Detailled semantic labeling (2D) result


Name S. Piramanayagam et al.
Affiliation RIT, USA
Abbreviation RIT_7
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
0.907
0.030
0.043
0.016
0.005
0.000
building
0.044
0.933
0.016
0.006
0.001
0.000
low_veg
0.060
0.024
0.783
0.132
0.000
0.000
tree
0.023
0.007
0.099
0.871
0.000
0.000
car
0.249
0.043
0.012
0.006
0.690
0.000
clutter
0.613
0.302
0.036
0.010
0.039
0.000
Precision/Correctness
0.868
0.930
0.814
0.851
0.818
-nan
Recall/Completeness
0.907
0.933
0.783
0.871
0.690
0.000
F1
0.887
0.931
0.798
0.861
0.749
-nan

Overall accuracy 0.868

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
0.934
0.022
0.034
0.007
0.002
0.000
building
0.036
0.951
0.010
0.003
0.001
0.000
low_veg
0.047
0.013
0.821
0.118
0.000
0.000
tree
0.011
0.003
0.082
0.904
0.000
0.000
car
0.141
0.049
0.007
0.003
0.800
0.000
clutter
0.602
0.320
0.034
0.004
0.040
0.000
Precision/Correctness
0.900
0.953
0.849
0.880
0.857
-nan
Recall/Completeness
0.934
0.951
0.821
0.904
0.800
0.000
F1
0.917
0.952
0.835
0.892
0.828
-nan

Overall accuracy 0.899
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9491
0.0089
0.0224
0.0134
0.0062
0.0000
building
0.0311
0.9460
0.0192
0.0036
0.0001
0.0000
low_veg
0.0895
0.0196
0.7194
0.1712
0.0003
0.0000
tree
0.0328
0.0096
0.0877
0.8696
0.0003
0.0000
car
0.2772
0.0102
0.0029
0.0028
0.7070
0.0000
clutter
0.9631
0.0052
0.0017
0.0300
0.0001
0.0000
Precision/Correctness
0.800
0.958
0.847
0.821
0.865
-nan
Recall/Completeness
0.949
0.946
0.719
0.870
0.707
0.000
F1
0.868
0.952
0.778
0.845
0.778
-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_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9736
0.0052
0.0134
0.0037
0.0040
0.0000
building
0.0212
0.9669
0.0109
0.0010
0.0000
0.0000
low_veg
0.0707
0.0089
0.7557
0.1645
0.0002
0.0000
tree
0.0166
0.0054
0.0756
0.9022
0.0001
0.0000
car
0.1475
0.0113
0.0015
0.0007
0.8390
0.0000
clutter
0.9847
0.0046
0.0017
0.0090
0.0001
0.0000
Precision/Correctness
0.835
0.979
0.879
0.847
0.904
-nan
Recall/Completeness
0.974
0.967
0.756
0.902
0.839
0.000
F1
0.899
0.973
0.813
0.874
0.870
-nan

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_area4_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9316
0.0509
0.0079
0.0052
0.0045
0.0000
building
0.0519
0.9379
0.0076
0.0016
0.0011
0.0000
low_veg
0.1689
0.0579
0.4928
0.2770
0.0035
0.0000
tree
0.0666
0.0189
0.0673
0.8463
0.0009
0.0000
car
0.3666
0.0084
0.0026
0.0011
0.6214
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.858
0.966
0.691
0.733
0.811
--
Recall/Completeness
0.932
0.938
0.493
0.846
0.621
--
F1
0.893
0.952
0.575
0.786
0.703
--

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_area4_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9604
0.0292
0.0054
0.0024
0.0026
0.0000
building
0.0383
0.9535
0.0066
0.0007
0.0010
0.0000
low_veg
0.1292
0.0220
0.5427
0.3030
0.0031
0.0000
tree
0.0353
0.0067
0.0626
0.8953
0.0002
0.0000
car
0.2614
0.0017
0.0009
0.0003
0.7357
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.895
0.983
0.721
0.761
0.848
--
Recall/Completeness
0.960
0.953
0.543
0.895
0.736
--
F1
0.926
0.968
0.619
0.823
0.788
--

