Detailled semantic labeling (2D) result


Name J. Sherrah (DFCN)
Affiliation DST Group, Australia
Abbreviation DST_2
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
0.894
0.038
0.045
0.019
0.004
0.000
building
0.057
0.917
0.017
0.009
0.000
0.000
low_veg
0.057
0.026
0.777
0.141
0.000
0.000
tree
0.018
0.007
0.088
0.887
0.000
0.000
car
0.359
0.062
0.034
0.014
0.530
0.000
clutter
0.576
0.338
0.042
0.010
0.034
0.000
Precision/Correctness
0.859
0.918
0.817
0.839
0.825
-nan
Recall/Completeness
0.894
0.917
0.777
0.887
0.530
0.000
F1
0.876
0.917
0.796
0.863
0.646
-nan

Overall accuracy 0.861

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
0.925
0.029
0.035
0.010
0.002
0.000
building
0.050
0.933
0.011
0.006
0.000
0.000
low_veg
0.047
0.015
0.814
0.124
0.000
0.000
tree
0.010
0.003
0.072
0.915
0.000
0.000
car
0.273
0.067
0.028
0.009
0.624
0.000
clutter
0.559
0.364
0.038
0.003
0.035
0.000
Precision/Correctness
0.886
0.941
0.855
0.870
0.867
-nan
Recall/Completeness
0.925
0.933
0.814
0.915
0.624
0.000
F1
0.905
0.937
0.834
0.892
0.726
-nan

Overall accuracy 0.891
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9279
0.0114
0.0431
0.0138
0.0038
0.0000
building
0.0322
0.9415
0.0217
0.0046
0.0000
0.0000
low_veg
0.0860
0.0206
0.7728
0.1200
0.0005
0.0000
tree
0.0253
0.0092
0.1067
0.8588
0.0001
0.0000
car
0.4027
0.0221
0.0166
0.0055
0.5532
0.0000
clutter
0.9542
0.0162
0.0043
0.0253
0.0000
0.0000
Precision/Correctness
0.798
0.952
0.817
0.860
0.887
-nan
Recall/Completeness
0.928
0.941
0.773
0.859
0.553
0.000
F1
0.858
0.947
0.794
0.860
0.681
-nan

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_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9606
0.0067
0.0258
0.0047
0.0022
0.0000
building
0.0247
0.9603
0.0124
0.0026
0.0000
0.0000
low_veg
0.0751
0.0105
0.8006
0.1133
0.0006
0.0000
tree
0.0137
0.0059
0.0906
0.8898
0.0000
0.0000
car
0.2924
0.0225
0.0131
0.0022
0.6698
0.0000
clutter
0.9767
0.0144
0.0025
0.0064
0.0000
0.0000
Precision/Correctness
0.826
0.973
0.857
0.884
0.922
-nan
Recall/Completeness
0.961
0.960
0.801
0.890
0.670
0.000
F1
0.888
0.967
0.828
0.887
0.776
-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
0.8867
0.0913
0.0112
0.0066
0.0042
0.0000
building
0.0455
0.9455
0.0070
0.0019
0.0001
0.0000
low_veg
0.1673
0.0753
0.5162
0.2411
0.0000
0.0000
tree
0.0546
0.0148
0.0701
0.8604
0.0001
0.0000
car
0.4681
0.0616
0.0119
0.0037
0.4548
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.859
0.944
0.682
0.750
0.837
--
Recall/Completeness
0.887
0.945
0.516
0.860
0.455
--
F1
0.873
0.945
0.587
0.801
0.589
--

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_area4_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9236
0.0630
0.0078
0.0035
0.0022
0.0000
building
0.0343
0.9589
0.0060
0.0008
0.0001
0.0000
low_veg
0.1344
0.0378
0.5664
0.2614
0.0000
0.0000
tree
0.0309
0.0060
0.0631
0.9001
0.0000
0.0000
car
0.4030
0.0508
0.0080
0.0019
0.5363
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.893
0.965
0.721
0.779
0.900
--
Recall/Completeness
0.924
0.959
0.566
0.900
0.536
--
F1
0.908
0.962
0.635
0.835
0.672
--

