Detailled semantic labeling (2D) result


Name K. Chen et al.
Affiliation Chinese Academy of Sciences, Institute of Electronics, China
Abbreviation CASIE
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
0.903
0.028
0.048
0.017
0.004
0.000
building
0.064
0.908
0.022
0.005
0.001
0.000
low_veg
0.058
0.025
0.772
0.144
0.000
0.000
tree
0.023
0.006
0.103
0.868
0.000
0.000
car
0.287
0.045
0.011
0.007
0.650
0.000
clutter
0.456
0.204
0.016
0.010
0.050
0.264
Precision/Correctness
0.856
0.933
0.796
0.840
0.811
0.955
Recall/Completeness
0.903
0.908
0.772
0.868
0.650
0.264
F1
0.879
0.920
0.784
0.854
0.721
0.414

Overall accuracy 0.859

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
0.928
0.021
0.040
0.008
0.003
0.000
building
0.057
0.924
0.015
0.002
0.001
0.000
low_veg
0.046
0.017
0.806
0.130
0.000
0.000
tree
0.012
0.003
0.086
0.899
0.000
0.000
car
0.193
0.051
0.007
0.004
0.744
0.000
clutter
0.429
0.212
0.013
0.006
0.051
0.289
Precision/Correctness
0.885
0.953
0.831
0.869
0.841
0.971
Recall/Completeness
0.928
0.924
0.806
0.899
0.744
0.289
F1
0.906
0.938
0.818
0.884
0.790
0.446

Overall accuracy 0.888
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9413
0.0107
0.0285
0.0134
0.0061
0.0000
building
0.0366
0.9354
0.0233
0.0046
0.0001
0.0000
low_veg
0.1077
0.0194
0.6876
0.1832
0.0004
0.0017
tree
0.0344
0.0047
0.0943
0.8648
0.0002
0.0016
car
0.2944
0.0018
0.0045
0.0056
0.6937
0.0000
clutter
0.0108
0.0000
0.0014
0.0135
0.0000
0.9743
Precision/Correctness
0.831
0.961
0.824
0.812
0.863
0.957
Recall/Completeness
0.941
0.935
0.688
0.865
0.694
0.974
F1
0.883
0.948
0.750
0.837
0.769
0.966

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_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9666
0.0070
0.0180
0.0041
0.0042
0.0000
building
0.0281
0.9550
0.0151
0.0017
0.0000
0.0000
low_veg
0.0936
0.0109
0.7160
0.1772
0.0004
0.0019
tree
0.0183
0.0022
0.0811
0.8974
0.0002
0.0008
car
0.1815
0.0006
0.0035
0.0050
0.8094
0.0000
clutter
0.0092
0.0000
0.0014
0.0035
0.0000
0.9859
Precision/Correctness
0.869
0.979
0.858
0.836
0.891
0.968
Recall/Completeness
0.967
0.955
0.716
0.897
0.809
0.986
F1
0.915
0.967
0.781
0.865
0.848
0.977

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_area4_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9336
0.0438
0.0125
0.0049
0.0052
0.0000
building
0.0841
0.9028
0.0104
0.0018
0.0009
0.0000
low_veg
0.1562
0.0426
0.4644
0.3349
0.0017
0.0000
tree
0.0588
0.0151
0.0986
0.8275
0.0000
0.0000
car
0.3674
0.0090
0.0115
0.0043
0.6078
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.814
0.970
0.590
0.695
0.805
--
Recall/Completeness
0.934
0.903
0.464
0.827
0.608
--
F1
0.870
0.935
0.520
0.755
0.693
--

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_area4_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9583
0.0266
0.0098
0.0020
0.0033
0.0000
building
0.0713
0.9176
0.0092
0.0009
0.0010
0.0000
low_veg
0.1155
0.0146
0.5027
0.3658
0.0014
0.0000
tree
0.0299
0.0065
0.0906
0.8731
0.0000
0.0000
car
0.2786
0.0044
0.0110
0.0033
0.7027
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.842
0.984
0.615
0.722
0.832
--
Recall/Completeness
0.958
0.918
0.503
0.873
0.703
--
F1
0.897
0.950
0.553
0.791
0.762
--

