Detailled semantic labeling (2D) result


Name H. Li et al.
Affiliation Chinese Academy of Sciences, China
Abbreviation CAS_L4
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
0.037
0.039
0.015
0.005
0.000
building
0.055
0.917
0.023
0.004
0.001
0.000
low_veg
0.062
0.027
0.770
0.140
0.001
0.000
tree
0.021
0.005
0.101
0.872
0.000
0.000
car
0.213
0.041
0.009
0.005
0.732
0.001
clutter
0.303
0.343
0.019
0.006
0.048
0.280
Precision/Correctness
0.869
0.919
0.806
0.846
0.804
0.969
Recall/Completeness
0.903
0.917
0.770
0.872
0.732
0.280
F1
0.886
0.918
0.788
0.859
0.766
0.434

Overall accuracy 0.863

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
0.929
0.030
0.031
0.007
0.003
0.000
building
0.047
0.933
0.017
0.002
0.001
0.000
low_veg
0.049
0.018
0.806
0.126
0.001
0.000
tree
0.010
0.002
0.084
0.904
0.000
0.000
car
0.114
0.044
0.005
0.002
0.834
0.001
clutter
0.261
0.364
0.016
0.002
0.050
0.307
Precision/Correctness
0.900
0.940
0.841
0.874
0.834
0.978
Recall/Completeness
0.929
0.933
0.806
0.904
0.834
0.307
F1
0.914
0.936
0.823
0.889
0.834
0.468

Overall accuracy 0.892
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9397
0.0202
0.0222
0.0115
0.0064
0.0000
building
0.0434
0.9310
0.0211
0.0027
0.0015
0.0002
low_veg
0.0745
0.0240
0.7144
0.1869
0.0002
0.0000
tree
0.0276
0.0050
0.0980
0.8683
0.0001
0.0011
car
0.2091
0.0152
0.0004
0.0011
0.7742
0.0000
clutter
0.0050
0.0000
0.0000
0.0186
0.0009
0.9756
Precision/Correctness
0.860
0.945
0.835
0.812
0.856
0.982
Recall/Completeness
0.940
0.931
0.714
0.868
0.774
0.976
F1
0.898
0.938
0.770
0.839
0.813
0.979

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_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9644
0.0161
0.0123
0.0028
0.0044
0.0000
building
0.0358
0.9484
0.0134
0.0006
0.0015
0.0003
low_veg
0.0579
0.0145
0.7458
0.1816
0.0001
0.0000
tree
0.0131
0.0019
0.0845
0.9000
0.0001
0.0005
car
0.0969
0.0106
0.0001
0.0001
0.8923
0.0000
clutter
0.0049
0.0000
0.0000
0.0057
0.0009
0.9885
Precision/Correctness
0.898
0.965
0.868
0.835
0.876
0.990
Recall/Completeness
0.964
0.948
0.746
0.900
0.892
0.988
F1
0.930
0.957
0.802
0.866
0.884
0.989

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_area4_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9279
0.0516
0.0099
0.0049
0.0057
0.0000
building
0.0722
0.9185
0.0069
0.0015
0.0008
0.0000
low_veg
0.1816
0.0707
0.4689
0.2745
0.0043
0.0000
tree
0.0532
0.0136
0.1057
0.8261
0.0014
0.0000
car
0.2894
0.0279
0.0019
0.0026
0.6783
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.830
0.964
0.638
0.731
0.805
--
Recall/Completeness
0.928
0.919
0.469
0.826
0.678
--
F1
0.876
0.941
0.540
0.776
0.736
--

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_area4_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9559
0.0315
0.0067
0.0019
0.0040
0.0000
building
0.0596
0.9331
0.0060
0.0006
0.0008
0.0000
low_veg
0.1455
0.0440
0.5013
0.3049
0.0043
0.0000
tree
0.0251
0.0047
0.1038
0.8652
0.0012
0.0000
car
0.1828
0.0215
0.0001
0.0016
0.7940
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.861
0.980
0.661
0.756
0.827
--
Recall/Completeness
0.956
0.933
0.501
0.865
0.794
--
F1
0.906
0.956
0.570
0.807
0.810
--

