Detailled semantic labeling (2D) result


Name H. Li et al.
Affiliation Chinese Academy of Sciences, China
Abbreviation CAS_L2
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
0.913
0.028
0.038
0.017
0.004
0.000
building
0.065
0.905
0.024
0.006
0.001
0.000
low_veg
0.069
0.026
0.759
0.147
0.000
0.000
tree
0.022
0.004
0.092
0.882
0.000
0.000
car
0.244
0.059
0.010
0.005
0.682
0.001
clutter
0.330
0.281
0.015
0.009
0.039
0.327
Precision/Correctness
0.856
0.931
0.813
0.840
0.825
0.942
Recall/Completeness
0.913
0.905
0.759
0.882
0.682
0.327
F1
0.884
0.917
0.785
0.861
0.746
0.486

Overall accuracy 0.862

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
0.938
0.022
0.030
0.008
0.003
0.000
building
0.056
0.923
0.018
0.002
0.001
0.000
low_veg
0.056
0.018
0.793
0.131
0.000
0.000
tree
0.011
0.002
0.075
0.913
0.000
0.000
car
0.133
0.068
0.006
0.002
0.790
0.001
clutter
0.289
0.298
0.012
0.003
0.040
0.358
Precision/Correctness
0.887
0.949
0.848
0.870
0.850
0.955
Recall/Completeness
0.938
0.923
0.793
0.913
0.790
0.358
F1
0.912
0.936
0.820
0.891
0.819
0.521

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

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9486
0.0117
0.0235
0.0115
0.0047
0.0000
building
0.0514
0.9210
0.0224
0.0049
0.0003
0.0000
low_veg
0.1028
0.0148
0.6967
0.1857
0.0001
0.0000
tree
0.0331
0.0028
0.1025
0.8606
0.0001
0.0009
car
0.2882
0.0077
0.0018
0.0019
0.7004
0.0000
clutter
0.0384
0.0000
0.0005
0.0191
0.0000
0.9420
Precision/Correctness
0.825
0.966
0.824
0.810
0.894
0.987
Recall/Completeness
0.949
0.921
0.697
0.861
0.700
0.942
F1
0.883
0.943
0.755
0.835
0.785
0.964

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_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9713
0.0088
0.0133
0.0032
0.0035
0.0000
building
0.0405
0.9443
0.0138
0.0012
0.0003
0.0000
low_veg
0.0869
0.0080
0.7252
0.1797
0.0001
0.0000
tree
0.0168
0.0009
0.0892
0.8926
0.0000
0.0004
car
0.1511
0.0074
0.0011
0.0011
0.8393
0.0000
clutter
0.0380
0.0000
0.0004
0.0043
0.0000
0.9573
Precision/Correctness
0.866
0.981
0.858
0.834
0.913
0.994
Recall/Completeness
0.971
0.944
0.725
0.893
0.839
0.957
F1
0.915
0.962
0.786
0.862
0.875
0.975

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
0.9446
0.0350
0.0102
0.0050
0.0051
0.0000
building
0.0809
0.9089
0.0078
0.0013
0.0011
0.0000
low_veg
0.1752
0.0520
0.5120
0.2600
0.0008
0.0000
tree
0.0525
0.0119
0.1192
0.8162
0.0002
0.0000
car
0.2850
0.0292
0.0010
0.0030
0.6819
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.821
0.974
0.636
0.739
0.821
--
Recall/Completeness
0.945
0.909
0.512
0.816
0.682
--
F1
0.879
0.940
0.567
0.776
0.745
--

Overall accuracy 0.893

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area4_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9701
0.0177
0.0070
0.0019
0.0032
0.0000
building
0.0668
0.9251
0.0066
0.0005
0.0011
0.0000
low_veg
0.1382
0.0282
0.5465
0.2867
0.0003
0.0000
tree
0.0232
0.0047
0.1151
0.8570
0.0000
0.0000
car
0.1782
0.0267
0.0000
0.0016
0.7935
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.852
0.988
0.660
0.766
0.847
--
Recall/Completeness
0.970
0.925
0.546
0.857
0.794
--
F1
0.908
0.955
0.598
0.809
0.819
--