Overall accuracy 0.908

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
0.8986
0.0522
0.0354
0.0097
0.0040
0.0000
building
0.0630
0.9182
0.0158
0.0029
0.0001
0.0000
low_veg
0.0981
0.0295
0.7413
0.1309
0.0003
0.0000
tree
0.0220
0.0037
0.0626
0.9116
0.0001
0.0001
car
0.3439
0.0068
0.0045
0.0030
0.6415
0.0003
clutter
--
--
--
--
--
--
Precision/Correctness
0.841
0.945
0.710
0.938
0.905
--
Recall/Completeness
0.899
0.918
0.741
0.912
0.641
--
F1
0.869
0.932
0.725
0.924
0.751
--

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_area6_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9319
0.0370
0.0267
0.0031
0.0013
0.0000
building
0.0538
0.9348
0.0107
0.0007
0.0000
0.0000
low_veg
0.0802
0.0176
0.7884
0.1138
0.0001
0.0000
tree
0.0120
0.0012
0.0483
0.9385
0.0000
0.0001
car
0.2443
0.0034
0.0035
0.0005
0.7479
0.0004
clutter
--
--
--
--
--
--
Precision/Correctness
0.876
0.966
0.756
0.958
0.963
--
Recall/Completeness
0.932
0.935
0.788
0.938
0.748
--
F1
0.903
0.950
0.772
0.948
0.842
--

Overall accuracy 0.919

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area8_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8782
0.0283
0.0808
0.0096
0.0031
0.0000
building
0.0270
0.9508
0.0181
0.0041
0.0000
0.0000
low_veg
0.0536
0.0141
0.8692
0.0628
0.0003
0.0000
tree
0.0252
0.0063
0.1069
0.8616
0.0001
0.0000
car
0.3440
0.0125
0.0185
0.0032
0.6218
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.906
0.943
0.755
0.926
0.908
--
Recall/Completeness
0.878
0.951
0.869
0.862
0.622
--
F1
0.892
0.947
0.808
0.893
0.738
--

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_area8_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9044
0.0224
0.0694
0.0025
0.0013
0.0000
building
0.0178
0.9707
0.0097
0.0018
0.0000
0.0000
low_veg
0.0396
0.0059
0.9028
0.0517
0.0001
0.0000
tree
0.0109
0.0031
0.0863
0.8997
0.0000
0.0000
car
0.2405
0.0120
0.0086
0.0026
0.7364
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.941
0.963
0.796
0.950
0.955
--
Recall/Completeness
0.904
0.971
0.903
0.900
0.736
--
F1
0.922
0.967
0.846
0.924
0.832
--

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_area10_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8310
0.0510
0.0917
0.0211
0.0051
0.0001
building
0.0265
0.9433
0.0159
0.0129
0.0013
0.0000
low_veg
0.0777
0.0244
0.7638
0.1340
0.0001
0.0000
tree
0.0189
0.0075
0.0867
0.8869
0.0001
0.0000
car
0.2251
0.0060
0.0014
0.0080
0.7594
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.925
0.899
0.706
0.841
0.703
--
Recall/Completeness
0.831
0.943
0.764
0.887
0.759
--
F1
0.875
0.921
0.734
0.863
0.730
--

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
0.8607
0.0384
0.0871
0.0098
0.0040
0.0001
building
0.0206
0.9578
0.0106
0.0097
0.0012
0.0000
low_veg
0.0743
0.0123
0.8075
0.1058
0.0001
0.0000
tree
0.0092
0.0036
0.0682
0.9189
0.0000
0.0000
car
0.1363
0.0036
0.0004
0.0042
0.8554
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.943
0.929
0.733
0.884
0.708
--
Recall/Completeness
0.861
0.958
0.808
0.919
0.855
--
F1
0.900
0.943
0.769
0.901
0.775
--

