Detailled semantic labeling (2D) result


Name S. Piramanayagam et al.
Affiliation RIT, USA
Abbreviation RIT
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
0.818
0.051
0.059
0.017
0.055
0.000
building
0.040
0.915
0.013
0.015
0.016
0.000
low_veg
0.059
0.032
0.764
0.135
0.009
0.000
tree
0.010
0.010
0.130
0.849
0.001
0.000
car
0.128
0.028
0.013
0.006
0.826
0.000
clutter
0.371
0.174
0.020
0.007
0.428
0.000
Precision/Correctness
0.882
0.904
0.770
0.834
0.295
-nan
Recall/Completeness
0.818
0.915
0.764
0.849
0.826
0.000
F1
0.849
0.909
0.767
0.842
0.435
-nan

Overall accuracy 0.832

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
0.863
0.039
0.044
0.008
0.046
0.000
building
0.037
0.929
0.009
0.011
0.015
0.000
low_veg
0.053
0.020
0.799
0.119
0.008
0.000
tree
0.005
0.006
0.111
0.878
0.000
0.000
car
0.096
0.029
0.008
0.003
0.865
0.000
clutter
0.382
0.174
0.015
0.002
0.427
0.000
Precision/Correctness
0.900
0.932
0.810
0.866
0.277
-nan
Recall/Completeness
0.863
0.929
0.799
0.878
0.865
0.000
F1
0.881
0.930
0.805
0.872
0.419
-nan

Overall accuracy 0.863
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8638
0.0235
0.0591
0.0131
0.0405
0.0000
building
0.0204
0.9488
0.0159
0.0070
0.0080
0.0000
low_veg
0.0644
0.0341
0.7608
0.1348
0.0059
0.0000
tree
0.0114
0.0172
0.1208
0.8502
0.0004
0.0000
car
0.1766
0.0025
0.0128
0.0029
0.8051
0.0000
clutter
0.8693
0.0845
0.0048
0.0270
0.0143
0.0000
Precision/Correctness
0.837
0.916
0.793
0.845
0.476
-nan
Recall/Completeness
0.864
0.949
0.761
0.850
0.805
0.000
F1
0.850
0.932
0.777
0.848
0.599
-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_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9125
0.0157
0.0348
0.0043
0.0328
0.0000
building
0.0160
0.9625
0.0111
0.0037
0.0066
0.0000
low_veg
0.0573
0.0204
0.7906
0.1272
0.0046
0.0000
tree
0.0050
0.0123
0.1017
0.8808
0.0001
0.0000
car
0.1181
0.0005
0.0096
0.0007
0.8710
0.0000
clutter
0.8947
0.0805
0.0023
0.0077
0.0149
0.0000
Precision/Correctness
0.856
0.944
0.838
0.871
0.485
-nan
Recall/Completeness
0.912
0.963
0.791
0.881
0.871
0.000
F1
0.883
0.953
0.813
0.876
0.623
-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_area4_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.7791
0.1576
0.0135
0.0074
0.0424
0.0000
building
0.0338
0.9534
0.0057
0.0046
0.0025
0.0000
low_veg
0.1456
0.1115
0.4660
0.2717
0.0052
0.0000
tree
0.0276
0.0238
0.1235
0.8229
0.0022
0.0000
car
0.2330
0.0580
0.0089
0.0005
0.6997
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.883
0.910
0.612
0.700
0.418
--
Recall/Completeness
0.779
0.953
0.466
0.823
0.700
--
F1
0.828
0.931
0.529
0.757
0.523
--

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_area4_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8259
0.1231
0.0094
0.0040
0.0375
0.0000
building
0.0269
0.9628
0.0048
0.0032
0.0022
0.0000
low_veg
0.1266
0.0756
0.5075
0.2868
0.0035
0.0000
tree
0.0139
0.0120
0.1156
0.8579
0.0005
0.0000
car
0.2090
0.0498
0.0056
0.0002
0.7354
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.908
0.935
0.648
0.735
0.400
--
Recall/Completeness
0.826
0.963
0.507
0.858
0.735
--
F1
0.865
0.949
0.569
0.792
0.519
--

