Detailled semantic labeling (2D) result


Name G. Lin et al.
Affiliation University of Adelaide, Australia
Abbreviation UOA
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
0.880
0.043
0.051
0.020
0.006
0.000
building
0.062
0.899
0.032
0.006
0.001
0.000
low_veg
0.056
0.038
0.757
0.149
0.000
0.000
tree
0.022
0.006
0.103
0.869
0.000
0.000
car
0.244
0.054
0.012
0.007
0.683
0.000
clutter
0.534
0.419
0.014
0.009
0.023
0.000
Precision/Correctness
0.856
0.901
0.781
0.834
0.807
-nan
Recall/Completeness
0.880
0.899
0.757
0.869
0.683
0.000
F1
0.868
0.900
0.769
0.851
0.740
-nan

Overall accuracy 0.846

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
0.911
0.035
0.041
0.010
0.003
0.000
building
0.053
0.919
0.024
0.003
0.001
0.000
low_veg
0.046
0.030
0.791
0.134
0.000
0.000
tree
0.011
0.002
0.085
0.901
0.000
0.000
car
0.141
0.059
0.006
0.004
0.789
0.000
clutter
0.516
0.447
0.011
0.003
0.023
0.000
Precision/Correctness
0.887
0.922
0.818
0.864
0.854
-nan
Recall/Completeness
0.911
0.919
0.791
0.901
0.789
0.000
F1
0.898
0.921
0.804
0.882
0.820
-nan

Overall accuracy 0.876
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8845
0.0236
0.0715
0.0143
0.0060
0.0000
building
0.0642
0.8930
0.0392
0.0030
0.0006
0.0000
low_veg
0.0668
0.0329
0.7544
0.1457
0.0002
0.0000
tree
0.0305
0.0078
0.1342
0.8274
0.0002
0.0000
car
0.3366
0.0083
0.0141
0.0019
0.6390
0.0000
clutter
0.9526
0.0167
0.0092
0.0213
0.0002
0.0000
Precision/Correctness
0.783
0.926
0.753
0.835
0.851
-nan
Recall/Completeness
0.884
0.893
0.754
0.827
0.639
0.000
F1
0.830
0.909
0.754
0.831
0.730
-nan

Overall accuracy 0.821

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9176
0.0182
0.0550
0.0051
0.0041
0.0000
building
0.0553
0.9158
0.0274
0.0008
0.0007
0.0000
low_veg
0.0537
0.0219
0.7855
0.1389
0.0000
0.0000
tree
0.0171
0.0042
0.1170
0.8618
0.0000
0.0000
car
0.2160
0.0071
0.0102
0.0002
0.7664
0.0000
clutter
0.9716
0.0172
0.0067
0.0043
0.0002
0.0000
Precision/Correctness
0.813
0.951
0.792
0.861
0.884
-nan
Recall/Completeness
0.918
0.916
0.785
0.862
0.766
0.000
F1
0.862
0.933
0.789
0.861
0.821
-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_area4_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9132
0.0611
0.0164
0.0049
0.0045
0.0000
building
0.0717
0.9140
0.0119
0.0021
0.0004
0.0000
low_veg
0.1630
0.0473
0.5192
0.2662
0.0044
0.0000
tree
0.0478
0.0166
0.0911
0.8435
0.0010
0.0000
car
0.2988
0.0141
0.0012
0.0020
0.6838
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.831
0.961
0.594
0.737
0.848
--
Recall/Completeness
0.913
0.914
0.519
0.844
0.684
--
F1
0.870
0.937
0.554
0.786
0.757
--

Overall accuracy 0.888

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
0.9459
0.0379
0.0126
0.0018
0.0018
0.0000
building
0.0580
0.9311
0.0098
0.0008
0.0003
0.0000
low_veg
0.1225
0.0209
0.5613
0.2915
0.0038
0.0000
tree
0.0193
0.0055
0.0844
0.8907
0.0000
0.0000
car
0.1865
0.0087
0.0001
0.0004
0.8042
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.865
0.979
0.628
0.768
0.910
--
Recall/Completeness
0.946
0.931
0.561
0.891
0.804
--
F1
0.904
0.954
0.593
0.825
0.854
--