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_area6_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9144
0.0416
0.0271
0.0095
0.0075
0.0000
building
0.0748
0.9071
0.0139
0.0035
0.0004
0.0002
low_veg
0.1034
0.0188
0.7253
0.1517
0.0008
0.0000
tree
0.0176
0.0029
0.0549
0.9243
0.0003
0.0000
car
0.2611
0.0154
0.0021
0.0014
0.7199
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.838
0.956
0.739
0.931
0.842
--
Recall/Completeness
0.914
0.907
0.725
0.924
0.720
--
F1
0.874
0.931
0.732
0.928
0.776
--

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_area6_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9476
0.0280
0.0177
0.0025
0.0043
0.0000
building
0.0647
0.9251
0.0085
0.0011
0.0003
0.0003
low_veg
0.0842
0.0079
0.7753
0.1321
0.0005
0.0000
tree
0.0070
0.0006
0.0413
0.9510
0.0001
0.0000
car
0.1573
0.0104
0.0008
0.0002
0.8312
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.873
0.975
0.794
0.953
0.891
--
Recall/Completeness
0.948
0.925
0.775
0.951
0.831
--
F1
0.909
0.950
0.784
0.952
0.860
--

Overall accuracy 0.923

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
0.8965
0.0297
0.0597
0.0095
0.0037
0.0009
building
0.0471
0.9297
0.0186
0.0041
0.0006
0.0000
low_veg
0.0639
0.0127
0.8665
0.0563
0.0006
0.0000
tree
0.0268
0.0044
0.0823
0.8864
0.0001
0.0001
car
0.2698
0.0159
0.0141
0.0021
0.6981
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.891
0.942
0.799
0.934
0.891
--
Recall/Completeness
0.896
0.930
0.866
0.886
0.698
--
F1
0.894
0.936
0.831
0.909
0.783
--

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_area8_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9213
0.0236
0.0495
0.0026
0.0022
0.0008
building
0.0358
0.9504
0.0114
0.0018
0.0006
0.0000
low_veg
0.0473
0.0052
0.9026
0.0445
0.0005
0.0000
tree
0.0114
0.0015
0.0607
0.9263
0.0000
0.0000
car
0.1430
0.0160
0.0083
0.0007
0.8320
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.928
0.962
0.842
0.957
0.921
--
Recall/Completeness
0.921
0.950
0.903
0.926
0.832
--
F1
0.925
0.956
0.871
0.942
0.874
--

Overall accuracy 0.925

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area10_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8634
0.0656
0.0463
0.0194
0.0036
0.0016
building
0.0450
0.9249
0.0191
0.0105
0.0005
0.0000
low_veg
0.0923
0.0287
0.7288
0.1498
0.0003
0.0000
tree
0.0149
0.0071
0.0678
0.9101
0.0000
0.0000
car
0.2646
0.0071
0.0009
0.0009
0.7265
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.911
0.875
0.781
0.838
0.770
--
Recall/Completeness
0.863
0.925
0.729
0.910
0.727
--
F1
0.886
0.899
0.754
0.873
0.748
--

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_area10_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8945
0.0547
0.0379
0.0084
0.0027
0.0017
building
0.0382
0.9394
0.0149
0.0071
0.0004
0.0000
low_veg
0.0887
0.0163
0.7724
0.1222
0.0003
0.0000
tree
0.0068
0.0032
0.0478
0.9422
0.0000
0.0000
car
0.1552
0.0082
0.0005
0.0000
0.8360
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.929
0.903
0.825
0.880
0.789
--
Recall/Completeness
0.895
0.939
0.772
0.942
0.836
--
F1
0.911
0.921
0.798
0.910
0.812
--