Overall accuracy 0.896

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
0.7650
0.0945
0.0500
0.0143
0.0761
0.0000
building
0.0212
0.9446
0.0166
0.0114
0.0062
0.0000
low_veg
0.0357
0.0626
0.6898
0.2091
0.0028
0.0000
tree
0.0037
0.0057
0.0748
0.9154
0.0004
0.0000
car
0.1235
0.0242
0.0053
0.0024
0.8447
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.933
0.905
0.649
0.899
0.387
--
Recall/Completeness
0.765
0.945
0.690
0.915
0.845
--
F1
0.841
0.924
0.669
0.907
0.531
--

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_area6_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8238
0.0693
0.0345
0.0048
0.0676
0.0000
building
0.0176
0.9570
0.0133
0.0068
0.0052
0.0000
low_veg
0.0302
0.0462
0.7308
0.1910
0.0019
0.0000
tree
0.0009
0.0024
0.0606
0.9361
0.0000
0.0000
car
0.1018
0.0156
0.0022
0.0000
0.8804
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.951
0.935
0.695
0.926
0.365
--
Recall/Completeness
0.824
0.957
0.731
0.936
0.880
--
F1
0.883
0.946
0.712
0.931
0.516
--

Overall accuracy 0.895

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
0.8153
0.0669
0.0563
0.0142
0.0473
0.0000
building
0.0207
0.9549
0.0103
0.0086
0.0054
0.0000
low_veg
0.0657
0.0251
0.8368
0.0652
0.0073
0.0000
tree
0.0082
0.0120
0.1113
0.8677
0.0008
0.0000
car
0.1362
0.0252
0.0157
0.0050
0.8179
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.921
0.883
0.778
0.915
0.439
--
Recall/Completeness
0.815
0.955
0.837
0.868
0.818
--
F1
0.865
0.918
0.806
0.891
0.571
--

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_area8_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8598
0.0569
0.0404
0.0042
0.0387
0.0000
building
0.0151
0.9699
0.0058
0.0054
0.0039
0.0000
low_veg
0.0554
0.0136
0.8713
0.0541
0.0056
0.0000
tree
0.0028
0.0069
0.0883
0.9017
0.0003
0.0000
car
0.1058
0.0249
0.0073
0.0039
0.8582
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.943
0.912
0.827
0.943
0.435
--
Recall/Completeness
0.860
0.970
0.871
0.902
0.858
--
F1
0.899
0.940
0.849
0.922
0.578
--

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_area10_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.7945
0.0866
0.0641
0.0249
0.0300
0.0000
building
0.0079
0.9550
0.0103
0.0196
0.0072
0.0000
low_veg
0.0627
0.0418
0.7294
0.1455
0.0205
0.0000
tree
0.0046
0.0078
0.1073
0.8796
0.0006
0.0000
car
0.1101
0.0242
0.0276
0.0017
0.8364
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.953
0.844
0.725
0.821
0.261
--
Recall/Completeness
0.795
0.955
0.729
0.880
0.836
--
F1
0.867
0.896
0.727
0.849
0.398
--

Overall accuracy 0.839

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
0.8425
0.0679
0.0515
0.0121
0.0260
0.0000
building
0.0046
0.9691
0.0057
0.0144
0.0062
0.0000
low_veg
0.0629
0.0274
0.7762
0.1136
0.0199
0.0000
tree
0.0028
0.0037
0.0840
0.9093
0.0002
0.0000
car
0.0802
0.0197
0.0218
0.0000
0.8783
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.962
0.881
0.775
0.869
0.237
--
Recall/Completeness
0.843
0.969
0.776
0.909
0.878
--
F1
0.898
0.923
0.776
0.889
0.373
--