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
0.9051
0.0487
0.0323
0.0071
0.0068
0.0000
building
0.0697
0.9127
0.0143
0.0026
0.0007
0.0000
low_veg
0.0962
0.0264
0.7591
0.1177
0.0006
0.0000
tree
0.0162
0.0031
0.0753
0.9051
0.0002
0.0000
car
0.2800
0.0075
0.0021
0.0019
0.7085
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.844
0.949
0.700
0.945
0.848
--
Recall/Completeness
0.905
0.913
0.759
0.905
0.708
--
F1
0.874
0.930
0.728
0.925
0.772
--

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_area6_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9374
0.0354
0.0223
0.0014
0.0035
0.0000
building
0.0594
0.9302
0.0092
0.0006
0.0006
0.0000
low_veg
0.0794
0.0124
0.8069
0.1011
0.0003
0.0000
tree
0.0054
0.0006
0.0603
0.9336
0.0000
0.0000
car
0.1783
0.0034
0.0006
0.0008
0.8169
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.880
0.969
0.747
0.964
0.900
--
Recall/Completeness
0.937
0.930
0.807
0.934
0.817
--
F1
0.908
0.949
0.776
0.948
0.857
--

Overall accuracy 0.920

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
0.8869
0.0306
0.0690
0.0078
0.0056
0.0000
building
0.0435
0.9348
0.0171
0.0036
0.0011
0.0000
low_veg
0.0594
0.0132
0.8574
0.0691
0.0009
0.0000
tree
0.0247
0.0050
0.0916
0.8787
0.0001
0.0000
car
0.2393
0.0197
0.0132
0.0053
0.7225
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.898
0.940
0.779
0.925
0.847
--
Recall/Completeness
0.887
0.935
0.857
0.879
0.723
--
F1
0.892
0.937
0.817
0.901
0.780
--

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_area8_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9130
0.0245
0.0573
0.0019
0.0033
0.0000
building
0.0324
0.9554
0.0095
0.0015
0.0011
0.0000
low_veg
0.0434
0.0056
0.8913
0.0592
0.0005
0.0000
tree
0.0097
0.0016
0.0688
0.9198
0.0000
0.0000
car
0.1257
0.0204
0.0077
0.0043
0.8418
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.934
0.961
0.825
0.946
0.884
--
Recall/Completeness
0.913
0.955
0.891
0.920
0.842
--
F1
0.923
0.958
0.857
0.933
0.862
--

Overall accuracy 0.920

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
0.8207
0.1049
0.0524
0.0171
0.0048
0.0000
building
0.0364
0.9354
0.0191
0.0087
0.0004
0.0000
low_veg
0.0867
0.0307
0.7434
0.1391
0.0001
0.0000
tree
0.0160
0.0075
0.0805
0.8959
0.0000
0.0000
car
0.1762
0.0257
0.0212
0.0007
0.7762
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.916
0.826
0.762
0.848
0.741
--
Recall/Completeness
0.821
0.935
0.743
0.896
0.776
--
F1
0.866
0.877
0.753
0.871
0.758
--

Overall accuracy 0.849

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area10_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8500
0.0961
0.0439
0.0066
0.0034
0.0000
building
0.0303
0.9482
0.0148
0.0064
0.0003
0.0000
low_veg
0.0832
0.0175
0.7870
0.1121
0.0001
0.0000
tree
0.0068
0.0031
0.0594
0.9307
0.0000
0.0000
car
0.0938
0.0262
0.0176
0.0000
0.8624
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.934
0.849
0.804
0.890
0.765
--
Recall/Completeness
0.850
0.948
0.787
0.931
0.862
--
F1
0.890
0.896
0.795
0.910
0.811
--