Overall accuracy 0.894

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
0.8935
0.0264
0.0474
0.0304
0.0023
0.0000
building
0.1007
0.8744
0.0165
0.0085
0.0000
0.0000
low_veg
0.0416
0.0219
0.7602
0.1763
0.0001
0.0000
tree
0.0093
0.0049
0.1018
0.8840
0.0000
0.0000
car
0.2130
0.0018
0.0170
0.0114
0.7568
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.780
0.933
0.822
0.851
0.916
--
Recall/Completeness
0.894
0.874
0.760
0.884
0.757
--
F1
0.833
0.903
0.790
0.867
0.829
--

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_area12_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9214
0.0241
0.0379
0.0158
0.0008
0.0000
building
0.1041
0.8846
0.0084
0.0029
0.0000
0.0000
low_veg
0.0389
0.0136
0.7967
0.1508
0.0000
0.0000
tree
0.0046
0.0018
0.0844
0.9092
0.0000
0.0000
car
0.0818
0.0027
0.0147
0.0053
0.8955
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.798
0.956
0.854
0.881
0.965
--
Recall/Completeness
0.921
0.885
0.797
0.909
0.896
--
F1
0.855
0.919
0.824
0.895
0.929
--

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_area14_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8548
0.0328
0.0790
0.0281
0.0052
0.0000
building
0.0166
0.9614
0.0149
0.0070
0.0000
0.0001
low_veg
0.1083
0.0486
0.6933
0.1482
0.0015
0.0001
tree
0.0300
0.0114
0.1249
0.8337
0.0000
0.0000
car
0.1502
0.0000
0.0033
0.0048
0.8418
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.827
0.877
0.738
0.860
0.584
--
Recall/Completeness
0.855
0.961
0.693
0.834
0.842
--
F1
0.841
0.917
0.715
0.847
0.690
--

Overall accuracy 0.825

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
0.8752
0.0282
0.0743
0.0176
0.0047
0.0000
building
0.0109
0.9780
0.0083
0.0027
0.0000
0.0001
low_veg
0.1039
0.0325
0.7244
0.1376
0.0016
0.0001
tree
0.0217
0.0051
0.1128
0.8605
0.0000
0.0000
car
0.0426
0.0000
0.0012
0.0009
0.9553
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.853
0.912
0.760
0.882
0.559
--
Recall/Completeness
0.875
0.978
0.724
0.860
0.955
--
F1
0.864
0.944
0.742
0.871
0.705
--

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_area16_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8109
0.0318
0.1023
0.0524
0.0026
0.0000
building
0.0391
0.9184
0.0303
0.0118
0.0004
0.0000
low_veg
0.0271
0.0242
0.8227
0.1252
0.0008
0.0000
tree
0.0195
0.0047
0.0983
0.8775
0.0000
0.0000
car
0.1651
0.0013
0.0627
0.0078
0.7631
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.848
0.922
0.810
0.872
0.701
--
Recall/Completeness
0.811
0.918
0.823
0.878
0.763
--
F1
0.829
0.920
0.816
0.875
0.731
--

Overall accuracy 0.858

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
0.8461
0.0276
0.0915
0.0334
0.0013
0.0000
building
0.0356
0.9402
0.0194
0.0044
0.0003
0.0000
low_veg
0.0229
0.0190
0.8484
0.1088
0.0008
0.0000
tree
0.0122
0.0019
0.0835
0.9024
0.0000
0.0000
car
0.0875
0.0000
0.0550
0.0001
0.8574
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.878
0.941
0.840
0.897
0.736
--
Recall/Completeness
0.846
0.940
0.848
0.902
0.857
--
F1
0.862
0.941
0.844
0.900
0.792
--