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_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8054
0.0354
0.0843
0.0277
0.0472
0.0000
building
0.1476
0.7996
0.0079
0.0107
0.0342
0.0000
low_veg
0.0665
0.0371
0.6933
0.1894
0.0137
0.0000
tree
0.0074
0.0088
0.1624
0.8204
0.0009
0.0000
car
0.0608
0.0000
0.0062
0.0025
0.9305
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.694
0.889
0.732
0.833
0.210
--
Recall/Completeness
0.805
0.800
0.693
0.820
0.931
--
F1
0.745
0.842
0.712
0.827
0.343
--

Overall accuracy 0.778

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
0.8470
0.0297
0.0675
0.0155
0.0403
0.0000
building
0.1551
0.8020
0.0039
0.0043
0.0347
0.0000
low_veg
0.0673
0.0244
0.7250
0.1696
0.0137
0.0000
tree
0.0042
0.0042
0.1457
0.8453
0.0006
0.0000
car
0.0232
0.0000
0.0020
0.0000
0.9747
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.704
0.925
0.761
0.860
0.179
--
Recall/Completeness
0.847
0.802
0.725
0.845
0.975
--
F1
0.769
0.859
0.743
0.853
0.302
--

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_area14_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8122
0.0370
0.0890
0.0341
0.0277
0.0000
building
0.0156
0.9475
0.0187
0.0113
0.0069
0.0000
low_veg
0.0637
0.0578
0.7203
0.1427
0.0155
0.0000
tree
0.0171
0.0167
0.1663
0.7994
0.0006
0.0000
car
0.0660
0.0000
0.0014
0.0097
0.9230
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.882
0.853
0.698
0.853
0.174
--
Recall/Completeness
0.812
0.948
0.720
0.799
0.923
--
F1
0.846
0.898
0.709
0.825
0.293
--

Overall accuracy 0.809

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area14_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8429
0.0311
0.0778
0.0235
0.0248
0.0000
building
0.0112
0.9659
0.0115
0.0062
0.0052
0.0000
low_veg
0.0603
0.0416
0.7532
0.1305
0.0144
0.0000
tree
0.0122
0.0098
0.1544
0.8232
0.0004
0.0000
car
0.0299
0.0000
0.0003
0.0055
0.9643
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.903
0.889
0.721
0.877
0.155
--
Recall/Completeness
0.843
0.966
0.753
0.823
0.964
--
F1
0.872
0.926
0.737
0.849
0.267
--

Overall accuracy 0.836

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
0.7641
0.0312
0.1188
0.0474
0.0385
0.0000
building
0.0315
0.9209
0.0200
0.0231
0.0045
0.0000
low_veg
0.0403
0.0211
0.7909
0.1388
0.0090
0.0000
tree
0.0185
0.0092
0.1723
0.7983
0.0017
0.0000
car
0.0613
0.0029
0.0313
0.0036
0.9009
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.828
0.919
0.734
0.848
0.167
--
Recall/Completeness
0.764
0.921
0.791
0.798
0.901
--
F1
0.795
0.920
0.761
0.822
0.282
--

Overall accuracy 0.813

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
0.8083
0.0241
0.1017
0.0303
0.0356
0.0000
building
0.0286
0.9397
0.0137
0.0143
0.0037
0.0000
low_veg
0.0383
0.0131
0.8155
0.1248
0.0084
0.0000
tree
0.0138
0.0046
0.1577
0.8225
0.0014
0.0000
car
0.0242
0.0000
0.0146
0.0000
0.9611
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.850
0.948
0.762
0.872
0.144
--
Recall/Completeness
0.808
0.940
0.815
0.822
0.961
--
F1
0.828
0.944
0.788
0.847
0.251
--

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_area20_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.7184
0.0376
0.1688
0.0417
0.0335
0.0000
building
0.0114
0.9403
0.0195
0.0258
0.0030
0.0000
low_veg
0.0463
0.0201
0.7657
0.1548
0.0131
0.0000
tree
0.0023
0.0021
0.0937
0.9017
0.0002
0.0000
car
0.1032
0.0168
0.0370
0.0179
0.8252
0.0000
clutter
0.8805
0.0142
0.0674
0.0001
0.0377
0.0000
Precision/Correctness
0.801
0.923
0.656
0.897
0.238
-nan
Recall/Completeness
0.718
0.940
0.766
0.902
0.825
0.000
F1
0.757
0.932
0.707
0.899
0.370
-nan