Overall accuracy 0.879

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
0.8855
0.0346
0.0527
0.0248
0.0024
0.0000
building
0.0596
0.9240
0.0122
0.0041
0.0000
0.0000
low_veg
0.0460
0.0261
0.7636
0.1634
0.0002
0.0007
tree
0.0111
0.0065
0.1151
0.8674
0.0000
0.0000
car
0.1835
0.0002
0.0115
0.0078
0.7821
0.0148
clutter
--
--
--
--
--
--
Precision/Correctness
0.809
0.922
0.808
0.861
0.905
--
Recall/Completeness
0.885
0.924
0.764
0.867
0.782
--
F1
0.845
0.923
0.785
0.864
0.839
--

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_area12_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9119
0.0315
0.0441
0.0117
0.0007
0.0000
building
0.0597
0.9343
0.0049
0.0011
0.0000
0.0000
low_veg
0.0427
0.0158
0.7989
0.1416
0.0002
0.0008
tree
0.0056
0.0023
0.0975
0.8947
0.0000
0.0000
car
0.0599
0.0000
0.0079
0.0021
0.9118
0.0183
clutter
--
--
--
--
--
--
Precision/Correctness
0.834
0.949
0.839
0.888
0.957
--
Recall/Completeness
0.912
0.934
0.799
0.895
0.912
--
F1
0.871
0.941
0.818
0.891
0.934
--

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_area14_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8345
0.0403
0.0881
0.0311
0.0060
0.0000
building
0.0165
0.9619
0.0170
0.0046
0.0001
0.0000
low_veg
0.0909
0.0445
0.7183
0.1444
0.0019
0.0000
tree
0.0257
0.0113
0.1389
0.8240
0.0001
0.0000
car
0.1222
0.0002
0.0030
0.0034
0.8711
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.846
0.874
0.724
0.861
0.552
--
Recall/Completeness
0.835
0.962
0.718
0.824
0.871
--
F1
0.840
0.916
0.721
0.842
0.676
--

Overall accuracy 0.824

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
0.8544
0.0361
0.0836
0.0207
0.0052
0.0000
building
0.0113
0.9788
0.0085
0.0014
0.0001
0.0000
low_veg
0.0850
0.0295
0.7489
0.1346
0.0019
0.0000
tree
0.0175
0.0051
0.1258
0.8515
0.0000
0.0000
car
0.0284
0.0000
0.0012
0.0006
0.9698
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.873
0.907
0.746
0.882
0.528
--
Recall/Completeness
0.854
0.979
0.749
0.852
0.970
--
F1
0.863
0.941
0.747
0.866
0.684
--

Overall accuracy 0.849

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area16_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8162
0.0363
0.0946
0.0500
0.0029
0.0000
building
0.0357
0.9224
0.0328
0.0089
0.0001
0.0000
low_veg
0.0192
0.0160
0.8431
0.1204
0.0006
0.0007
tree
0.0240
0.0049
0.1360
0.8351
0.0000
0.0000
car
0.1578
0.0026
0.0261
0.0019
0.8116
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.856
0.931
0.780
0.872
0.729
--
Recall/Completeness
0.816
0.922
0.843
0.835
0.812
--
F1
0.836
0.927
0.811
0.853
0.768
--

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_area16_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8502
0.0318
0.0852
0.0315
0.0013
0.0000
building
0.0322
0.9419
0.0216
0.0042
0.0001
0.0000
low_veg
0.0143
0.0098
0.8680
0.1065
0.0007
0.0007
tree
0.0163
0.0017
0.1214
0.8606
0.0000
0.0000
car
0.0798
0.0000
0.0160
0.0000
0.9042
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.888
0.953
0.808
0.895
0.774
--
Recall/Completeness
0.850
0.942
0.868
0.861
0.904
--
F1
0.869
0.947
0.837
0.877
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_area20_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8553
0.0453
0.0524
0.0428
0.0042
0.0000
building
0.0244
0.9527
0.0181
0.0049
0.0000
0.0000
low_veg
0.0537
0.0351
0.7541
0.1569
0.0001
0.0000
tree
0.0077
0.0020
0.0541
0.9362
0.0000
0.0000
car
0.1000
0.0296
0.0178
0.0112
0.8414
0.0000
clutter
0.0078
0.9894
0.0023
0.0005
0.0000
0.0000
Precision/Correctness
0.905
0.781
0.803
0.906
0.799
0.000
Recall/Completeness
0.855
0.953
0.754
0.936
0.841
0.000
F1
0.879
0.858
0.778
0.921
0.820
-nan