Overall accuracy 0.917

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
0.8826
0.0549
0.0384
0.0151
0.0089
0.0000
building
0.0704
0.9050
0.0199
0.0037
0.0010
0.0000
low_veg
0.0897
0.0247
0.6867
0.1987
0.0002
0.0000
tree
0.0182
0.0054
0.0594
0.9166
0.0004
0.0000
car
0.2602
0.0227
0.0048
0.0091
0.7033
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.842
0.942
0.686
0.909
0.808
--
Recall/Completeness
0.883
0.905
0.687
0.917
0.703
--
F1
0.862
0.923
0.686
0.913
0.752
--

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
0.9225
0.0387
0.0284
0.0061
0.0042
0.0000
building
0.0571
0.9264
0.0145
0.0013
0.0007
0.0000
low_veg
0.0747
0.0122
0.7275
0.1857
0.0000
0.0000
tree
0.0090
0.0016
0.0464
0.9429
0.0002
0.0000
car
0.1577
0.0161
0.0020
0.0073
0.8169
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.880
0.965
0.732
0.933
0.883
--
Recall/Completeness
0.923
0.926
0.727
0.943
0.817
--
F1
0.901
0.945
0.730
0.938
0.849
--

Overall accuracy 0.910

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
0.8720
0.0321
0.0731
0.0176
0.0052
0.0000
building
0.0502
0.9239
0.0196
0.0061
0.0002
0.0000
low_veg
0.0496
0.0196
0.8471
0.0827
0.0011
0.0000
tree
0.0239
0.0049
0.0940
0.8768
0.0004
0.0000
car
0.2695
0.0198
0.0167
0.0047
0.6893
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.896
0.933
0.768
0.900
0.855
--
Recall/Completeness
0.872
0.924
0.847
0.877
0.689
--
F1
0.884
0.928
0.806
0.888
0.763
--

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_area8_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9039
0.0242
0.0615
0.0077
0.0026
0.0000
building
0.0395
0.9458
0.0118
0.0029
0.0001
0.0000
low_veg
0.0357
0.0110
0.8819
0.0709
0.0005
0.0000
tree
0.0097
0.0021
0.0731
0.9149
0.0002
0.0000
car
0.1742
0.0167
0.0071
0.0031
0.7988
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.931
0.956
0.812
0.928
0.911
--
Recall/Completeness
0.904
0.946
0.882
0.915
0.799
--
F1
0.917
0.951
0.845
0.922
0.851
--

Overall accuracy 0.911

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
0.7905
0.1010
0.0826
0.0222
0.0037
0.0000
building
0.0373
0.9264
0.0229
0.0132
0.0003
0.0000
low_veg
0.0619
0.0491
0.7182
0.1708
0.0000
0.0000
tree
0.0147
0.0075
0.0831
0.8946
0.0001
0.0000
car
0.2387
0.0238
0.0123
0.0083
0.7168
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.924
0.819
0.702
0.816
0.773
--
Recall/Completeness
0.790
0.926
0.718
0.895
0.717
--
F1
0.852
0.870
0.710
0.853
0.744
--

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_area10_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8208
0.0902
0.0758
0.0108
0.0024
0.0000
building
0.0301
0.9448
0.0160
0.0089
0.0002
0.0000
low_veg
0.0576
0.0382
0.7612
0.1430
0.0000
0.0000
tree
0.0064
0.0037
0.0619
0.9281
0.0000
0.0000
car
0.1375
0.0246
0.0055
0.0083
0.8242
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.943
0.844
0.739
0.859
0.817
--
Recall/Completeness
0.821
0.945
0.761
0.928
0.824
--
F1
0.878
0.892
0.750
0.892
0.821
--