Overall accuracy 0.933

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
0.8910
0.0577
0.0372
0.0099
0.0042
0.0000
building
0.0420
0.9380
0.0157
0.0040
0.0003
0.0000
low_veg
0.0747
0.0426
0.7585
0.1235
0.0007
0.0000
tree
0.0182
0.0048
0.0674
0.9095
0.0001
0.0000
car
0.3056
0.0159
0.0031
0.0025
0.6730
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.876
0.937
0.703
0.939
0.895
--
Recall/Completeness
0.891
0.938
0.758
0.910
0.673
--
F1
0.884
0.937
0.730
0.924
0.768
--

Overall accuracy 0.894

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
0.9283
0.0402
0.0270
0.0031
0.0014
0.0000
building
0.0331
0.9545
0.0107
0.0014
0.0002
0.0000
low_veg
0.0588
0.0259
0.8088
0.1062
0.0004
0.0000
tree
0.0073
0.0014
0.0526
0.9385
0.0000
0.0000
car
0.1882
0.0094
0.0014
0.0004
0.8007
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.915
0.962
0.751
0.960
0.956
--
Recall/Completeness
0.928
0.955
0.809
0.939
0.801
--
F1
0.921
0.958
0.779
0.949
0.871
--

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_area8_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8817
0.0358
0.0700
0.0079
0.0046
0.0000
building
0.0335
0.9490
0.0131
0.0044
0.0001
0.0000
low_veg
0.0489
0.0151
0.8868
0.0488
0.0005
0.0000
tree
0.0283
0.0075
0.0914
0.8726
0.0001
0.0000
car
0.2826
0.0112
0.0198
0.0054
0.6810
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.905
0.931
0.787
0.941
0.878
--
Recall/Completeness
0.882
0.949
0.887
0.873
0.681
--
F1
0.893
0.940
0.834
0.905
0.767
--

Overall accuracy 0.893

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
0.9088
0.0285
0.0586
0.0015
0.0026
0.0000
building
0.0245
0.9679
0.0054
0.0021
0.0001
0.0000
low_veg
0.0324
0.0065
0.9236
0.0375
0.0001
0.0000
tree
0.0116
0.0032
0.0700
0.9152
0.0000
0.0000
car
0.1700
0.0098
0.0111
0.0029
0.8062
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.943
0.954
0.831
0.964
0.923
--
Recall/Completeness
0.909
0.968
0.924
0.915
0.806
--
F1
0.926
0.961
0.875
0.939
0.861
--

Overall accuracy 0.926

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
0.8442
0.0640
0.0707
0.0190
0.0020
0.0000
building
0.0296
0.9446
0.0140
0.0114
0.0004
0.0000
low_veg
0.0737
0.0334
0.7547
0.1378
0.0005
0.0000
tree
0.0149
0.0103
0.0827
0.8920
0.0000
0.0000
car
0.2678
0.0352
0.0063
0.0035
0.6873
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.927
0.874
0.739
0.843
0.835
--
Recall/Completeness
0.844
0.945
0.755
0.892
0.687
--
F1
0.884
0.908
0.747
0.867
0.754
--

Overall accuracy 0.861

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
0.8774
0.0496
0.0643
0.0077
0.0010
0.0000
building
0.0242
0.9587
0.0082
0.0085
0.0004
0.0000
low_veg
0.0708
0.0202
0.8013
0.1072
0.0005
0.0000
tree
0.0063
0.0049
0.0648
0.9240
0.0000
0.0000
car
0.1628
0.0418
0.0021
0.0008
0.7925
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.944
0.907
0.773
0.889
0.876
--
Recall/Completeness
0.877
0.959
0.801
0.924
0.793
--
F1
0.910
0.932
0.787
0.906
0.832
--