Overall accuracy 0.862

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area20_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8885
0.0363
0.0493
0.0239
0.0020
0.0000
building
0.0221
0.9622
0.0144
0.0013
0.0000
0.0000
low_veg
0.0474
0.0233
0.8001
0.1291
0.0001
0.0000
tree
0.0032
0.0004
0.0410
0.9555
0.0000
0.0000
car
0.0322
0.0303
0.0023
0.0040
0.9312
0.0000
clutter
0.0045
0.9936
0.0017
0.0003
0.0000
0.0000
Precision/Correctness
0.927
0.801
0.834
0.932
0.866
0.000
Recall/Completeness
0.888
0.962
0.800
0.956
0.931
0.000
F1
0.908
0.874
0.817
0.944
0.897
-nan

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_area22_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8962
0.0241
0.0428
0.0311
0.0058
0.0000
building
0.0381
0.9444
0.0118
0.0050
0.0006
0.0000
low_veg
0.0966
0.0407
0.7213
0.1408
0.0006
0.0000
tree
0.0213
0.0041
0.0606
0.9140
0.0000
0.0000
car
0.2104
0.0179
0.0192
0.0086
0.7439
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.892
0.907
0.813
0.870
0.796
--
Recall/Completeness
0.896
0.944
0.721
0.914
0.744
--
F1
0.894
0.925
0.764
0.892
0.769
--

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_area22_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9292
0.0163
0.0360
0.0151
0.0033
0.0000
building
0.0318
0.9606
0.0048
0.0023
0.0006
0.0000
low_veg
0.0929
0.0279
0.7666
0.1120
0.0005
0.0000
tree
0.0089
0.0012
0.0435
0.9464
0.0000
0.0000
car
0.1181
0.0215
0.0118
0.0025
0.8461
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.917
0.939
0.856
0.909
0.842
--
Recall/Completeness
0.929
0.961
0.767
0.946
0.846
--
F1
0.923
0.950
0.809
0.927
0.844
--

Overall accuracy 0.907

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
0.8197
0.0457
0.0932
0.0345
0.0069
0.0000
building
0.0635
0.8775
0.0457
0.0133
0.0000
0.0000
low_veg
0.0260
0.0209
0.8654
0.0873
0.0004
0.0000
tree
0.0166
0.0064
0.1512
0.8257
0.0000
0.0000
car
0.2271
0.0000
0.0055
0.0042
0.7633
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.812
0.907
0.855
0.828
0.707
--
Recall/Completeness
0.820
0.877
0.865
0.826
0.763
--
F1
0.816
0.892
0.860
0.827
0.734
--

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_area24_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8500
0.0346
0.0870
0.0230
0.0054
0.0000
building
0.0611
0.8884
0.0395
0.0109
0.0001
0.0000
low_veg
0.0224
0.0154
0.8857
0.0760
0.0004
0.0000
tree
0.0102
0.0029
0.1308
0.8562
0.0000
0.0000
car
0.1229
0.0000
0.0012
0.0002
0.8758
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.836
0.933
0.875
0.852
0.710
--
Recall/Completeness
0.850
0.888
0.886
0.856
0.876
--
F1
0.843
0.910
0.881
0.854
0.784
--