Overall accuracy 0.925

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
0.8803
0.0700
0.0359
0.0089
0.0049
0.0000
building
0.0338
0.9418
0.0173
0.0070
0.0001
0.0000
low_veg
0.0635
0.0384
0.7264
0.1714
0.0003
0.0000
tree
0.0115
0.0036
0.0589
0.9261
0.0000
0.0000
car
0.3484
0.0626
0.0188
0.0063
0.5639
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.893
0.928
0.707
0.921
0.875
--
Recall/Completeness
0.880
0.942
0.726
0.926
0.564
--
F1
0.886
0.935
0.716
0.923
0.686
--

Overall accuracy 0.892

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
0.9217
0.0501
0.0242
0.0021
0.0020
0.0000
building
0.0264
0.9579
0.0119
0.0038
0.0000
0.0000
low_veg
0.0510
0.0257
0.7717
0.1516
0.0000
0.0000
tree
0.0038
0.0015
0.0452
0.9495
0.0000
0.0000
car
0.2674
0.0538
0.0147
0.0017
0.6624
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.926
0.953
0.760
0.944
0.943
--
Recall/Completeness
0.922
0.958
0.772
0.949
0.662
--
F1
0.924
0.956
0.766
0.947
0.778
--

Overall accuracy 0.925

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
0.8823
0.0349
0.0674
0.0117
0.0037
0.0000
building
0.0267
0.9543
0.0152
0.0038
0.0000
0.0000
low_veg
0.0659
0.0169
0.8640
0.0531
0.0001
0.0000
tree
0.0219
0.0069
0.0933
0.8778
0.0001
0.0000
car
0.3412
0.0211
0.0571
0.0129
0.5678
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.902
0.931
0.780
0.932
0.891
--
Recall/Completeness
0.882
0.954
0.864
0.878
0.568
--
F1
0.892
0.943
0.820
0.904
0.693
--

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_area8_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9124
0.0277
0.0544
0.0036
0.0019
0.0000
building
0.0171
0.9727
0.0086
0.0015
0.0000
0.0000
low_veg
0.0527
0.0084
0.8977
0.0411
0.0000
0.0000
tree
0.0104
0.0032
0.0735
0.9129
0.0000
0.0000
car
0.2521
0.0182
0.0440
0.0096
0.6762
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.934
0.954
0.824
0.958
0.935
--
Recall/Completeness
0.912
0.973
0.898
0.913
0.676
--
F1
0.923
0.963
0.859
0.935
0.785
--

Overall accuracy 0.921

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
0.8321
0.0888
0.0532
0.0231
0.0027
0.0000
building
0.0150
0.9537
0.0161
0.0147
0.0005
0.0000
low_veg
0.0678
0.0367
0.7357
0.1598
0.0000
0.0000
tree
0.0121
0.0069
0.0759
0.9051
0.0000
0.0000
car
0.2997
0.0532
0.0217
0.0153
0.6101
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.940
0.844
0.766
0.822
0.788
--
Recall/Completeness
0.832
0.954
0.736
0.905
0.610
--
F1
0.883
0.896
0.751
0.861
0.688
--

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_area10_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8702
0.0744
0.0433
0.0106
0.0016
0.0000
building
0.0102
0.9682
0.0102
0.0110
0.0004
0.0000
low_veg
0.0663
0.0230
0.7824
0.1284
0.0000
0.0000
tree
0.0060
0.0031
0.0571
0.9337
0.0000
0.0000
car
0.2231
0.0467
0.0161
0.0108
0.7033
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.954
0.875
0.812
0.868
0.841
--
Recall/Completeness
0.870
0.968
0.782
0.934
0.703
--
F1
0.910
0.919
0.797
0.899
0.766
--