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_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8677
0.0381
0.0519
0.0381
0.0042
0.0000
building
0.1282
0.8449
0.0208
0.0061
0.0000
0.0000
low_veg
0.0455
0.0336
0.7485
0.1722
0.0002
0.0000
tree
0.0097
0.0080
0.1180
0.8643
0.0000
0.0000
car
0.2119
0.0222
0.0193
0.0136
0.7330
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.744
0.899
0.798
0.850
0.846
--
Recall/Completeness
0.868
0.845
0.749
0.864
0.733
--
F1
0.801
0.871
0.772
0.857
0.785
--

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_area12_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9006
0.0346
0.0411
0.0222
0.0015
0.0000
building
0.1326
0.8555
0.0104
0.0015
0.0000
0.0000
low_veg
0.0442
0.0225
0.7825
0.1506
0.0001
0.0000
tree
0.0048
0.0026
0.0994
0.8932
0.0000
0.0000
car
0.1032
0.0294
0.0190
0.0057
0.8427
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.761
0.931
0.832
0.878
0.927
--
Recall/Completeness
0.901
0.856
0.783
0.893
0.843
--
F1
0.825
0.891
0.806
0.885
0.883
--

Overall accuracy 0.855

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area14_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.7928
0.0514
0.1070
0.0418
0.0070
0.0000
building
0.0260
0.9432
0.0232
0.0075
0.0000
0.0000
low_veg
0.0831
0.0529
0.6990
0.1648
0.0002
0.0000
tree
0.0269
0.0112
0.1217
0.8399
0.0002
0.0000
car
0.1508
0.0011
0.0040
0.0051
0.8389
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.838
0.851
0.719
0.842
0.563
--
Recall/Completeness
0.793
0.943
0.699
0.840
0.839
--
F1
0.815
0.895
0.709
0.841
0.674
--

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_area14_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8124
0.0469
0.1043
0.0302
0.0062
0.0000
building
0.0202
0.9641
0.0131
0.0026
0.0000
0.0000
low_veg
0.0784
0.0390
0.7288
0.1536
0.0002
0.0000
tree
0.0188
0.0052
0.1098
0.8661
0.0002
0.0000
car
0.0490
0.0000
0.0012
0.0010
0.9488
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.865
0.882
0.740
0.865
0.549
--
Recall/Completeness
0.812
0.964
0.729
0.866
0.949
--
F1
0.838
0.921
0.734
0.866
0.695
--

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_area16_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8063
0.0448
0.0912
0.0539
0.0039
0.0000
building
0.0480
0.9102
0.0309
0.0106
0.0003
0.0000
low_veg
0.0298
0.0221
0.8236
0.1245
0.0000
0.0000
tree
0.0258
0.0070
0.1187
0.8484
0.0001
0.0000
car
0.1084
0.0071
0.0338
0.0104
0.8403
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.821
0.910
0.794
0.868
0.728
--
Recall/Completeness
0.806
0.910
0.824
0.848
0.840
--
F1
0.814
0.910
0.809
0.858
0.780
--

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_area16_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8432
0.0387
0.0816
0.0343
0.0021
0.0000
building
0.0451
0.9325
0.0187
0.0034
0.0003
0.0000
low_veg
0.0260
0.0157
0.8484
0.1099
0.0000
0.0000
tree
0.0178
0.0030
0.1049
0.8741
0.0001
0.0000
car
0.0372
0.0044
0.0189
0.0030
0.9365
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.850
0.935
0.823
0.893
0.784
--
Recall/Completeness
0.843
0.932
0.848
0.874
0.936
--
F1
0.847
0.934
0.835
0.884
0.853
--

Overall accuracy 0.872

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
0.8479
0.0493
0.0493
0.0489
0.0046
0.0000
building
0.0208
0.9397
0.0331
0.0062
0.0003
0.0000
low_veg
0.0475
0.0346
0.7109
0.2067
0.0003
0.0000
tree
0.0070
0.0028
0.0503
0.9399
0.0000
0.0000
car
0.1334
0.0251
0.0382
0.0199
0.7834
0.0000
clutter
0.0028
0.9939
0.0021
0.0012
0.0000
0.0000
Precision/Correctness
0.914
0.775
0.792
0.883
0.755
-nan
Recall/Completeness
0.848
0.940
0.711
0.940
0.783
0.000
F1
0.880
0.849
0.749
0.911
0.769
-nan