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_area20_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8568
0.0408
0.0537
0.0457
0.0030
0.0000
building
0.0163
0.9528
0.0236
0.0073
0.0000
0.0000
low_veg
0.0584
0.0294
0.7341
0.1778
0.0003
0.0000
tree
0.0074
0.0015
0.0516
0.9395
0.0000
0.0000
car
0.1571
0.0096
0.0186
0.0150
0.7997
0.0000
clutter
0.2042
0.7632
0.0314
0.0013
0.0000
0.0000
Precision/Correctness
0.882
0.816
0.794
0.896
0.833
0.000
Recall/Completeness
0.857
0.953
0.734
0.939
0.800
0.000
F1
0.869
0.879
0.763
0.917
0.816
-nan

Overall accuracy 0.859

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area20_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8885
0.0337
0.0488
0.0276
0.0013
0.0000
building
0.0129
0.9653
0.0194
0.0024
0.0000
0.0000
low_veg
0.0518
0.0194
0.7807
0.1478
0.0003
0.0000
tree
0.0030
0.0001
0.0391
0.9577
0.0000
0.0000
car
0.0630
0.0096
0.0040
0.0085
0.9150
0.0000
clutter
0.2022
0.7711
0.0261
0.0005
0.0000
0.0000
Precision/Correctness
0.904
0.833
0.827
0.923
0.893
0.000
Recall/Completeness
0.888
0.965
0.781
0.958
0.915
0.000
F1
0.896
0.894
0.803
0.940
0.904
-nan

Overall accuracy 0.885

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area22_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9000
0.0205
0.0415
0.0331
0.0050
0.0000
building
0.0422
0.9395
0.0102
0.0074
0.0008
0.0000
low_veg
0.1100
0.0277
0.7009
0.1577
0.0008
0.0030
tree
0.0215
0.0028
0.0535
0.9221
0.0000
0.0000
car
0.2378
0.0034
0.0099
0.0128
0.7361
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.882
0.928
0.822
0.858
0.811
--
Recall/Completeness
0.900
0.939
0.701
0.922
0.736
--
F1
0.891
0.934
0.757
0.889
0.772
--

Overall accuracy 0.871

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
0.9318
0.0141
0.0346
0.0163
0.0031
0.0000
building
0.0332
0.9589
0.0037
0.0034
0.0007
0.0000
low_veg
0.1077
0.0147
0.7451
0.1286
0.0006
0.0034
tree
0.0090
0.0008
0.0377
0.9525
0.0000
0.0000
car
0.1237
0.0026
0.0078
0.0040
0.8620
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.908
0.958
0.865
0.898
0.848
--
Recall/Completeness
0.932
0.959
0.745
0.953
0.862
--
F1
0.920
0.958
0.800
0.924
0.855
--

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
0.8208
0.0326
0.0981
0.0419
0.0065
0.0000
building
0.0697
0.8646
0.0549
0.0108
0.0000
0.0000
low_veg
0.0246
0.0659
0.8199
0.0894
0.0002
0.0000
tree
0.0172
0.0064
0.1389
0.8374
0.0000
0.0000
car
0.1885
0.0000
0.0048
0.0058
0.8009
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.809
0.829
0.849
0.826
0.741
--
Recall/Completeness
0.821
0.865
0.820
0.837
0.801
--
F1
0.815
0.847
0.834
0.831
0.770
--

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_area24_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8518
0.0233
0.0894
0.0306
0.0050
0.0000
building
0.0660
0.8766
0.0503
0.0070
0.0000
0.0000
low_veg
0.0210
0.0635
0.8372
0.0780
0.0002
0.0000
tree
0.0111
0.0029
0.1175
0.8684
0.0000
0.0000
car
0.0858
0.0000
0.0000
0.0025
0.9117
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.833
0.846
0.871
0.850
0.750
--
Recall/Completeness
0.852
0.877
0.837
0.868
0.912
--
F1
0.842
0.861
0.854
0.859
0.823
--

