Detailled semantic labeling (2D) result


Name Z. Cheng
Affiliation Wuhan University, China
Abbreviation WUH_C5
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
0.889
0.035
0.048
0.020
0.007
0.001
building
0.034
0.942
0.015
0.009
0.000
0.000
low_veg
0.057
0.022
0.794
0.126
0.000
0.000
tree
0.019
0.006
0.126
0.848
0.000
0.000
car
0.335
0.031
0.018
0.006
0.610
0.000
clutter
0.185
0.079
0.013
0.009
0.010
0.704
Precision/Correctness
0.885
0.937
0.791
0.843
0.769
0.929
Recall/Completeness
0.889
0.942
0.794
0.848
0.610
0.704
F1
0.887
0.939
0.792
0.845
0.680
0.801

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
0.921
0.027
0.036
0.011
0.004
0.001
building
0.025
0.961
0.009
0.005
0.000
0.000
low_veg
0.046
0.014
0.829
0.110
0.000
0.000
tree
0.011
0.003
0.109
0.877
0.000
0.000
car
0.270
0.035
0.013
0.003
0.679
0.000
clutter
0.148
0.078
0.008
0.004
0.008
0.754
Precision/Correctness
0.916
0.956
0.827
0.875
0.823
0.956
Recall/Completeness
0.921
0.961
0.829
0.877
0.679
0.754
F1
0.919
0.959
0.828
0.876
0.744
0.843

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
0.9043
0.0133
0.0522
0.0173
0.0129
0.0000
building
0.0267
0.9453
0.0227
0.0053
0.0000
0.0000
low_veg
0.0506
0.0152
0.8343
0.0998
0.0001
0.0000
tree
0.0225
0.0063
0.1439
0.8259
0.0002
0.0011
car
0.3155
0.0012
0.0072
0.0021
0.6740
0.0000
clutter
0.0000
0.0000
0.0052
0.0258
0.0000
0.9690
Precision/Correctness
0.887
0.962
0.791
0.870
0.760
0.985
Recall/Completeness
0.904
0.945
0.834
0.826
0.674
0.969
F1
0.895
0.953
0.812
0.847
0.714
0.977

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_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9421
0.0090
0.0317
0.0082
0.0089
0.0000
building
0.0190
0.9676
0.0108
0.0026
0.0000
0.0000
low_veg
0.0378
0.0087
0.8607
0.0929
0.0000
0.0000
tree
0.0117
0.0039
0.1264
0.8573
0.0001
0.0006
car
0.2402
0.0000
0.0022
0.0006
0.7570
0.0000
clutter
0.0000
0.0000
0.0021
0.0106
0.0000
0.9874
Precision/Correctness
0.923
0.977
0.831
0.895
0.802
0.992
Recall/Completeness
0.942
0.968
0.861
0.857
0.757
0.987
F1
0.932
0.973
0.846
0.876
0.779
0.990

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: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9007
0.0731
0.0122
0.0082
0.0058
0.0000
building
0.0731
0.9162
0.0062
0.0044
0.0002
0.0000
low_veg
0.2347
0.0873
0.4249
0.2508
0.0022
0.0000
tree
0.0517
0.0170
0.1089
0.8204
0.0020
0.0000
car
0.4823
0.0154
0.0059
0.0008
0.4956
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.812
0.951
0.605
0.711
0.785
--
Recall/Completeness
0.901
0.916
0.425
0.820
0.496
--
F1
0.854
0.933
0.499
0.762
0.608
--

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_area4_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9314
0.0517
0.0096
0.0043
0.0030
0.0000
building
0.0589
0.9330
0.0053
0.0027
0.0001
0.0000
low_veg
0.2085
0.0637
0.4632
0.2629
0.0018
0.0000
tree
0.0281
0.0087
0.1074
0.8550
0.0008
0.0000
car
0.4159
0.0144
0.0034
0.0001
0.5662
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.844
0.968
0.630
0.750
0.856
--
Recall/Completeness
0.931
0.933
0.463
0.855
0.566
--
F1
0.886
0.950
0.534
0.799
0.682
--

Overall accuracy 0.905

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area6_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8683
0.0654
0.0360
0.0201
0.0101
0.0000
building
0.0439
0.9306
0.0165
0.0086
0.0004
0.0000
low_veg
0.0956
0.0305
0.5907
0.2815
0.0016
0.0000
tree
0.0125
0.0044
0.0423
0.9406
0.0002
0.0000
car
0.3531
0.0147
0.0025
0.0080
0.6217
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.867
0.935
0.701
0.877
0.776
--
Recall/Completeness
0.868
0.931
0.591
0.941
0.622
--
F1
0.867
0.933
0.641
0.907
0.690
--