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_area20_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8855
0.0394
0.0436
0.0288
0.0027
0.0000
building
0.0164
0.9553
0.0262
0.0019
0.0003
0.0000
low_veg
0.0416
0.0248
0.7527
0.1804
0.0004
0.0000
tree
0.0030
0.0008
0.0377
0.9585
0.0000
0.0000
car
0.0428
0.0213
0.0319
0.0111
0.8929
0.0000
clutter
0.0009
0.9982
0.0009
0.0000
0.0000
0.0000
Precision/Correctness
0.938
0.795
0.827
0.910
0.799
-nan
Recall/Completeness
0.886
0.955
0.753
0.959
0.893
0.000
F1
0.911
0.868
0.788
0.934
0.844
-nan

Overall accuracy 0.878

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area22_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8749
0.0347
0.0483
0.0343
0.0078
0.0000
building
0.0524
0.9157
0.0227
0.0084
0.0009
0.0000
low_veg
0.0850
0.0386
0.7070
0.1685
0.0009
0.0000
tree
0.0224
0.0040
0.0626
0.9106
0.0005
0.0000
car
0.2460
0.0207
0.0089
0.0120
0.7123
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.887
0.890
0.791
0.849
0.724
--
Recall/Completeness
0.875
0.916
0.707
0.911
0.712
--
F1
0.881
0.902
0.747
0.879
0.718
--

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_area22_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9099
0.0270
0.0404
0.0177
0.0050
0.0000
building
0.0456
0.9357
0.0140
0.0039
0.0008
0.0000
low_veg
0.0820
0.0259
0.7501
0.1412
0.0008
0.0000
tree
0.0099
0.0011
0.0463
0.9424
0.0003
0.0000
car
0.1438
0.0221
0.0053
0.0048
0.8240
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.912
0.922
0.835
0.888
0.769
--
Recall/Completeness
0.910
0.936
0.750
0.942
0.824
--
F1
0.911
0.929
0.790
0.914
0.795
--

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_area24_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8105
0.0412
0.0971
0.0435
0.0077
0.0000
building
0.0883
0.8428
0.0586
0.0103
0.0000
0.0000
low_veg
0.0280
0.0589
0.8311
0.0818
0.0003
0.0000
tree
0.0195
0.0054
0.1587
0.8163
0.0001
0.0000
car
0.1620
0.0026
0.0054
0.0005
0.8295
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.778
0.834
0.839
0.832
0.714
--
Recall/Completeness
0.811
0.843
0.831
0.816
0.830
--
F1
0.794
0.838
0.835
0.824
0.767
--

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_area24_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8437
0.0311
0.0876
0.0321
0.0054
0.0000
building
0.0841
0.8558
0.0525
0.0076
0.0000
0.0000
low_veg
0.0239
0.0562
0.8493
0.0703
0.0003
0.0000
tree
0.0130
0.0024
0.1365
0.8481
0.0001
0.0000
car
0.0704
0.0000
0.0006
0.0000
0.9290
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.804
0.852
0.862
0.857
0.734
--
Recall/Completeness
0.844
0.856
0.849
0.848
0.929
--
F1
0.823
0.854
0.856
0.852
0.820
--

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
0.9116
0.0407
0.0294
0.0089
0.0093
0.0000
building
0.0830
0.8820
0.0295
0.0048
0.0007
0.0000
low_veg
0.0673
0.0244
0.6593
0.2480
0.0010
0.0000
tree
0.0129
0.0042
0.0430
0.9396
0.0002
0.0000
car
0.2506
0.0208
0.0084
0.0070
0.7133
0.0000
clutter
0.6467
0.1860
0.1085
0.0035
0.0554
0.0000
Precision/Correctness
0.845
0.941
0.840
0.639
0.866
-nan
Recall/Completeness
0.912
0.882
0.659
0.940
0.713
0.000
F1
0.877
0.911
0.739
0.760
0.782
-nan