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_area27_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9438
0.0223
0.0208
0.0071
0.0061
0.0000
building
0.0938
0.8776
0.0240
0.0044
0.0002
0.0000
low_veg
0.1004
0.0220
0.6812
0.1959
0.0006
0.0000
tree
0.0135
0.0036
0.0526
0.9300
0.0001
0.0001
car
0.2745
0.0149
0.0054
0.0055
0.6997
0.0000
clutter
0.6168
0.1732
0.1089
0.0028
0.0982
0.0000
Precision/Correctness
0.824
0.960
0.865
0.688
0.906
0.000
Recall/Completeness
0.944
0.878
0.681
0.930
0.700
0.000
F1
0.880
0.917
0.762
0.791
0.789
-nan

Overall accuracy 0.858

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
0.9672
0.0143
0.0138
0.0027
0.0020
0.0000
building
0.0808
0.8991
0.0183
0.0016
0.0002
0.0000
low_veg
0.0817
0.0123
0.7214
0.1841
0.0005
0.0000
tree
0.0058
0.0008
0.0371
0.9562
0.0000
0.0000
car
0.1592
0.0161
0.0039
0.0036
0.8172
0.0000
clutter
0.6432
0.1477
0.0849
0.0003
0.1240
0.0000
Precision/Correctness
0.859
0.977
0.901
0.720
0.951
0.000
Recall/Completeness
0.967
0.899
0.721
0.956
0.817
0.000
F1
0.910
0.937
0.801
0.821
0.879
-nan

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_area29_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9484
0.0127
0.0192
0.0154
0.0043
0.0000
building
0.0388
0.9421
0.0108
0.0080
0.0003
0.0000
low_veg
0.0763
0.0199
0.5988
0.3047
0.0003
0.0000
tree
0.0058
0.0023
0.0292
0.9626
0.0000
0.0000
car
0.2335
0.0201
0.0116
0.0118
0.7156
0.0074
clutter
0.4320
0.4249
0.0190
0.0142
0.0437
0.0662
Precision/Correctness
0.913
0.923
0.855
0.660
0.746
0.950
Recall/Completeness
0.948
0.942
0.599
0.963
0.716
0.066
F1
0.930
0.932
0.704
0.783
0.731
0.124

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_area29_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9696
0.0068
0.0132
0.0073
0.0032
0.0000
building
0.0325
0.9566
0.0064
0.0042
0.0003
0.0000
low_veg
0.0551
0.0099
0.6426
0.2922
0.0002
0.0000
tree
0.0026
0.0004
0.0224
0.9746
0.0000
0.0000
car
0.1293
0.0216
0.0116
0.0093
0.8183
0.0100
clutter
0.4004
0.4534
0.0130
0.0067
0.0476
0.0789
Precision/Correctness
0.935
0.941
0.895
0.699
0.753
0.952
Recall/Completeness
0.970
0.957
0.643
0.975
0.818
0.079
F1
0.952
0.949
0.748
0.814
0.784
0.146

Overall accuracy 0.896

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area31_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9658
0.0127
0.0117
0.0038
0.0053
0.0007
building
0.1239
0.8638
0.0078
0.0024
0.0017
0.0004
low_veg
0.0555
0.0033
0.9069
0.0334
0.0004
0.0005
tree
0.0391
0.0023
0.0856
0.8725
0.0005
0.0000
car
0.1567
0.2884
0.0110
0.0047
0.5392
0.0000
clutter
0.3959
0.2830
0.0166
0.0118
0.0999
0.1929
Precision/Correctness
0.851
0.903
0.886
0.928
0.764
0.930
Recall/Completeness
0.966
0.864
0.907
0.872
0.539
0.193
F1
0.905
0.883
0.896
0.900
0.632
0.320