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
0.9112
0.0468
0.0268
0.0099
0.0054
0.0000
building
0.0346
0.9486
0.0127
0.0039
0.0002
0.0000
low_veg
0.0833
0.0166
0.6386
0.2598
0.0016
0.0000
tree
0.0052
0.0017
0.0329
0.9602
0.0001
0.0000
car
0.2992
0.0067
0.0003
0.0037
0.6900
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.900
0.959
0.749
0.907
0.842
--
Recall/Completeness
0.911
0.949
0.639
0.960
0.690
--
F1
0.906
0.954
0.689
0.933
0.759
--

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_area8_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8914
0.0429
0.0383
0.0198
0.0076
0.0000
building
0.0298
0.9478
0.0131
0.0081
0.0011
0.0000
low_veg
0.0738
0.0179
0.8409
0.0671
0.0004
0.0000
tree
0.0206
0.0089
0.1038
0.8667
0.0001
0.0000
car
0.4099
0.0051
0.0284
0.0076
0.5489
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.894
0.919
0.804
0.906
0.772
--
Recall/Completeness
0.891
0.948
0.841
0.867
0.549
--
F1
0.893
0.933
0.822
0.886
0.642
--

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_area8_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9232
0.0357
0.0261
0.0102
0.0049
0.0000
building
0.0179
0.9693
0.0073
0.0046
0.0009
0.0000
low_veg
0.0587
0.0097
0.8755
0.0559
0.0002
0.0000
tree
0.0093
0.0048
0.0859
0.8999
0.0000
0.0000
car
0.3502
0.0033
0.0177
0.0066
0.6222
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.928
0.942
0.847
0.934
0.816
--
Recall/Completeness
0.923
0.969
0.875
0.900
0.622
--
F1
0.926
0.956
0.861
0.917
0.706
--

Overall accuracy 0.916

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
0.8648
0.0559
0.0438
0.0307
0.0049
0.0000
building
0.0173
0.9459
0.0150
0.0209
0.0010
0.0000
low_veg
0.1027
0.0306
0.6539
0.2121
0.0007
0.0000
tree
0.0154
0.0069
0.0877
0.8898
0.0002
0.0000
car
0.2670
0.0310
0.0259
0.0129
0.6632
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.923
0.889
0.751
0.773
0.676
--
Recall/Completeness
0.865
0.946
0.654
0.890
0.663
--
F1
0.893
0.916
0.699
0.827
0.669
--

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_area10_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8997
0.0453
0.0351
0.0170
0.0029
0.0000
building
0.0102
0.9638
0.0099
0.0154
0.0007
0.0000
low_veg
0.0992
0.0222
0.6947
0.1831
0.0007
0.0000
tree
0.0086
0.0035
0.0714
0.9164
0.0000
0.0000
car
0.2176
0.0362
0.0240
0.0087
0.7135
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.940
0.913
0.795
0.816
0.727
--
Recall/Completeness
0.900
0.964
0.695
0.916
0.713
--
F1
0.919
0.938
0.741
0.863
0.720
--

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_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8382
0.0217
0.1051
0.0266
0.0083
0.0000
building
0.0109
0.9484
0.0325
0.0083
0.0000
0.0000
low_veg
0.0317
0.0183
0.8033
0.1447
0.0002
0.0018
tree
0.0078
0.0053
0.1787
0.8081
0.0001
0.0000
car
0.1663
0.0000
0.0278
0.0012
0.8047
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.888
0.946
0.727
0.863
0.762
--
Recall/Completeness
0.838
0.948
0.803
0.808
0.805
--
F1
0.863
0.947
0.763
0.835
0.783
--

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_area12_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8736
0.0188
0.0891
0.0142
0.0042
0.0000
building
0.0077
0.9700
0.0190
0.0034
0.0000
0.0000
low_veg
0.0287
0.0117
0.8325
0.1251
0.0001
0.0019
tree
0.0037
0.0027
0.1580
0.8355
0.0000
0.0000
car
0.1035
0.0000
0.0193
0.0001
0.8771
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.917
0.964
0.758
0.891
0.836
--
Recall/Completeness
0.874
0.970
0.833
0.836
0.877
--
F1
0.895
0.967
0.794
0.862
0.856
--