Overall accuracy 0.887

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8894
0.0260
0.0524
0.0300
0.0022
0.0000
building
0.1456
0.8348
0.0147
0.0050
0.0000
0.0000
low_veg
0.0511
0.0178
0.7456
0.1854
0.0002
0.0000
tree
0.0125
0.0073
0.1154
0.8646
0.0001
0.0000
car
0.1839
0.0007
0.0145
0.0132
0.7877
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.724
0.932
0.803
0.844
0.908
--
Recall/Completeness
0.889
0.835
0.746
0.865
0.788
--
F1
0.798
0.881
0.773
0.854
0.844
--

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
0.9171
0.0237
0.0435
0.0153
0.0004
0.0000
building
0.1523
0.8405
0.0059
0.0013
0.0000
0.0000
low_veg
0.0482
0.0094
0.7781
0.1643
0.0001
0.0000
tree
0.0068
0.0033
0.0986
0.8913
0.0001
0.0000
car
0.0838
0.0008
0.0121
0.0114
0.8918
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.740
0.958
0.833
0.871
0.969
--
Recall/Completeness
0.917
0.840
0.778
0.891
0.892
--
F1
0.819
0.895
0.805
0.881
0.929
--

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_area14_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8046
0.0361
0.1185
0.0347
0.0061
0.0000
building
0.0119
0.9644
0.0167
0.0070
0.0000
0.0000
low_veg
0.0708
0.0512
0.7284
0.1492
0.0004
0.0000
tree
0.0244
0.0133
0.1292
0.8331
0.0000
0.0000
car
0.1723
0.0059
0.0000
0.0157
0.8061
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.865
0.868
0.716
0.855
0.588
--
Recall/Completeness
0.805
0.964
0.728
0.833
0.806
--
F1
0.834
0.914
0.722
0.844
0.680
--

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_area14_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8226
0.0321
0.1161
0.0239
0.0054
0.0000
building
0.0062
0.9829
0.0078
0.0032
0.0000
0.0000
low_veg
0.0649
0.0381
0.7589
0.1377
0.0004
0.0000
tree
0.0167
0.0067
0.1175
0.8591
0.0000
0.0000
car
0.0711
0.0065
0.0000
0.0127
0.9097
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.893
0.899
0.735
0.878
0.570
--
Recall/Completeness
0.823
0.983
0.759
0.859
0.910
--
F1
0.856
0.939
0.747
0.868
0.701
--

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_area16_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8383
0.0305
0.0740
0.0534
0.0038
0.0000
building
0.0197
0.9541
0.0172
0.0089
0.0001
0.0000
low_veg
0.0274
0.0155
0.8399
0.1167
0.0001
0.0004
tree
0.0250
0.0055
0.1329
0.8366
0.0000
0.0000
car
0.1134
0.0004
0.0000
0.0114
0.8748
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.860
0.937
0.798
0.873
0.757
--
Recall/Completeness
0.838
0.954
0.840
0.837
0.875
--
F1
0.849
0.946
0.818
0.855
0.812
--

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: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8723
0.0269
0.0645
0.0341
0.0022
0.0000
building
0.0152
0.9742
0.0071
0.0035
0.0000
0.0000
low_veg
0.0234
0.0095
0.8636
0.1031
0.0001
0.0004
tree
0.0172
0.0023
0.1190
0.8615
0.0000
0.0000
car
0.0408
0.0000
0.0000
0.0045
0.9547
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.891
0.958
0.824
0.897
0.809
--
Recall/Completeness
0.872
0.974
0.864
0.862
0.955
--
F1
0.882
0.966
0.843
0.879
0.876
--

