.814
0.946
0.810
0.686
0.641
0.834
Recall/Completeness
0.988
0.808
0.743
0.833
0.780
0.004
F1
0.893
0.872
0.775
0.753
0.704
0.008

Overall accuracy 0.830

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
0.8942
0.0329
0.0550
0.0169
0.0009
0.0002
building
0.0424
0.9252
0.0269
0.0051
0.0004
0.0000
low_veg
0.0626
0.0083
0.7028
0.2258
0.0004
0.0000
tree
0.0324
0.0038
0.1082
0.8555
0.0001
0.0000
car
0.2698
0.0288
0.0004
0.0069
0.6942
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.860
0.956
0.790
0.765
0.919
--
Recall/Completeness
0.894
0.925
0.703
0.855
0.694
--
F1
0.877
0.940
0.744
0.808
0.791
--

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_area35_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9293
0.0301
0.0371
0.0032
0.0001
0.0002
building
0.0297
0.9555
0.0135
0.0010
0.0004
0.0000
low_veg
0.0461
0.0041
0.7293
0.2200
0.0005
0.0000
tree
0.0105
0.0009
0.0836
0.9050
0.0000
0.0000
car
0.1709
0.0343
0.0000
0.0007
0.7940
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.908
0.968
0.848
0.790
0.948
--
Recall/Completeness
0.929
0.956
0.729
0.905
0.794
--
F1
0.919
0.962
0.784
0.844
0.864
--

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_area38_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9283
0.0303
0.0294
0.0096
0.0024
0.0000
building
0.0255
0.9386
0.0308
0.0045
0.0005
0.0000
low_veg
0.0789
0.0177
0.8232
0.0800
0.0002
0.0000
tree
0.0292
0.0091
0.1158
0.8457
0.0003
0.0000
car
0.2604
0.0356
0.0124
0.0092
0.6818
0.0006
clutter
--
--
--
--
--
--
Precision/Correctness
0.871
0.940
0.857
0.863
0.885
--
Recall/Completeness
0.928
0.939
0.823
0.846
0.682
--
F1
0.899
0.939
0.840
0.854
0.770
--

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_area38_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9485
0.0288
0.0189
0.0025
0.0013
0.0000
building
0.0165
0.9631
0.0183
0.0018
0.0004
0.0000
low_veg
0.0621
0.0138
0.8585
0.0656
0.0001
0.0000
tree
0.0116
0.0070
0.0931
0.8881
0.0003
0.0000
car
0.1652
0.0412
0.0021
0.0021
0.7886
0.0009
clutter
--
--
--
--
--
--
Precision/Correctness
0.911
0.951
0.896
0.897
0.916
--
Recall/Completeness
0.949
0.963
0.859
0.888
0.789
--
F1
0.929
0.957
0.877
0.893
0.847
--

Overall accuracy 0.915

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image