Overall accuracy 0.893

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
0.8932
0.0274
0.0478
0.0272
0.0044
0.0000
building
0.1692
0.8104
0.0146
0.0051
0.0008
0.0000
low_veg
0.0566
0.0242
0.7654
0.1535
0.0003
0.0000
tree
0.0133
0.0089
0.1133
0.8645
0.0000
0.0000
car
0.1670
0.0013
0.0132
0.0040
0.8145
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.700
0.916
0.811
0.866
0.825
--
Recall/Completeness
0.893
0.810
0.765
0.864
0.815
--
F1
0.785
0.860
0.788
0.865
0.820
--

Overall accuracy 0.829

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
0.9213
0.0240
0.0388
0.0144
0.0015
0.0000
building
0.1769
0.8152
0.0061
0.0012
0.0007
0.0000
low_veg
0.0546
0.0134
0.8003
0.1315
0.0002
0.0000
tree
0.0072
0.0036
0.0952
0.8941
0.0000
0.0000
car
0.0549
0.0019
0.0046
0.0009
0.9376
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.714
0.949
0.843
0.894
0.891
--
Recall/Completeness
0.921
0.815
0.800
0.894
0.938
--
F1
0.805
0.877
0.821
0.894
0.914
--

Overall accuracy 0.856

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area14_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8350
0.0317
0.0962
0.0309
0.0062
0.0000
building
0.0128
0.9656
0.0138
0.0071
0.0006
0.0000
low_veg
0.0787
0.0537
0.7193
0.1478
0.0006
0.0000
tree
0.0295
0.0141
0.1263
0.8301
0.0001
0.0000
car
0.1380
0.0012
0.0000
0.0071
0.8537
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.855
0.869
0.732
0.858
0.573
--
Recall/Completeness
0.835
0.966
0.719
0.830
0.854
--
F1
0.845
0.915
0.726
0.844
0.686
--

Overall accuracy 0.827

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
0.8549
0.0265
0.0925
0.0207
0.0054
0.0000
building
0.0078
0.9836
0.0053
0.0027
0.0006
0.0000
low_veg
0.0730
0.0383
0.7523
0.1358
0.0006
0.0000
tree
0.0209
0.0070
0.1148
0.8572
0.0000
0.0000
car
0.0438
0.0003
0.0000
0.0025
0.9534
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.882
0.904
0.753
0.881
0.556
--
Recall/Completeness
0.855
0.984
0.752
0.857
0.953
--
F1
0.868
0.942
0.753
0.869
0.703
--

Overall accuracy 0.853

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
0.8268
0.0368
0.0896
0.0435
0.0033
0.0000
building
0.0207
0.9498
0.0183
0.0102
0.0010
0.0000
low_veg
0.0189
0.0162
0.8527
0.1112
0.0010
0.0000
tree
0.0229
0.0064
0.1351
0.8355
0.0001
0.0000
car
0.1230
0.0023
0.0049
0.0200
0.8498
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.877
0.929
0.791
0.881
0.651
--
Recall/Completeness
0.827
0.950
0.853
0.836
0.850
--
F1
0.851
0.939
0.821
0.857
0.737
--

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_area16_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8605
0.0320
0.0796
0.0263
0.0015
0.0000
building
0.0173
0.9706
0.0068
0.0044
0.0010
0.0000
low_veg
0.0151
0.0091
0.8765
0.0981
0.0011
0.0000
tree
0.0154
0.0019
0.1202
0.8624
0.0001
0.0000
car
0.0422
0.0000
0.0015
0.0088
0.9475
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.907
0.955
0.819
0.903
0.663
--
Recall/Completeness
0.861
0.971
0.877
0.862
0.948
--
F1
0.883
0.963
0.847
0.882
0.780
--