Overall accuracy 0.846

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area27_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9413
0.0308
0.0207
0.0035
0.0037
0.0000
building
0.0720
0.9025
0.0232
0.0017
0.0006
0.0000
low_veg
0.0517
0.0127
0.6956
0.2395
0.0006
0.0000
tree
0.0058
0.0013
0.0275
0.9653
0.0000
0.0000
car
0.1452
0.0204
0.0050
0.0053
0.8241
0.0000
clutter
0.6579
0.1965
0.0788
0.0001
0.0666
0.0000
Precision/Correctness
0.878
0.961
0.880
0.667
0.925
-nan
Recall/Completeness
0.941
0.903
0.696
0.965
0.824
0.000
F1
0.909
0.931
0.777
0.789
0.871
-nan

Overall accuracy 0.878

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area29_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9163
0.0310
0.0303
0.0166
0.0059
0.0000
building
0.0324
0.9476
0.0131
0.0064
0.0004
0.0000
low_veg
0.0522
0.0284
0.6258
0.2934
0.0002
0.0000
tree
0.0054
0.0034
0.0410
0.9502
0.0000
0.0000
car
0.2528
0.0194
0.0055
0.0109
0.7113
0.0000
clutter
0.4101
0.5225
0.0293
0.0139
0.0242
0.0000
Precision/Correctness
0.922
0.885
0.809
0.664
0.740
-nan
Recall/Completeness
0.916
0.948
0.626
0.950
0.711
0.000
F1
0.919
0.915
0.706
0.781
0.725
-nan

Overall accuracy 0.855

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area29_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9418
0.0232
0.0224
0.0083
0.0042
0.0000
building
0.0260
0.9622
0.0084
0.0031
0.0003
0.0000
low_veg
0.0337
0.0148
0.6692
0.2822
0.0001
0.0000
tree
0.0020
0.0011
0.0330
0.9640
0.0000
0.0000
car
0.1469
0.0166
0.0014
0.0083
0.8268
0.0000
clutter
0.3798
0.5674
0.0213
0.0069
0.0245
0.0000
Precision/Correctness
0.945
0.907
0.850
0.703
0.765
-nan
Recall/Completeness
0.942
0.962
0.669
0.964
0.827
0.000
F1
0.943
0.934
0.749
0.813
0.794
-nan

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_area31_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9510
0.0205
0.0166
0.0051
0.0068
0.0000
building
0.0459
0.9401
0.0097
0.0021
0.0022
0.0000
low_veg
0.0535
0.0084
0.8971
0.0402
0.0008
0.0000
tree
0.0391
0.0043
0.1112
0.8441
0.0014
0.0000
car
0.1587
0.2207
0.0131
0.0056
0.6019
0.0000
clutter
0.4291
0.5092
0.0184
0.0100
0.0333
0.0000
Precision/Correctness
0.891
0.882
0.854
0.913
0.823
-nan
Recall/Completeness
0.951
0.940
0.897
0.844
0.602
0.000
F1
0.920
0.910
0.875
0.877
0.695
-nan

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_area31_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9690
0.0138
0.0126
0.0013
0.0033
0.0000
building
0.0359
0.9569
0.0051
0.0003
0.0019
0.0000
low_veg
0.0345
0.0043
0.9283
0.0325
0.0004
0.0000
tree
0.0180
0.0009
0.0902
0.8904
0.0006
0.0000
car
0.0762
0.2475
0.0047
0.0013
0.6704
0.0000
clutter
0.3776
0.5665
0.0189
0.0033
0.0337
0.0000
Precision/Correctness
0.924
0.902
0.891
0.946
0.866
-nan
Recall/Completeness
0.969
0.957
0.928
0.890
0.670
0.000
F1
0.946
0.928
0.909
0.917
0.756
-nan