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_area20_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8399
0.0618
0.0529
0.0406
0.0047
0.0000
building
0.0218
0.9477
0.0251
0.0053
0.0000
0.0000
low_veg
0.0545
0.0319
0.7733
0.1400
0.0004
0.0000
tree
0.0108
0.0017
0.0619
0.9256
0.0000
0.0000
car
0.1126
0.0007
0.0415
0.0110
0.8342
0.0000
clutter
0.7563
0.2403
0.0025
0.0010
0.0000
0.0000
Precision/Correctness
0.811
0.857
0.787
0.913
0.770
-nan
Recall/Completeness
0.840
0.948
0.773
0.926
0.834
0.000
F1
0.825
0.900
0.780
0.919
0.801
-nan

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_area20_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8691
0.0562
0.0495
0.0229
0.0023
0.0000
building
0.0184
0.9599
0.0203
0.0014
0.0000
0.0000
low_veg
0.0484
0.0223
0.8156
0.1133
0.0004
0.0000
tree
0.0054
0.0002
0.0482
0.9461
0.0000
0.0000
car
0.0557
0.0000
0.0365
0.0038
0.9040
0.0000
clutter
0.7633
0.2348
0.0017
0.0002
0.0000
0.0000
Precision/Correctness
0.829
0.878
0.818
0.939
0.832
-nan
Recall/Completeness
0.869
0.960
0.816
0.946
0.904
0.000
F1
0.849
0.917
0.817
0.942
0.867
-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_area22_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8862
0.0249
0.0533
0.0305
0.0050
0.0000
building
0.0304
0.9471
0.0172
0.0053
0.0000
0.0000
low_veg
0.0858
0.0371
0.7404
0.1365
0.0002
0.0000
tree
0.0211
0.0042
0.0641
0.9104
0.0002
0.0000
car
0.2929
0.0195
0.0351
0.0106
0.6420
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.898
0.909
0.793
0.873
0.806
--
Recall/Completeness
0.886
0.947
0.740
0.910
0.642
--
F1
0.892
0.928
0.766
0.891
0.715
--

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_area22_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9181
0.0186
0.0452
0.0150
0.0031
0.0000
building
0.0240
0.9661
0.0080
0.0019
0.0000
0.0000
low_veg
0.0819
0.0244
0.7850
0.1085
0.0002
0.0000
tree
0.0089
0.0014
0.0468
0.9427
0.0001
0.0000
car
0.2083
0.0200
0.0242
0.0034
0.7441
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.924
0.939
0.838
0.911
0.848
--
Recall/Completeness
0.918
0.966
0.785
0.943
0.744
--
F1
0.921
0.952
0.810
0.927
0.793
--

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_area24_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8235
0.0329
0.1005
0.0379
0.0052
0.0000
building
0.0623
0.8926
0.0344
0.0106
0.0001
0.0000
low_veg
0.0285
0.0234
0.8650
0.0831
0.0000
0.0000
tree
0.0167
0.0076
0.1754
0.8003
0.0001
0.0000
car
0.2455
0.0000
0.0035
0.0018
0.7492
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.807
0.911
0.844
0.830
0.777
--
Recall/Completeness
0.823
0.893
0.865
0.800
0.749
--
F1
0.815
0.902
0.854
0.815
0.763
--

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_area24_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8532
0.0238
0.0912
0.0283
0.0036
0.0000
building
0.0607
0.9033
0.0273
0.0086
0.0001
0.0000
low_veg
0.0251
0.0188
0.8834
0.0727
0.0000
0.0000
tree
0.0098
0.0037
0.1553
0.8311
0.0001
0.0000
car
0.1492
0.0000
0.0000
0.0000
0.8508
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.830
0.934
0.866
0.852
0.800
--
Recall/Completeness
0.853
0.903
0.883
0.831
0.851
--
F1
0.842
0.918
0.875
0.841
0.824
--

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: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9347
0.0217
0.0276
0.0081
0.0080
0.0000
building
0.0705
0.9040
0.0206
0.0045
0.0003
0.0000
low_veg
0.0636
0.0229
0.6920
0.2214
0.0001
0.0000
tree
0.0117
0.0065
0.0474
0.9344
0.0001
0.0000
car
0.2873
0.0102
0.0081
0.0057
0.6886
0.0000
clutter
0.6453
0.1308
0.1332
0.0208
0.0644
0.0056
Precision/Correctness
0.859
0.961
0.864
0.663
0.887
1.000
Recall/Completeness
0.935
0.904
0.692
0.934
0.689
0.006
F1
0.895
0.932
0.768
0.775
0.775
0.011