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_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8758
0.0301
0.0483
0.0438
0.0019
0.0000
building
0.1768
0.8040
0.0117
0.0075
0.0000
0.0000
low_veg
0.0477
0.0373
0.6943
0.2205
0.0001
0.0000
tree
0.0093
0.0080
0.0875
0.8953
0.0000
0.0000
car
0.3950
0.0126
0.0226
0.0133
0.5566
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.701
0.894
0.829
0.822
0.904
--
Recall/Completeness
0.876
0.804
0.694
0.895
0.557
--
F1
0.779
0.847
0.756
0.857
0.689
--

Overall accuracy 0.815

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area12_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9061
0.0259
0.0401
0.0269
0.0010
0.0000
building
0.1846
0.8077
0.0049
0.0028
0.0000
0.0000
low_veg
0.0454
0.0263
0.7319
0.1963
0.0000
0.0000
tree
0.0048
0.0037
0.0735
0.9180
0.0000
0.0000
car
0.2828
0.0096
0.0172
0.0071
0.6833
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.715
0.926
0.859
0.850
0.945
--
Recall/Completeness
0.906
0.808
0.732
0.918
0.683
--
F1
0.799
0.863
0.790
0.883
0.793
--

Overall accuracy 0.841

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area14_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8327
0.0562
0.0748
0.0332
0.0030
0.0000
building
0.0191
0.9569
0.0159
0.0081
0.0000
0.0000
low_veg
0.0747
0.0576
0.7166
0.1508
0.0002
0.0000
tree
0.0286
0.0128
0.1021
0.8565
0.0000
0.0000
car
0.1825
0.0107
0.0040
0.0239
0.7788
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.855
0.841
0.771
0.858
0.734
--
Recall/Completeness
0.833
0.957
0.717
0.856
0.779
--
F1
0.844
0.895
0.743
0.857
0.756
--

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_area14_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8537
0.0521
0.0692
0.0227
0.0023
0.0000
building
0.0130
0.9760
0.0075
0.0035
0.0000
0.0000
low_veg
0.0694
0.0418
0.7518
0.1369
0.0002
0.0000
tree
0.0206
0.0067
0.0910
0.8816
0.0000
0.0000
car
0.0786
0.0076
0.0002
0.0172
0.8964
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.882
0.873
0.795
0.882
0.749
--
Recall/Completeness
0.854
0.976
0.752
0.882
0.896
--
F1
0.868
0.921
0.773
0.882
0.816
--

Overall accuracy 0.859

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
0.8148
0.0303
0.0892
0.0641
0.0016
0.0000
building
0.0267
0.9431
0.0179
0.0123
0.0000
0.0000
low_veg
0.0266
0.0187
0.7989
0.1558
0.0000
0.0000
tree
0.0209
0.0080
0.0910
0.8800
0.0000
0.0000
car
0.2510
0.0078
0.0977
0.0251
0.6184
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.858
0.927
0.824
0.847
0.848
--
Recall/Completeness
0.815
0.943
0.799
0.880
0.618
--
F1
0.836
0.935
0.811
0.863
0.715
--

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_area16_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8510
0.0249
0.0808
0.0426
0.0006
0.0000
building
0.0218
0.9626
0.0103
0.0054
0.0000
0.0000
low_veg
0.0234
0.0104
0.8277
0.1385
0.0000
0.0000
tree
0.0140
0.0038
0.0799
0.9024
0.0000
0.0000
car
0.1787
0.0037
0.1002
0.0096
0.7078
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.888
0.954
0.849
0.872
0.922
--
Recall/Completeness
0.851
0.963
0.828
0.902
0.708
--
F1
0.869
0.958
0.838
0.887
0.801
--

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_area20_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8373
0.0314
0.0872
0.0413
0.0028
0.0000
building
0.0130
0.9423
0.0331
0.0116
0.0000
0.0000
low_veg
0.0476
0.0213
0.7737
0.1574
0.0000
0.0000
tree
0.0071
0.0015
0.0570
0.9343
0.0000
0.0000
car
0.2393
0.0080
0.0619
0.0204
0.6705
0.0000
clutter
0.0188
0.8713
0.1091
0.0009
0.0000
0.0000
Precision/Correctness
0.914
0.816
0.751
0.904
0.832
-nan
Recall/Completeness
0.837
0.942
0.774
0.934
0.670
0.000
F1
0.874
0.875
0.762
0.919
0.743
-nan