Overall accuracy 0.886

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
0.8561
0.0396
0.0601
0.0394
0.0047
0.0000
building
0.0184
0.9468
0.0263
0.0085
0.0000
0.0000
low_veg
0.0595
0.0251
0.7669
0.1482
0.0003
0.0000
tree
0.0078
0.0026
0.0553
0.9344
0.0000
0.0000
car
0.1464
0.0194
0.0244
0.0243
0.7855
0.0000
clutter
0.2906
0.5871
0.1198
0.0017
0.0007
0.0000
Precision/Correctness
0.868
0.838
0.778
0.910
0.758
-nan
Recall/Completeness
0.856
0.947
0.767
0.934
0.785
0.000
F1
0.862
0.889
0.772
0.922
0.771
-nan

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_area20_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8879
0.0314
0.0557
0.0220
0.0029
0.0000
building
0.0159
0.9582
0.0213
0.0046
0.0000
0.0000
low_veg
0.0528
0.0114
0.8142
0.1212
0.0004
0.0000
tree
0.0028
0.0006
0.0423
0.9543
0.0000
0.0000
car
0.0515
0.0206
0.0125
0.0130
0.9023
0.0000
clutter
0.2822
0.6002
0.1162
0.0006
0.0007
0.0000
Precision/Correctness
0.891
0.861
0.808
0.935
0.797
-nan
Recall/Completeness
0.888
0.958
0.814
0.954
0.902
0.000
F1
0.890
0.907
0.811
0.945
0.846
-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
0.8888
0.0270
0.0467
0.0306
0.0069
0.0000
building
0.0140
0.9694
0.0117
0.0047
0.0001
0.0000
low_veg
0.1011
0.0416
0.7291
0.1274
0.0007
0.0000
tree
0.0227
0.0045
0.0758
0.8969
0.0001
0.0000
car
0.2379
0.0119
0.0285
0.0162
0.7055
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.898
0.904
0.790
0.876
0.764
--
Recall/Completeness
0.889
0.969
0.729
0.897
0.705
--
F1
0.894
0.935
0.758
0.886
0.734
--

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
0.9230
0.0179
0.0391
0.0153
0.0047
0.0000
building
0.0085
0.9847
0.0055
0.0013
0.0000
0.0000
low_veg
0.0987
0.0255
0.7752
0.1000
0.0006
0.0000
tree
0.0090
0.0012
0.0588
0.9309
0.0000
0.0000
car
0.1345
0.0138
0.0199
0.0063
0.8255
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.924
0.941
0.831
0.915
0.803
--
Recall/Completeness
0.923
0.985
0.775
0.931
0.826
--
F1
0.924
0.962
0.802
0.923
0.814
--

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_area24_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8229
0.0384
0.0952
0.0331
0.0104
0.0000
building
0.0592
0.8978
0.0249
0.0177
0.0005
0.0000
low_veg
0.0253
0.0227
0.8820
0.0697
0.0003
0.0000
tree
0.0186
0.0079
0.1626
0.8108
0.0003
0.0000
car
0.1659
0.0000
0.0070
0.0082
0.8189
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.817
0.909
0.858
0.848
0.633
--
Recall/Completeness
0.823
0.898
0.882
0.811
0.819
--
F1
0.820
0.903
0.870
0.829
0.714
--

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_area24_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8542
0.0282
0.0870
0.0226
0.0081
0.0000
building
0.0570
0.9099
0.0173
0.0154
0.0004
0.0000
low_veg
0.0215
0.0174
0.9020
0.0588
0.0003
0.0000
tree
0.0115
0.0034
0.1410
0.8439
0.0002
0.0000
car
0.0815
0.0000
0.0005
0.0035
0.9145
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.842
0.935
0.881
0.873
0.635
--
Recall/Completeness
0.854
0.910
0.902
0.844
0.915
--
F1
0.848
0.922
0.891
0.858
0.750
--