Overall accuracy 0.874

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
0.9325
0.0321
0.0206
0.0058
0.0089
0.0000
building
0.0799
0.8942
0.0210
0.0038
0.0011
0.0000
low_veg
0.0984
0.0267
0.6773
0.1966
0.0010
0.0000
tree
0.0121
0.0051
0.0647
0.9180
0.0002
0.0000
car
0.2301
0.0095
0.0053
0.0049
0.7502
0.0000
clutter
0.6230
0.1483
0.1078
0.0038
0.1171
0.0000
Precision/Correctness
0.838
0.949
0.864
0.687
0.867
0.000
Recall/Completeness
0.933
0.894
0.677
0.918
0.750
0.000
F1
0.883
0.921
0.759
0.786
0.804
-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_area27_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9581
0.0229
0.0137
0.0019
0.0033
0.0000
building
0.0678
0.9136
0.0160
0.0017
0.0010
0.0000
low_veg
0.0804
0.0146
0.7167
0.1874
0.0008
0.0000
tree
0.0044
0.0015
0.0464
0.9477
0.0000
0.0000
car
0.1295
0.0064
0.0026
0.0043
0.8571
0.0000
clutter
0.6313
0.1540
0.0763
0.0018
0.1366
0.0000
Precision/Correctness
0.872
0.969
0.901
0.716
0.918
-nan
Recall/Completeness
0.958
0.914
0.717
0.948
0.857
0.000
F1
0.913
0.940
0.798
0.815
0.887
-nan

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_area29_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9385
0.0206
0.0227
0.0124
0.0058
0.0000
building
0.0317
0.9523
0.0105
0.0055
0.0000
0.0000
low_veg
0.0624
0.0203
0.6402
0.2765
0.0006
0.0000
tree
0.0067
0.0020
0.0343
0.9570
0.0000
0.0000
car
0.1997
0.0303
0.0026
0.0114
0.7530
0.0029
clutter
0.4441
0.4339
0.0351
0.0092
0.0662
0.0115
Precision/Correctness
0.920
0.911
0.846
0.685
0.690
0.858
Recall/Completeness
0.938
0.952
0.640
0.957
0.753
0.011
F1
0.929
0.931
0.729
0.799
0.720
0.023

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_area29_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9606
0.0134
0.0168
0.0050
0.0041
0.0000
building
0.0263
0.9656
0.0055
0.0025
0.0000
0.0000
low_veg
0.0393
0.0083
0.6863
0.2658
0.0003
0.0000
tree
0.0025
0.0003
0.0243
0.9729
0.0000
0.0000
car
0.1070
0.0327
0.0012
0.0085
0.8464
0.0042
clutter
0.4248
0.4616
0.0266
0.0038
0.0708
0.0123
Precision/Correctness
0.942
0.932
0.886
0.724
0.699
0.874
Recall/Completeness
0.961
0.966
0.686
0.973
0.846
0.012
F1
0.951
0.949
0.773
0.830
0.766
0.024

Overall accuracy 0.899

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
0.9694
0.0120
0.0091
0.0031
0.0062
0.0002
building
0.0921
0.8928
0.0102
0.0012
0.0037
0.0000
low_veg
0.0526
0.0033
0.9077
0.0362
0.0002
0.0000
tree
0.0387
0.0041
0.1071
0.8494
0.0008
0.0000
car
0.1289
0.1655
0.0110
0.0040
0.6904
0.0002
clutter
0.3834
0.3832
0.0434
0.0061
0.1016
0.0824
Precision/Correctness
0.872
0.910
0.869
0.930
0.781
0.970
Recall/Completeness
0.969
0.893
0.908
0.849
0.690
0.082
F1
0.918
0.901
0.888
0.888
0.733
0.152

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_area31_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9822
0.0085
0.0062
0.0005
0.0025
0.0001
building
0.0803
0.9116
0.0049
0.0001
0.0032
0.0000
low_veg
0.0320
0.0007
0.9380
0.0292
0.0000
0.0000
tree
0.0145
0.0007
0.0854
0.8993
0.0002
0.0000
car
0.0513
0.1796
0.0059
0.0012
0.7620
0.0001
clutter
0.3240
0.4266
0.0429
0.0011
0.1097
0.0956
Precision/Correctness
0.903
0.925
0.906
0.955
0.808
0.980
Recall/Completeness
0.982
0.912
0.938
0.899
0.762
0.096
F1
0.941
0.918
0.922
0.926
0.784
0.174