Overall accuracy 0.859

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
0.8715
0.0229
0.0794
0.0245
0.0017
0.0000
building
0.0107
0.9552
0.0279
0.0062
0.0000
0.0000
low_veg
0.0422
0.0099
0.8196
0.1282
0.0000
0.0000
tree
0.0031
0.0003
0.0434
0.9532
0.0000
0.0000
car
0.1528
0.0022
0.0481
0.0073
0.7896
0.0000
clutter
0.0125
0.8916
0.0958
0.0001
0.0000
0.0000
Precision/Correctness
0.937
0.834
0.785
0.931
0.874
-nan
Recall/Completeness
0.872
0.955
0.820
0.953
0.790
0.000
F1
0.903
0.890
0.802
0.942
0.830
-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_area22_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8845
0.0271
0.0509
0.0334
0.0041
0.0000
building
0.0265
0.9503
0.0146
0.0085
0.0001
0.0000
low_veg
0.0895
0.0394
0.7088
0.1623
0.0001
0.0000
tree
0.0196
0.0045
0.0618
0.9139
0.0000
0.0000
car
0.4119
0.0074
0.0516
0.0133
0.5158
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.895
0.904
0.793
0.854
0.809
--
Recall/Completeness
0.884
0.950
0.709
0.914
0.516
--
F1
0.890
0.927
0.749
0.883
0.630
--

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_area22_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9185
0.0199
0.0416
0.0174
0.0026
0.0000
building
0.0190
0.9686
0.0081
0.0042
0.0000
0.0000
low_veg
0.0879
0.0241
0.7543
0.1337
0.0001
0.0000
tree
0.0094
0.0020
0.0460
0.9426
0.0000
0.0000
car
0.3351
0.0104
0.0403
0.0046
0.6096
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.920
0.937
0.838
0.893
0.852
--
Recall/Completeness
0.918
0.969
0.754
0.943
0.610
--
F1
0.919
0.953
0.794
0.917
0.711
--

Overall accuracy 0.900

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
0.8004
0.0456
0.1058
0.0425
0.0057
0.0000
building
0.0645
0.8918
0.0260
0.0177
0.0000
0.0000
low_veg
0.0247
0.0203
0.8646
0.0905
0.0000
0.0000
tree
0.0143
0.0091
0.1277
0.8489
0.0000
0.0000
car
0.2955
0.0005
0.0321
0.0011
0.6708
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.812
0.907
0.871
0.822
0.754
--
Recall/Completeness
0.800
0.892
0.865
0.849
0.671
--
F1
0.806
0.899
0.868
0.835
0.710
--

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_area24_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8355
0.0363
0.0938
0.0308
0.0037
0.0000
building
0.0615
0.9046
0.0192
0.0148
0.0000
0.0000
low_veg
0.0218
0.0150
0.8873
0.0759
0.0000
0.0000
tree
0.0087
0.0049
0.1123
0.8741
0.0000
0.0000
car
0.2083
0.0000
0.0182
0.0000
0.7735
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.835
0.932
0.891
0.849
0.799
--
Recall/Completeness
0.835
0.905
0.887
0.874
0.774
--
F1
0.835
0.918
0.889
0.861
0.786
--

Overall accuracy 0.880

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
0.9293
0.0293
0.0240
0.0085
0.0090
0.0000
building
0.0571
0.9238
0.0114
0.0075
0.0003
0.0000
low_veg
0.1007
0.0274
0.7043
0.1675
0.0001
0.0000
tree
0.0121
0.0073
0.0446
0.9359
0.0001
0.0000
car
0.3911
0.0158
0.0210
0.0109
0.5612
0.0000
clutter
0.7076
0.0854
0.1083
0.0153
0.0834
0.0000
Precision/Correctness
0.843
0.952
0.890
0.709
0.851
-nan
Recall/Completeness
0.929
0.924
0.704
0.936
0.561
0.000
F1
0.884
0.938
0.786
0.807
0.676
-nan