Overall accuracy 0.820

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
0.7576
0.0282
0.1600
0.0241
0.0301
0.0000
building
0.0096
0.9546
0.0149
0.0184
0.0026
0.0000
low_veg
0.0428
0.0093
0.8078
0.1272
0.0129
0.0000
tree
0.0006
0.0005
0.0783
0.9204
0.0002
0.0000
car
0.0564
0.0168
0.0249
0.0090
0.8929
0.0000
clutter
0.8918
0.0134
0.0576
0.0000
0.0372
0.0000
Precision/Correctness
0.812
0.952
0.684
0.924
0.209
-nan
Recall/Completeness
0.758
0.955
0.808
0.920
0.893
0.000
F1
0.784
0.953
0.741
0.922
0.339
-nan

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_area22_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.7870
0.0411
0.0801
0.0370
0.0549
0.0000
building
0.0156
0.9509
0.0163
0.0119
0.0054
0.0000
low_veg
0.0754
0.0472
0.6933
0.1676
0.0164
0.0000
tree
0.0077
0.0057
0.0873
0.8985
0.0008
0.0000
car
0.1823
0.0274
0.0314
0.0090
0.7499
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.919
0.873
0.722
0.844
0.272
--
Recall/Completeness
0.787
0.951
0.693
0.899
0.750
--
F1
0.848
0.910
0.707
0.870
0.399
--

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_area22_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8331
0.0309
0.0658
0.0199
0.0504
0.0000
building
0.0130
0.9668
0.0110
0.0058
0.0034
0.0000
low_veg
0.0772
0.0309
0.7348
0.1405
0.0166
0.0000
tree
0.0027
0.0026
0.0671
0.9273
0.0003
0.0000
car
0.1518
0.0368
0.0200
0.0031
0.7883
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.933
0.911
0.770
0.884
0.240
--
Recall/Completeness
0.833
0.967
0.735
0.927
0.788
--
F1
0.880
0.938
0.752
0.905
0.368
--

Overall accuracy 0.865

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
0.7076
0.0562
0.1327
0.0308
0.0727
0.0000
building
0.0501
0.8914
0.0242
0.0276
0.0068
0.0000
low_veg
0.0278
0.0212
0.8612
0.0843
0.0055
0.0000
tree
0.0091
0.0117
0.1900
0.7883
0.0009
0.0000
car
0.0612
0.0026
0.0044
0.0046
0.9272
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.815
0.894
0.831
0.819
0.197
--
Recall/Completeness
0.708
0.891
0.861
0.788
0.927
--
F1
0.758
0.893
0.846
0.803
0.325
--

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_area24_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.7483
0.0441
0.1190
0.0209
0.0677
0.0000
building
0.0490
0.9020
0.0187
0.0247
0.0057
0.0000
low_veg
0.0255
0.0154
0.8827
0.0714
0.0049
0.0000
tree
0.0057
0.0073
0.1733
0.8131
0.0006
0.0000
car
0.0486
0.0016
0.0022
0.0007
0.9468
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.832
0.922
0.852
0.844
0.165
--
Recall/Completeness
0.748
0.902
0.883
0.813
0.947
--
F1
0.788
0.912
0.867
0.828
0.281
--

Overall accuracy 0.850

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
0.8541
0.0422
0.0269
0.0071
0.0696
0.0000
building
0.0435
0.9302
0.0068
0.0124
0.0071
0.0000
low_veg
0.1008
0.0477
0.6773
0.1670
0.0072
0.0000
tree
0.0071
0.0132
0.0557
0.9240
0.0001
0.0000
car
0.1516
0.0068
0.0100
0.0061
0.8255
0.0000
clutter
0.3013
0.0934
0.0498
0.0108
0.5447
0.0000
Precision/Correctness
0.868
0.930
0.886
0.701
0.494
-nan
Recall/Completeness
0.854
0.930
0.677
0.924
0.826
0.000
F1
0.861
0.930
0.768
0.797
0.618
-nan