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_area27_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9608
0.0130
0.0204
0.0032
0.0026
0.0000
building
0.0593
0.9242
0.0143
0.0020
0.0002
0.0000
low_veg
0.0471
0.0107
0.7300
0.2121
0.0000
0.0000
tree
0.0045
0.0023
0.0325
0.9607
0.0000
0.0000
car
0.1908
0.0087
0.0063
0.0035
0.7906
0.0000
clutter
0.6504
0.1416
0.1117
0.0183
0.0701
0.0079
Precision/Correctness
0.892
0.980
0.901
0.691
0.948
1.000
Recall/Completeness
0.961
0.924
0.730
0.961
0.791
0.008
F1
0.925
0.951
0.806
0.804
0.862
0.016

Overall accuracy 0.897

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
0.9375
0.0139
0.0275
0.0142
0.0068
0.0000
building
0.0398
0.9379
0.0153
0.0069
0.0000
0.0000
low_veg
0.0619
0.0237
0.6311
0.2830
0.0003
0.0000
tree
0.0051
0.0020
0.0405
0.9525
0.0000
0.0000
car
0.3207
0.0033
0.0022
0.0102
0.6635
0.0000
clutter
0.5804
0.2859
0.0287
0.0143
0.0739
0.0167
Precision/Correctness
0.904
0.933
0.816
0.674
0.635
0.980
Recall/Completeness
0.938
0.938
0.631
0.952
0.664
0.017
F1
0.921
0.936
0.712
0.790
0.649
0.033

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
0.9595
0.0076
0.0206
0.0068
0.0055
0.0000
building
0.0351
0.9513
0.0100
0.0037
0.0000
0.0000
low_veg
0.0419
0.0125
0.6749
0.2707
0.0000
0.0000
tree
0.0012
0.0003
0.0313
0.9673
0.0000
0.0000
car
0.2421
0.0009
0.0014
0.0083
0.7473
0.0000
clutter
0.5680
0.3037
0.0237
0.0061
0.0801
0.0185
Precision/Correctness
0.925
0.953
0.855
0.714
0.628
0.997
Recall/Completeness
0.960
0.951
0.675
0.967
0.747
0.018
F1
0.942
0.952
0.754
0.822
0.682
0.036

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_area31_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9704
0.0098
0.0128
0.0037
0.0033
0.0001
building
0.1957
0.7883
0.0112
0.0022
0.0025
0.0000
low_veg
0.0447
0.0033
0.9283
0.0235
0.0002
0.0000
tree
0.0410
0.0041
0.1170
0.8371
0.0008
0.0000
car
0.2327
0.2204
0.0109
0.0067
0.5290
0.0003
clutter
0.4057
0.4381
0.0326
0.0117
0.0571
0.0548
Precision/Correctness
0.812
0.888
0.858
0.939
0.826
0.971
Recall/Completeness
0.970
0.788
0.928
0.837
0.529
0.055
F1
0.884
0.835
0.892
0.885
0.645
0.104

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_area31_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9821
0.0068
0.0091
0.0008
0.0012
0.0001
building
0.1898
0.8021
0.0058
0.0004
0.0020
0.0000
low_veg
0.0254
0.0011
0.9564
0.0170
0.0001
0.0000
tree
0.0150
0.0012
0.0992
0.8843
0.0003
0.0000
car
0.1448
0.2519
0.0054
0.0031
0.5947
0.0001
clutter
0.3482
0.4919
0.0298
0.0060
0.0596
0.0644
Precision/Correctness
0.836
0.903
0.893
0.968
0.855
0.986
Recall/Completeness
0.982
0.802
0.956
0.884
0.595
0.064
F1
0.903
0.850
0.924
0.924
0.701
0.121