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_area27_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9417
0.0232
0.0204
0.0069
0.0077
0.0000
building
0.0584
0.9232
0.0139
0.0043
0.0003
0.0000
low_veg
0.0833
0.0271
0.6886
0.2007
0.0003
0.0000
tree
0.0147
0.0061
0.0483
0.9306
0.0003
0.0000
car
0.2459
0.0061
0.0093
0.0041
0.7346
0.0000
clutter
0.7228
0.1179
0.0958
0.0162
0.0473
0.0000
Precision/Correctness
0.862
0.959
0.889
0.684
0.896
-nan
Recall/Completeness
0.942
0.923
0.689
0.931
0.735
0.000
F1
0.900
0.941
0.776
0.788
0.807
-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_area27_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9684
0.0135
0.0133
0.0023
0.0025
0.0000
building
0.0466
0.9431
0.0084
0.0017
0.0002
0.0000
low_veg
0.0650
0.0115
0.7321
0.1913
0.0001
0.0000
tree
0.0065
0.0019
0.0302
0.9613
0.0001
0.0000
car
0.1346
0.0029
0.0060
0.0027
0.8538
0.0000
clutter
0.7367
0.1169
0.0804
0.0101
0.0559
0.0000
Precision/Correctness
0.899
0.980
0.929
0.714
0.954
-nan
Recall/Completeness
0.968
0.943
0.732
0.961
0.854
0.000
F1
0.932
0.961
0.819
0.819
0.901
-nan

Overall accuracy 0.909

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
0.9429
0.0161
0.0231
0.0126
0.0053
0.0000
building
0.0290
0.9556
0.0095
0.0058
0.0001
0.0000
low_veg
0.0731
0.0248
0.6196
0.2823
0.0002
0.0000
tree
0.0067
0.0044
0.0281
0.9608
0.0000
0.0000
car
0.2621
0.0039
0.0041
0.0142
0.7157
0.0000
clutter
0.6272
0.2969
0.0273
0.0115
0.0372
0.0000
Precision/Correctness
0.906
0.929
0.849
0.681
0.738
-nan
Recall/Completeness
0.943
0.956
0.620
0.961
0.716
0.000
F1
0.924
0.942
0.716
0.797
0.727
-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_area29_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9641
0.0096
0.0173
0.0052
0.0038
0.0000
building
0.0232
0.9692
0.0050
0.0026
0.0000
0.0000
low_veg
0.0511
0.0102
0.6694
0.2691
0.0001
0.0000
tree
0.0021
0.0019
0.0200
0.9760
0.0000
0.0000
car
0.1607
0.0011
0.0038
0.0099
0.8245
0.0000
clutter
0.6254
0.3096
0.0216
0.0041
0.0394
0.0000
Precision/Correctness
0.928
0.951
0.888
0.722
0.755
-nan
Recall/Completeness
0.964
0.969
0.669
0.976
0.825
0.000
F1
0.946
0.960
0.763
0.830
0.788
-nan

Overall accuracy 0.899

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area31_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9695
0.0114
0.0112
0.0032
0.0048
0.0000
building
0.0543
0.9316
0.0106
0.0021
0.0015
0.0000
low_veg
0.0497
0.0079
0.9125
0.0294
0.0005
0.0000
tree
0.0450
0.0037
0.1102
0.8401
0.0011
0.0000
car
0.1694
0.2028
0.0104
0.0043
0.6131
0.0000
clutter
0.4725
0.4174
0.0387
0.0115
0.0600
0.0000
Precision/Correctness
0.884
0.904
0.864
0.934
0.831
-nan
Recall/Completeness
0.969
0.932
0.913
0.840
0.613
0.000
F1
0.925
0.918
0.887
0.885
0.706
-nan

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_area31_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9839
0.0061
0.0081
0.0006
0.0013
0.0000
building
0.0440
0.9491
0.0055
0.0003
0.0010
0.0000
low_veg
0.0294
0.0041
0.9437
0.0227
0.0001
0.0000
tree
0.0168
0.0007
0.0902
0.8921
0.0002
0.0000
car
0.0793
0.2274
0.0037
0.0013
0.6884
0.0000
clutter
0.4282
0.4646
0.0372
0.0060
0.0640
0.0000
Precision/Correctness
0.918
0.921
0.899
0.961
0.876
-nan
Recall/Completeness
0.984
0.949
0.944
0.892
0.688
0.000
F1
0.950
0.935
0.921
0.925
0.771
-nan