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_area14_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8407
0.0257
0.0959
0.0331
0.0046
0.0000
building
0.0212
0.9385
0.0341
0.0062
0.0000
0.0000
low_veg
0.0621
0.0422
0.7855
0.1102
0.0001
0.0000
tree
0.0228
0.0109
0.1702
0.7960
0.0000
0.0000
car
0.2554
0.0000
0.0223
0.0122
0.7101
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.874
0.890
0.701
0.879
0.633
--
Recall/Completeness
0.841
0.938
0.785
0.796
0.710
--
F1
0.857
0.914
0.741
0.835
0.669
--

Overall accuracy 0.828

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
0.8649
0.0225
0.0859
0.0232
0.0036
0.0000
building
0.0148
0.9639
0.0189
0.0024
0.0000
0.0000
low_veg
0.0563
0.0316
0.8148
0.0973
0.0000
0.0000
tree
0.0163
0.0063
0.1560
0.8214
0.0000
0.0000
car
0.1960
0.0000
0.0156
0.0088
0.7795
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.900
0.917
0.727
0.902
0.648
--
Recall/Completeness
0.865
0.964
0.815
0.821
0.780
--
F1
0.882
0.940
0.768
0.860
0.708
--

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_area16_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8280
0.0247
0.0910
0.0519
0.0044
0.0000
building
0.0219
0.9431
0.0205
0.0143
0.0001
0.0000
low_veg
0.0226
0.0139
0.8564
0.1055
0.0000
0.0015
tree
0.0251
0.0056
0.1708
0.7985
0.0000
0.0000
car
0.1109
0.0000
0.1738
0.0078
0.7075
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.865
0.944
0.759
0.875
0.682
--
Recall/Completeness
0.828
0.943
0.856
0.798
0.707
--
F1
0.846
0.943
0.805
0.835
0.695
--

Overall accuracy 0.846

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area16_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8631
0.0217
0.0783
0.0341
0.0027
0.0000
building
0.0163
0.9685
0.0080
0.0071
0.0001
0.0000
low_veg
0.0189
0.0087
0.8793
0.0914
0.0000
0.0016
tree
0.0184
0.0027
0.1565
0.8223
0.0000
0.0000
car
0.0484
0.0000
0.1761
0.0008
0.7747
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.894
0.962
0.786
0.900
0.738
--
Recall/Completeness
0.863
0.969
0.879
0.822
0.775
--
F1
0.878
0.965
0.830
0.859
0.756
--

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
0.8234
0.0374
0.0857
0.0510
0.0015
0.0009
building
0.0139
0.9593
0.0158
0.0106
0.0000
0.0004
low_veg
0.0388
0.0183
0.7475
0.1950
0.0002
0.0000
tree
0.0080
0.0020
0.0497
0.9402
0.0000
0.0001
car
0.3759
0.0043
0.0419
0.0164
0.5615
0.0000
clutter
0.0109
0.0000
0.0055
0.0018
0.0000
0.9818
Precision/Correctness
0.917
0.929
0.781
0.886
0.871
0.990
Recall/Completeness
0.823
0.959
0.748
0.940
0.562
0.982
F1
0.868
0.944
0.764
0.912
0.683
0.986

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_area20_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8545
0.0331
0.0807
0.0310
0.0006
0.0001
building
0.0108
0.9756
0.0092
0.0043
0.0000
0.0001
low_veg
0.0320
0.0106
0.7925
0.1646
0.0002
0.0000
tree
0.0036
0.0005
0.0384
0.9575
0.0000
0.0000
car
0.2953
0.0021
0.0359
0.0064
0.6602
0.0000
clutter
0.0019
0.0000
0.0012
0.0006
0.0000
0.9962
Precision/Correctness
0.944
0.949
0.812
0.914
0.926
0.999
Recall/Completeness
0.854
0.976
0.793
0.957
0.660
0.996
F1
0.897
0.962
0.802
0.935
0.771
0.997

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_area24_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.7854
0.0342
0.1526
0.0239
0.0040
0.0000
building
0.0677
0.8935
0.0256
0.0133
0.0000
0.0000
low_veg
0.0222
0.0161
0.9102
0.0511
0.0004
0.0000
tree
0.0134
0.0067
0.2265
0.7534
0.0000
0.0000
car
0.2800
0.0000
0.0368
0.0062
0.6770
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.813
0.927
0.816
0.876
0.773
--
Recall/Completeness
0.785
0.893
0.910
0.753
0.677
--
F1
0.799
0.910
0.860
0.810
0.722
--