Overall accuracy 0.850

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
0.9022
0.0283
0.0169
0.0028
0.0498
0.0000
building
0.0360
0.9456
0.0035
0.0096
0.0053
0.0000
low_veg
0.0932
0.0309
0.7176
0.1531
0.0052
0.0000
tree
0.0029
0.0074
0.0392
0.9506
0.0000
0.0000
car
0.1222
0.0044
0.0070
0.0043
0.8621
0.0000
clutter
0.2957
0.0895
0.0326
0.0036
0.5786
0.0000
Precision/Correctness
0.892
0.956
0.927
0.735
0.515
-nan
Recall/Completeness
0.902
0.946
0.718
0.951
0.862
0.000
F1
0.897
0.951
0.809
0.829
0.645
-nan

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_area29_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8737
0.0284
0.0272
0.0117
0.0590
0.0000
building
0.0250
0.9104
0.0034
0.0075
0.0536
0.0000
low_veg
0.0599
0.0416
0.6407
0.2517
0.0059
0.0000
tree
0.0037
0.0119
0.0333
0.9510
0.0001
0.0000
car
0.0667
0.0114
0.0067
0.0080
0.9072
0.0000
clutter
0.1726
0.1828
0.0227
0.0076
0.6143
0.0000
Precision/Correctness
0.944
0.908
0.849
0.700
0.172
-nan
Recall/Completeness
0.874
0.910
0.641
0.951
0.907
0.000
F1
0.907
0.909
0.730
0.807
0.289
-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_area29_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9074
0.0190
0.0176
0.0053
0.0508
0.0000
building
0.0215
0.9181
0.0016
0.0041
0.0548
0.0000
low_veg
0.0481
0.0225
0.6846
0.2411
0.0036
0.0000
tree
0.0017
0.0079
0.0231
0.9673
0.0000
0.0000
car
0.0345
0.0061
0.0053
0.0049
0.9492
0.0000
clutter
0.1443
0.1770
0.0152
0.0016
0.6618
0.0000
Precision/Correctness
0.958
0.938
0.895
0.738
0.148
-nan
Recall/Completeness
0.907
0.918
0.685
0.967
0.949
0.000
F1
0.932
0.928
0.776
0.837
0.257
-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_area31_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8574
0.0224
0.0165
0.0040
0.0997
0.0000
building
0.0861
0.8573
0.0029
0.0039
0.0498
0.0000
low_veg
0.0591
0.0075
0.8917
0.0287
0.0131
0.0000
tree
0.0209
0.0076
0.1213
0.8483
0.0019
0.0000
car
0.0325
0.0809
0.0090
0.0073
0.8703
0.0000
clutter
0.1342
0.3630
0.0169
0.0046
0.4814
0.0000
Precision/Correctness
0.891
0.902
0.859
0.930
0.306
-nan
Recall/Completeness
0.857
0.857
0.892
0.848
0.870
0.000
F1
0.874
0.879
0.875
0.887
0.453
-nan

Overall accuracy 0.833

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
0.8955
0.0164
0.0104
0.0006
0.0770
0.0000
building
0.0822
0.8701
0.0009
0.0013
0.0456
0.0000
low_veg
0.0444
0.0040
0.9246
0.0191
0.0079
0.0000
tree
0.0116
0.0030
0.0951
0.8897
0.0005
0.0000
car
0.0184
0.0913
0.0041
0.0020
0.8842
0.0000
clutter
0.1041
0.4105
0.0104
0.0012
0.4738
0.0000
Precision/Correctness
0.908
0.919
0.901
0.965
0.302
-nan
Recall/Completeness
0.896
0.870
0.925
0.890
0.884
0.000
F1
0.902
0.894
0.913
0.926
0.450
-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_area33_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8736
0.0257
0.0139
0.0020
0.0847
0.0000
building
0.1395
0.7447
0.0051
0.0709
0.0398
0.0000
low_veg
0.0665
0.0267
0.8563
0.0309
0.0195
0.0000
tree
0.0187
0.0271
0.1807
0.7731
0.0005
0.0000
car
0.1391
0.0047
0.0103
0.0011
0.8448
0.0000
clutter
0.1365
0.1627
0.0020
0.0003
0.6985
0.0000
Precision/Correctness
0.845
0.894
0.835
0.756
0.113
-nan
Recall/Completeness
0.874
0.745
0.856
0.773
0.845
0.000
F1
0.859
0.812
0.846
0.764
0.200
-nan