Overall accuracy 0.870

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area27_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9593
0.0184
0.0151
0.0037
0.0036
0.0000
building
0.0454
0.9431
0.0062
0.0051
0.0002
0.0000
low_veg
0.0860
0.0134
0.7479
0.1526
0.0000
0.0000
tree
0.0057
0.0031
0.0305
0.9605
0.0000
0.0000
car
0.3064
0.0108
0.0169
0.0083
0.6576
0.0000
clutter
0.7311
0.0834
0.0834
0.0102
0.0919
0.0000
Precision/Correctness
0.878
0.974
0.930
0.745
0.921
-nan
Recall/Completeness
0.959
0.943
0.748
0.961
0.658
0.000
F1
0.917
0.958
0.829
0.839
0.767
-nan

Overall accuracy 0.904

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
0.9365
0.0195
0.0252
0.0155
0.0032
0.0000
building
0.0311
0.9525
0.0076
0.0087
0.0000
0.0000
low_veg
0.0546
0.0311
0.6059
0.3084
0.0000
0.0000
tree
0.0061
0.0036
0.0185
0.9717
0.0000
0.0000
car
0.3626
0.0188
0.0134
0.0226
0.5826
0.0000
clutter
0.5560
0.3641
0.0356
0.0098
0.0344
0.0000
Precision/Correctness
0.911
0.914
0.849
0.658
0.766
-nan
Recall/Completeness
0.937
0.953
0.606
0.972
0.583
0.000
F1
0.924
0.933
0.707
0.785
0.662
-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_area29_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9607
0.0119
0.0180
0.0077
0.0018
0.0000
building
0.0265
0.9646
0.0038
0.0051
0.0000
0.0000
low_veg
0.0375
0.0149
0.6519
0.2957
0.0000
0.0000
tree
0.0025
0.0017
0.0133
0.9825
0.0000
0.0000
car
0.2815
0.0112
0.0102
0.0178
0.6792
0.0000
clutter
0.5434
0.3884
0.0299
0.0033
0.0350
0.0000
Precision/Correctness
0.932
0.938
0.889
0.697
0.801
-nan
Recall/Completeness
0.961
0.965
0.652
0.983
0.679
0.000
F1
0.946
0.951
0.752
0.815
0.735
-nan

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_area31_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9616
0.0131
0.0121
0.0082
0.0050
0.0000
building
0.1802
0.8061
0.0091
0.0028
0.0018
0.0000
low_veg
0.0408
0.0047
0.9201
0.0344
0.0000
0.0000
tree
0.0204
0.0036
0.0695
0.9065
0.0000
0.0000
car
0.2767
0.2384
0.0357
0.0223
0.4269
0.0000
clutter
0.4725
0.4057
0.0710
0.0170
0.0336
0.0000
Precision/Correctness
0.816
0.887
0.879
0.908
0.812
-nan
Recall/Completeness
0.962
0.806
0.920
0.906
0.427
0.000
F1
0.883
0.845
0.899
0.907
0.559
-nan

Overall accuracy 0.854

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
0.9791
0.0082
0.0082
0.0022
0.0024
0.0000
building
0.1737
0.8195
0.0048
0.0005
0.0015
0.0000
low_veg
0.0228
0.0021
0.9501
0.0250
0.0000
0.0000
tree
0.0073
0.0006
0.0529
0.9392
0.0000
0.0000
car
0.1975
0.2732
0.0265
0.0142
0.4886
0.0000
clutter
0.4177
0.4672
0.0717
0.0066
0.0368
0.0000
Precision/Correctness
0.840
0.903
0.914
0.950
0.851
-nan
Recall/Completeness
0.979
0.819
0.950
0.939
0.489
0.000
F1
0.904
0.859
0.932
0.945
0.621
-nan