Overall accuracy 0.913

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
0.9474
0.0290
0.0144
0.0059
0.0032
0.0000
building
0.0878
0.7975
0.1061
0.0053
0.0032
0.0000
low_veg
0.0638
0.0986
0.7771
0.0601
0.0004
0.0000
tree
0.0391
0.0033
0.1285
0.8290
0.0001
0.0000
car
0.2841
0.0066
0.0125
0.0007
0.6962
0.0000
clutter
0.7361
0.2187
0.0033
0.0038
0.0381
0.0000
Precision/Correctness
0.815
0.857
0.705
0.867
0.675
-nan
Recall/Completeness
0.947
0.798
0.777
0.829
0.696
0.000
F1
0.876
0.826
0.739
0.848
0.686
-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
0.9629
0.0255
0.0077
0.0023
0.0016
0.0000
building
0.0796
0.8105
0.1046
0.0024
0.0029
0.0000
low_veg
0.0388
0.1027
0.8015
0.0568
0.0003
0.0000
tree
0.0190
0.0013
0.1176
0.8621
0.0000
0.0000
car
0.1657
0.0031
0.0068
0.0000
0.8245
0.0000
clutter
0.7186
0.2366
0.0022
0.0021
0.0404
0.0000
Precision/Correctness
0.842
0.867
0.722
0.896
0.697
-nan
Recall/Completeness
0.963
0.811
0.801
0.862
0.824
0.000
F1
0.899
0.838
0.760
0.879
0.755
-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_area35_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8471
0.0540
0.0758
0.0209
0.0022
0.0000
building
0.0562
0.9113
0.0266
0.0059
0.0000
0.0000
low_veg
0.0515
0.0129
0.7026
0.2329
0.0001
0.0000
tree
0.0361
0.0062
0.1165
0.8411
0.0001
0.0000
car
0.2850
0.0083
0.0079
0.0072
0.6916
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.847
0.930
0.765
0.753
0.897
--
Recall/Completeness
0.847
0.911
0.703
0.841
0.692
--
F1
0.847
0.921
0.733
0.795
0.781
--

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_area35_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8913
0.0497
0.0523
0.0060
0.0007
0.0000
building
0.0431
0.9420
0.0133
0.0016
0.0000
0.0000
low_veg
0.0378
0.0055
0.7302
0.2264
0.0000
0.0000
tree
0.0146
0.0020
0.0901
0.8932
0.0000
0.0000
car
0.1710
0.0101
0.0045
0.0026
0.8118
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.895
0.950
0.828
0.780
0.961
--
Recall/Completeness
0.891
0.942
0.730
0.893
0.812
--
F1
0.893
0.946
0.776
0.833
0.880
--

Overall accuracy 0.866

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
0.8921
0.0352
0.0535
0.0154
0.0039
0.0000
building
0.0568
0.8718
0.0633
0.0072
0.0009
0.0000
low_veg
0.0531
0.0475
0.8092
0.0897
0.0005
0.0000
tree
0.0236
0.0038
0.1385
0.8340
0.0000
0.0000
car
0.2410
0.0764
0.0284
0.0166
0.6376
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.869
0.901
0.797
0.839
0.810
--
Recall/Completeness
0.892
0.872
0.809
0.834
0.638
--
F1
0.880
0.886
0.803
0.837
0.714
--

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_area38_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9253
0.0311
0.0359
0.0057
0.0020
0.0000
building
0.0482
0.8990
0.0483
0.0037
0.0008
0.0000
low_veg
0.0392
0.0449
0.8403
0.0754
0.0002
0.0000
tree
0.0103
0.0012
0.1114
0.8770
0.0000
0.0000
car
0.1432
0.0788
0.0147
0.0122
0.7511
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.903
0.917
0.842
0.877
0.869
--
Recall/Completeness
0.925
0.899
0.840
0.877
0.751
--
F1
0.914
0.908
0.841
0.877
0.806
--

Overall accuracy 0.885

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image