Overall accuracy 0.848

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area24_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8222
0.0246
0.1358
0.0154
0.0020
0.0000
building
0.0657
0.9083
0.0159
0.0102
0.0000
0.0000
low_veg
0.0196
0.0120
0.9262
0.0418
0.0004
0.0000
tree
0.0084
0.0034
0.2026
0.7855
0.0000
0.0000
car
0.2131
0.0000
0.0288
0.0012
0.7569
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.834
0.949
0.841
0.901
0.823
--
Recall/Completeness
0.822
0.908
0.926
0.786
0.757
--
F1
0.828
0.928
0.882
0.839
0.789
--

Overall accuracy 0.873

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
0.9090
0.0391
0.0327
0.0063
0.0129
0.0000
building
0.0474
0.9272
0.0199
0.0053
0.0002
0.0000
low_veg
0.0970
0.0291
0.7624
0.1112
0.0003
0.0000
tree
0.0173
0.0087
0.1203
0.8537
0.0001
0.0000
car
0.4142
0.0052
0.0132
0.0042
0.5631
0.0000
clutter
0.7704
0.0486
0.1307
0.0084
0.0419
0.0000
Precision/Correctness
0.846
0.944
0.832
0.768
0.808
-nan
Recall/Completeness
0.909
0.927
0.762
0.854
0.563
0.000
F1
0.877
0.935
0.795
0.809
0.664
-nan

Overall accuracy 0.868

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
0.9394
0.0282
0.0229
0.0029
0.0066
0.0000
building
0.0362
0.9475
0.0132
0.0030
0.0001
0.0000
low_veg
0.0833
0.0171
0.8000
0.0994
0.0002
0.0000
tree
0.0092
0.0051
0.0945
0.8912
0.0000
0.0000
car
0.3522
0.0033
0.0086
0.0027
0.6331
0.0000
clutter
0.8145
0.0463
0.0970
0.0045
0.0377
0.0000
Precision/Correctness
0.882
0.964
0.874
0.806
0.875
-nan
Recall/Completeness
0.939
0.947
0.800
0.891
0.633
0.000
F1
0.910
0.956
0.836
0.847
0.734
-nan

Overall accuracy 0.902

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area29_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9257
0.0183
0.0350
0.0108
0.0058
0.0043
building
0.0152
0.9670
0.0089
0.0088
0.0000
0.0001
low_veg
0.0628
0.0304
0.7152
0.1913
0.0002
0.0001
tree
0.0147
0.0053
0.0602
0.9198
0.0001
0.0000
car
0.3690
0.0034
0.0190
0.0058
0.6029
0.0000
clutter
0.2629
0.1841
0.0229
0.0088
0.0265
0.4948
Precision/Correctness
0.934
0.935
0.810
0.739
0.710
0.888
Recall/Completeness
0.926
0.967
0.715
0.920
0.603
0.495
F1
0.930
0.951
0.760
0.819
0.652
0.635

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_area29_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9519
0.0117
0.0248
0.0054
0.0037
0.0026
building
0.0093
0.9808
0.0047
0.0052
0.0000
0.0000
low_veg
0.0467
0.0170
0.7577
0.1786
0.0000
0.0000
tree
0.0092
0.0027
0.0460
0.9422
0.0000
0.0000
car
0.3081
0.0010
0.0144
0.0031
0.6733
0.0000
clutter
0.2381
0.1840
0.0162
0.0034
0.0220
0.5362
Precision/Correctness
0.955
0.956
0.856
0.780
0.757
0.929
Recall/Completeness
0.952
0.981
0.758
0.942
0.673
0.536
F1
0.953
0.968
0.804
0.853
0.712
0.680

Overall accuracy 0.918

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
0.9537
0.0117
0.0124
0.0051
0.0110
0.0060
building
0.0245
0.9615
0.0073
0.0032
0.0019
0.0015
low_veg
0.0599
0.0070
0.9126
0.0197
0.0003
0.0005
tree
0.0396
0.0043
0.1115
0.8429
0.0008
0.0008
car
0.2130
0.1338
0.0172
0.0061
0.6299
0.0000
clutter
0.1845
0.1665
0.0174
0.0122
0.0186
0.6008
Precision/Correctness
0.916
0.942
0.868
0.937
0.803
0.874
Recall/Completeness
0.954
0.962
0.913
0.843
0.630
0.601
F1
0.934
0.951
0.890
0.887
0.706
0.712