Overall accuracy 0.776

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
0.9039
0.0170
0.0072
0.0003
0.0716
0.0000
building
0.1406
0.7464
0.0037
0.0716
0.0377
0.0000
low_veg
0.0399
0.0171
0.9002
0.0290
0.0137
0.0000
tree
0.0066
0.0159
0.1624
0.8147
0.0004
0.0000
car
0.1074
0.0028
0.0054
0.0004
0.8840
0.0000
clutter
0.1133
0.1576
0.0013
0.0000
0.7279
0.0000
Precision/Correctness
0.862
0.923
0.868
0.762
0.102
-nan
Recall/Completeness
0.904
0.746
0.900
0.815
0.884
0.000
F1
0.882
0.825
0.884
0.788
0.183
-nan

Overall accuracy 0.801

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
0.7833
0.0590
0.0969
0.0192
0.0416
0.0000
building
0.0356
0.9117
0.0152
0.0074
0.0302
0.0000
low_veg
0.0578
0.0187
0.7063
0.2121
0.0051
0.0000
tree
0.0092
0.0071
0.1694
0.8138
0.0004
0.0000
car
0.2182
0.0344
0.0077
0.0138
0.7260
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.877
0.919
0.720
0.762
0.216
--
Recall/Completeness
0.783
0.912
0.706
0.814
0.726
--
F1
0.827
0.915
0.713
0.787
0.333
--

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_area35_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8546
0.0504
0.0538
0.0052
0.0360
0.0000
building
0.0292
0.9365
0.0075
0.0019
0.0249
0.0000
low_veg
0.0507
0.0093
0.7326
0.2040
0.0033
0.0000
tree
0.0034
0.0022
0.1312
0.8632
0.0000
0.0000
car
0.1631
0.0409
0.0050
0.0058
0.7852
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.904
0.945
0.798
0.792
0.216
--
Recall/Completeness
0.855
0.937
0.733
0.863
0.785
--
F1
0.879
0.941
0.764
0.826
0.338
--

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_area38_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8403
0.0378
0.0678
0.0134
0.0407
0.0000
building
0.0160
0.9212
0.0287
0.0217
0.0125
0.0000
low_veg
0.0559
0.0208
0.8304
0.0888
0.0040
0.0000
tree
0.0085
0.0108
0.1444
0.8361
0.0003
0.0000
car
0.1457
0.0258
0.0259
0.0096
0.7930
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.908
0.927
0.812
0.827
0.333
--
Recall/Completeness
0.840
0.921
0.830
0.836
0.793
--
F1
0.873
0.924
0.821
0.832
0.469
--

Overall accuracy 0.857

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area38_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8876
0.0319
0.0410
0.0039
0.0356
0.0000
building
0.0107
0.9419
0.0220
0.0160
0.0093
0.0000
low_veg
0.0506
0.0110
0.8645
0.0710
0.0030
0.0000
tree
0.0048
0.0073
0.1139
0.8739
0.0001
0.0000
car
0.1093
0.0262
0.0141
0.0040
0.8464
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.928
0.950
0.861
0.869
0.324
--
Recall/Completeness
0.888
0.942
0.864
0.874
0.846
--
F1
0.907
0.946
0.863
0.872
0.468
--

Overall accuracy 0.893

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image