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
0.9686
0.0207
0.0057
0.0027
0.0018
0.0005
building
0.0792
0.8392
0.0720
0.0058
0.0031
0.0007
low_veg
0.0697
0.0251
0.8131
0.0914
0.0007
0.0000
tree
0.0395
0.0078
0.1379
0.8147
0.0000
0.0001
car
0.2884
0.0232
0.0007
0.0035
0.6841
0.0000
clutter
0.4506
0.1149
0.0028
0.0013
0.0429
0.3875
Precision/Correctness
0.850
0.927
0.769
0.835
0.687
0.980
Recall/Completeness
0.969
0.839
0.813
0.815
0.684
0.387
F1
0.905
0.881
0.790
0.825
0.686
0.555

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_area33_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9798
0.0164
0.0024
0.0005
0.0009
0.0000
building
0.0725
0.8482
0.0712
0.0045
0.0029
0.0006
low_veg
0.0379
0.0152
0.8543
0.0919
0.0007
0.0000
tree
0.0149
0.0032
0.1266
0.8553
0.0000
0.0000
car
0.1804
0.0173
0.0001
0.0016
0.8006
0.0000
clutter
0.4053
0.1190
0.0027
0.0003
0.0467
0.4260
Precision/Correctness
0.881
0.944
0.785
0.850
0.683
0.991
Recall/Completeness
0.980
0.848
0.854
0.855
0.801
0.426
F1
0.928
0.894
0.818
0.853
0.737
0.596

Overall accuracy 0.879

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
0.8777
0.0512
0.0544
0.0153
0.0014
0.0000
building
0.0410
0.9413
0.0131
0.0040
0.0006
0.0000
low_veg
0.0652
0.0153
0.6929
0.2264
0.0002
0.0000
tree
0.0299
0.0058
0.1216
0.8426
0.0001
0.0000
car
0.2668
0.0073
0.0018
0.0084
0.7157
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.859
0.933
0.790
0.764
0.903
--
Recall/Completeness
0.878
0.941
0.693
0.843
0.716
--
F1
0.868
0.937
0.738
0.801
0.799
--

Overall accuracy 0.840

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area35_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9163
0.0459
0.0341
0.0034
0.0003
0.0000
building
0.0296
0.9645
0.0047
0.0007
0.0006
0.0000
low_veg
0.0487
0.0068
0.7208
0.2235
0.0002
0.0000
tree
0.0094
0.0012
0.0916
0.8978
0.0000
0.0000
car
0.1596
0.0068
0.0000
0.0035
0.8301
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.906
0.953
0.852
0.786
0.944
--
Recall/Completeness
0.916
0.964
0.721
0.898
0.830
--
F1
0.911
0.959
0.781
0.838
0.884
--

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_area38_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9080
0.0306
0.0431
0.0150
0.0033
0.0000
building
0.0401
0.9035
0.0509
0.0040
0.0016
0.0000
low_veg
0.0476
0.0397
0.8139
0.0982
0.0007
0.0000
tree
0.0212
0.0044
0.1106
0.8636
0.0001
0.0000
car
0.2054
0.0410
0.0266
0.0070
0.7199
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.892
0.917
0.831
0.838
0.824
--
Recall/Completeness
0.908
0.903
0.814
0.864
0.720
--
F1
0.900
0.910
0.822
0.851
0.769
--

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_area38_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9339
0.0287
0.0303
0.0054
0.0016
0.0000
building
0.0326
0.9264
0.0380
0.0016
0.0014
0.0000
low_veg
0.0307
0.0376
0.8487
0.0825
0.0006
0.0000
tree
0.0074
0.0015
0.0893
0.9017
0.0000
0.0000
car
0.1052
0.0485
0.0142
0.0020
0.8301
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.929
0.929
0.869
0.874
0.863
--
Recall/Completeness
0.934
0.926
0.849
0.902
0.830
--
F1
0.931
0.928
0.859
0.888
0.846
--

Overall accuracy 0.902

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image