Overall accuracy 0.919

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
0.9789
0.0071
0.0096
0.0027
0.0017
0.0000
building
0.0405
0.9305
0.0181
0.0076
0.0032
0.0000
low_veg
0.0851
0.0129
0.8005
0.1011
0.0004
0.0000
tree
0.0464
0.0064
0.1389
0.8083
0.0001
0.0000
car
0.3084
0.0215
0.0029
0.0052
0.6620
0.0000
clutter
0.6784
0.2465
0.0093
0.0003
0.0655
0.0000
Precision/Correctness
0.843
0.934
0.837
0.818
0.620
-nan
Recall/Completeness
0.979
0.930
0.800
0.808
0.662
0.000
F1
0.906
0.932
0.818
0.813
0.640
-nan

Overall accuracy 0.863

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
0.9902
0.0036
0.0048
0.0007
0.0007
0.0000
building
0.0317
0.9446
0.0147
0.0061
0.0029
0.0000
low_veg
0.0527
0.0053
0.8370
0.1047
0.0003
0.0000
tree
0.0197
0.0015
0.1281
0.8507
0.0000
0.0000
car
0.1815
0.0278
0.0001
0.0034
0.7872
0.0000
clutter
0.6559
0.2627
0.0089
0.0000
0.0725
0.0000
Precision/Correctness
0.876
0.948
0.865
0.829
0.619
-nan
Recall/Completeness
0.990
0.945
0.837
0.851
0.787
0.000
F1
0.929
0.946
0.851
0.840
0.693
-nan

Overall accuracy 0.887

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
0.8726
0.0377
0.0666
0.0217
0.0014
0.0000
building
0.0536
0.9234
0.0171
0.0050
0.0010
0.0000
low_veg
0.0546
0.0154
0.7024
0.2275
0.0001
0.0000
tree
0.0355
0.0064
0.1101
0.8479
0.0001
0.0000
car
0.3086
0.0159
0.0030
0.0129
0.6596
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.851
0.943
0.787
0.758
0.883
--
Recall/Completeness
0.873
0.923
0.702
0.848
0.660
--
F1
0.861
0.933
0.742
0.801
0.755
--

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_area35_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9163
0.0327
0.0452
0.0056
0.0003
0.0000
building
0.0418
0.9492
0.0074
0.0007
0.0009
0.0000
low_veg
0.0394
0.0061
0.7339
0.2205
0.0001
0.0000
tree
0.0134
0.0016
0.0852
0.8997
0.0000
0.0000
car
0.1919
0.0169
0.0002
0.0062
0.7849
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.898
0.964
0.846
0.787
0.929
--
Recall/Completeness
0.916
0.949
0.734
0.900
0.785
--
F1
0.907
0.957
0.786
0.840
0.851
--

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_area38_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9152
0.0239
0.0449
0.0130
0.0030
0.0000
building
0.0267
0.9357
0.0303
0.0065
0.0008
0.0000
low_veg
0.0402
0.0146
0.8633
0.0814
0.0004
0.0000
tree
0.0241
0.0065
0.1086
0.8606
0.0001
0.0000
car
0.2281
0.0375
0.0468
0.0095
0.6782
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.908
0.951
0.854
0.857
0.850
--
Recall/Completeness
0.915
0.936
0.863
0.861
0.678
--
F1
0.911
0.943
0.859
0.859
0.754
--

Overall accuracy 0.893

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
0.9435
0.0198
0.0311
0.0045
0.0012
0.0000
building
0.0189
0.9596
0.0171
0.0035
0.0007
0.0000
low_veg
0.0232
0.0070
0.9035
0.0659
0.0004
0.0000
tree
0.0076
0.0030
0.0836
0.9057
0.0001
0.0000
car
0.1309
0.0432
0.0329
0.0043
0.7888
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.948
0.969
0.896
0.894
0.903
--
Recall/Completeness
0.944
0.960
0.903
0.906
0.789
--
F1
0.946
0.964
0.900
0.900
0.842
--

Overall accuracy 0.928

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image