Overall accuracy 0.880

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
0.9764
0.0098
0.0091
0.0029
0.0018
0.0000
building
0.1963
0.7282
0.0203
0.0534
0.0018
0.0000
low_veg
0.0694
0.0119
0.8705
0.0477
0.0005
0.0000
tree
0.0351
0.0098
0.1599
0.7951
0.0000
0.0000
car
0.4284
0.0272
0.0289
0.0045
0.5109
0.0000
clutter
0.7431
0.1829
0.0058
0.0007
0.0676
0.0000
Precision/Correctness
0.763
0.926
0.833
0.776
0.570
-nan
Recall/Completeness
0.976
0.728
0.871
0.795
0.511
0.000
F1
0.856
0.815
0.851
0.786
0.539
-nan

Overall accuracy 0.811

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
0.9884
0.0059
0.0041
0.0006
0.0010
0.0000
building
0.1939
0.7349
0.0158
0.0537
0.0016
0.0000
low_veg
0.0403
0.0067
0.9063
0.0463
0.0004
0.0000
tree
0.0139
0.0058
0.1457
0.8346
0.0000
0.0000
car
0.3399
0.0259
0.0235
0.0026
0.6080
0.0000
clutter
0.7258
0.1948
0.0035
0.0002
0.0756
0.0000
Precision/Correctness
0.783
0.941
0.863
0.785
0.562
-nan
Recall/Completeness
0.988
0.735
0.906
0.835
0.608
0.000
F1
0.874
0.825
0.884
0.809
0.584
-nan

Overall accuracy 0.831

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
0.8591
0.0360
0.0836
0.0204
0.0010
0.0000
building
0.0365
0.9339
0.0247
0.0048
0.0002
0.0000
low_veg
0.0465
0.0127
0.7291
0.2116
0.0000
0.0000
tree
0.0209
0.0045
0.1187
0.8558
0.0000
0.0000
car
0.3910
0.0318
0.0141
0.0165
0.5465
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.881
0.949
0.765
0.773
0.930
--
Recall/Completeness
0.859
0.934
0.729
0.856
0.547
--
F1
0.870
0.941
0.747
0.812
0.688
--

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_area35_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9112
0.0306
0.0527
0.0052
0.0003
0.0000
building
0.0241
0.9626
0.0121
0.0011
0.0002
0.0000
low_veg
0.0370
0.0059
0.7545
0.2027
0.0000
0.0000
tree
0.0075
0.0011
0.0891
0.9023
0.0000
0.0000
car
0.2869
0.0347
0.0103
0.0069
0.6612
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.921
0.966
0.834
0.801
0.967
--
Recall/Completeness
0.911
0.963
0.754
0.902
0.661
--
F1
0.916
0.965
0.792
0.849
0.785
--

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_area38_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8916
0.0339
0.0531
0.0189
0.0025
0.0000
building
0.0179
0.9442
0.0312
0.0064
0.0002
0.0000
low_veg
0.0355
0.0168
0.8550
0.0926
0.0000
0.0000
tree
0.0229
0.0051
0.1056
0.8663
0.0000
0.0000
car
0.3441
0.0447
0.1097
0.0241
0.4773
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.915
0.940
0.845
0.837
0.865
--
Recall/Completeness
0.892
0.944
0.855
0.866
0.477
--
F1
0.903
0.942
0.850
0.852
0.615
--

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_area38_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9248
0.0302
0.0363
0.0071
0.0016
0.0000
building
0.0107
0.9675
0.0186
0.0030
0.0003
0.0000
low_veg
0.0236
0.0080
0.8938
0.0746
0.0000
0.0000
tree
0.0143
0.0024
0.0825
0.9008
0.0000
0.0000
car
0.2559
0.0487
0.0984
0.0170
0.5800
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.947
0.958
0.888
0.879
0.894
--
Recall/Completeness
0.925
0.968
0.894
0.901
0.580
--
F1
0.936
0.963
0.891
0.890
0.704
--

Overall accuracy 0.920

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image