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_area33_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9799
0.0046
0.0094
0.0031
0.0014
0.0017
building
0.1518
0.7705
0.0690
0.0038
0.0047
0.0003
low_veg
0.0781
0.1057
0.6561
0.1601
0.0000
0.0000
tree
0.0499
0.0056
0.1528
0.7917
0.0000
0.0000
car
0.3797
0.0009
0.0079
0.0025
0.6041
0.0048
clutter
0.4896
0.0699
0.0026
0.0078
0.0814
0.3487
Precision/Correctness
0.803
0.909
0.717
0.752
0.553
0.959
Recall/Completeness
0.980
0.771
0.656
0.792
0.604
0.349
F1
0.883
0.834
0.685
0.771
0.577
0.511

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
0.9914
0.0019
0.0049
0.0008
0.0005
0.0005
building
0.1477
0.7790
0.0660
0.0026
0.0044
0.0002
low_veg
0.0470
0.1098
0.6734
0.1698
0.0000
0.0000
tree
0.0247
0.0015
0.1407
0.8331
0.0000
0.0000
car
0.2966
0.0003
0.0042
0.0017
0.6919
0.0053
clutter
0.4542
0.0691
0.0014
0.0086
0.0871
0.3796
Precision/Correctness
0.827
0.918
0.738
0.758
0.539
0.985
Recall/Completeness
0.991
0.779
0.673
0.833
0.692
0.380
F1
0.902
0.843
0.704
0.794
0.606
0.548

Overall accuracy 0.830

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
0.8710
0.0365
0.0723
0.0189
0.0013
0.0000
building
0.0434
0.9313
0.0202
0.0048
0.0003
0.0000
low_veg
0.0488
0.0136
0.7113
0.2261
0.0001
0.0000
tree
0.0317
0.0059
0.1225
0.8397
0.0002
0.0000
car
0.3566
0.0075
0.0000
0.0083
0.6275
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.866
0.947
0.772
0.760
0.907
--
Recall/Completeness
0.871
0.931
0.711
0.840
0.628
--
F1
0.869
0.939
0.740
0.798
0.742
--

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_area35_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9120
0.0315
0.0507
0.0054
0.0003
0.0000
building
0.0330
0.9557
0.0100
0.0010
0.0003
0.0000
low_veg
0.0343
0.0066
0.7379
0.2211
0.0001
0.0000
tree
0.0119
0.0017
0.0948
0.8915
0.0000
0.0000
car
0.2484
0.0078
0.0000
0.0021
0.7417
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.911
0.965
0.830
0.785
0.952
--
Recall/Completeness
0.912
0.956
0.738
0.892
0.742
--
F1
0.912
0.960
0.781
0.835
0.834
--

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_area38_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9111
0.0239
0.0487
0.0137
0.0026
0.0000
building
0.0246
0.9317
0.0375
0.0048
0.0014
0.0000
low_veg
0.0348
0.0158
0.8507
0.0985
0.0001
0.0000
tree
0.0224
0.0080
0.1114
0.8582
0.0000
0.0000
car
0.2475
0.0524
0.0217
0.0134
0.6651
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.915
0.948
0.843
0.837
0.858
--
Recall/Completeness
0.911
0.932
0.851
0.858
0.665
--
F1
0.913
0.940
0.847
0.847
0.749
--

Overall accuracy 0.887

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area38_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9382
0.0208
0.0348
0.0051
0.0011
0.0000
building
0.0168
0.9558
0.0243
0.0018
0.0012
0.0000
low_veg
0.0200
0.0100
0.8872
0.0828
0.0000
0.0000
tree
0.0084
0.0051
0.0887
0.8978
0.0000
0.0000
car
0.1481
0.0586
0.0130
0.0103
0.7700
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.952
0.963
0.882
0.873
0.898
--
Recall/Completeness
0.938
0.956
0.887
0.898
0.770
--
F1
0.945
0.959
0.885
0.885
0.829
--

Overall accuracy 0.920

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image