Overall accuracy 0.914

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
0.9727
0.0081
0.0078
0.0017
0.0059
0.0037
building
0.0137
0.9803
0.0033
0.0005
0.0014
0.0008
low_veg
0.0384
0.0045
0.9434
0.0136
0.0000
0.0000
tree
0.0181
0.0016
0.0891
0.8910
0.0001
0.0001
car
0.1442
0.1582
0.0124
0.0015
0.6836
0.0000
clutter
0.1301
0.1860
0.0125
0.0058
0.0179
0.6479
Precision/Correctness
0.950
0.953
0.907
0.969
0.858
0.920
Recall/Completeness
0.973
0.980
0.943
0.891
0.684
0.648
F1
0.961
0.966
0.925
0.929
0.761
0.760

Overall accuracy 0.943

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
0.9652
0.0103
0.0080
0.0054
0.0044
0.0067
building
0.0104
0.9800
0.0019
0.0076
0.0000
0.0001
low_veg
0.0717
0.0229
0.8798
0.0250
0.0006
0.0000
tree
0.0412
0.0066
0.1314
0.8198
0.0000
0.0009
car
0.3791
0.0004
0.0112
0.0029
0.6064
0.0000
clutter
0.2885
0.0315
0.0022
0.0015
0.0000
0.6764
Precision/Correctness
0.905
0.966
0.885
0.913
0.814
0.931
Recall/Completeness
0.965
0.980
0.880
0.820
0.606
0.676
F1
0.934
0.973
0.882
0.864
0.695
0.784

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_area33_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9822
0.0065
0.0029
0.0022
0.0027
0.0035
building
0.0032
0.9921
0.0002
0.0044
0.0000
0.0000
low_veg
0.0444
0.0144
0.9202
0.0206
0.0003
0.0000
tree
0.0217
0.0023
0.1198
0.8559
0.0000
0.0002
car
0.3165
0.0000
0.0078
0.0008
0.6749
0.0000
clutter
0.2462
0.0267
0.0022
0.0003
0.0000
0.7247
Precision/Correctness
0.937
0.979
0.911
0.943
0.862
0.963
Recall/Completeness
0.982
0.992
0.920
0.856
0.675
0.725
F1
0.959
0.986
0.916
0.897
0.757
0.827

Overall accuracy 0.947

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
0.8449
0.0462
0.0710
0.0345
0.0033
0.0000
building
0.0429
0.9381
0.0095
0.0094
0.0000
0.0000
low_veg
0.0656
0.0170
0.6569
0.2605
0.0000
0.0000
tree
0.0221
0.0067
0.1193
0.8519
0.0000
0.0000
car
0.3781
0.0472
0.0108
0.0167
0.5473
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.856
0.934
0.771
0.724
0.828
--
Recall/Completeness
0.845
0.938
0.657
0.852
0.547
--
F1
0.850
0.936
0.709
0.783
0.659
--

Overall accuracy 0.823

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area35_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8986
0.0409
0.0438
0.0147
0.0020
0.0000
building
0.0309
0.9631
0.0032
0.0028
0.0000
0.0000
low_veg
0.0532
0.0095
0.6851
0.2521
0.0000
0.0000
tree
0.0092
0.0024
0.0933
0.8950
0.0000
0.0000
car
0.3056
0.0615
0.0110
0.0085
0.6134
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.896
0.953
0.835
0.755
0.876
--
Recall/Completeness
0.899
0.963
0.685
0.895
0.613
--
F1
0.897
0.958
0.753
0.819
0.721
--

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_area38_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8850
0.0370
0.0485
0.0215
0.0081
0.0000
building
0.0153
0.9523
0.0165
0.0146
0.0014
0.0000
low_veg
0.0540
0.0196
0.8102
0.1157
0.0004
0.0000
tree
0.0259
0.0067
0.1117
0.8551
0.0006
0.0000
car
0.2721
0.0218
0.0299
0.0077
0.6684
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.899
0.934
0.853
0.799
0.702
--
Recall/Completeness
0.885
0.952
0.810
0.855
0.668
--
F1
0.892
0.943
0.831
0.826
0.685
--

Overall accuracy 0.873

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
0.9176
0.0336
0.0333
0.0102
0.0052
0.0000
building
0.0087
0.9758
0.0069
0.0075
0.0011
0.0000
low_veg
0.0392
0.0127
0.8515
0.0963
0.0002
0.0000
tree
0.0151
0.0035
0.0917
0.8893
0.0004
0.0000
car
0.2057
0.0236
0.0187
0.0031
0.7488
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.934
0.951
0.893
0.843
0.748
--
Recall/Completeness
0.918
0.976
0.852
0.889
0.749
--
F1
0.926
0.963
0.872
0.866
0.749
--

Overall accuracy 0.908

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image