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_area31_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9789
0.0086
0.0090
0.0005
0.0027
0.0002
building
0.1127
0.8815
0.0038
0.0003
0.0014
0.0003
low_veg
0.0364
0.0011
0.9362
0.0262
0.0002
0.0000
tree
0.0148
0.0002
0.0660
0.9189
0.0000
0.0000
car
0.0728
0.3245
0.0049
0.0013
0.5965
0.0000
clutter
0.3372
0.3183
0.0168
0.0046
0.1098
0.2134
Precision/Correctness
0.880
0.919
0.918
0.958
0.781
0.977
Recall/Completeness
0.979
0.882
0.936
0.919
0.597
0.213
F1
0.927
0.900
0.927
0.938
0.676
0.350

Overall accuracy 0.903

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
0.9785
0.0102
0.0060
0.0026
0.0017
0.0010
building
0.0994
0.7958
0.0972
0.0034
0.0033
0.0009
low_veg
0.0726
0.0117
0.8048
0.1101
0.0008
0.0000
tree
0.0471
0.0043
0.1400
0.8085
0.0000
0.0001
car
0.3058
0.0081
0.0043
0.0016
0.6781
0.0020
clutter
0.4209
0.0921
0.0030
0.0016
0.0263
0.4561
Precision/Correctness
0.840
0.954
0.732
0.816
0.734
0.973
Recall/Completeness
0.979
0.796
0.805
0.808
0.678
0.456
F1
0.904
0.868
0.767
0.812
0.705
0.621

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_area33_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9888
0.0077
0.0018
0.0006
0.0009
0.0001
building
0.0897
0.8087
0.0962
0.0014
0.0031
0.0009
low_veg
0.0413
0.0062
0.8362
0.1156
0.0007
0.0000
tree
0.0204
0.0030
0.1268
0.8498
0.0000
0.0000
car
0.1916
0.0069
0.0011
0.0004
0.7974
0.0025
clutter
0.3710
0.0974
0.0012
0.0006
0.0286
0.5013
Precision/Correctness
0.872
0.964
0.748
0.827
0.737
0.986
Recall/Completeness
0.989
0.809
0.836
0.850
0.797
0.501
F1
0.927
0.879
0.789
0.838
0.766
0.665

Overall accuracy 0.871

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
0.8843
0.0422
0.0551
0.0176
0.0008
0.0000
building
0.0506
0.9267
0.0164
0.0058
0.0006
0.0000
low_veg
0.0707
0.0089
0.6778
0.2425
0.0000
0.0000
tree
0.0350
0.0040
0.1150
0.8459
0.0001
0.0001
car
0.3126
0.0040
0.0009
0.0063
0.6763
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.842
0.947
0.789
0.750
0.930
--
Recall/Completeness
0.884
0.927
0.678
0.846
0.676
--
F1
0.863
0.937
0.729
0.795
0.783
--

Overall accuracy 0.834

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
0.9192
0.0397
0.0364
0.0047
0.0001
0.0000
building
0.0356
0.9563
0.0066
0.0009
0.0006
0.0000
low_veg
0.0518
0.0038
0.7059
0.2385
0.0000
0.0000
tree
0.0111
0.0008
0.0890
0.8990
0.0000
0.0000
car
0.1757
0.0029
0.0002
0.0016
0.8196
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.896
0.961
0.847
0.774
0.959
--
Recall/Completeness
0.919
0.956
0.706
0.899
0.820
--
F1
0.907
0.959
0.770
0.832
0.884
--

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: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9104
0.0277
0.0442
0.0134
0.0040
0.0003
building
0.0432
0.9079
0.0411
0.0061
0.0017
0.0000
low_veg
0.0502
0.0165
0.8373
0.0958
0.0002
0.0000
tree
0.0234
0.0027
0.1223
0.8514
0.0002
0.0000
car
0.2260
0.0419
0.0399
0.0060
0.6860
0.0003
clutter
--
--
--
--
--
--
Precision/Correctness
0.885
0.947
0.834
0.838
0.805
--
Recall/Completeness
0.910
0.908
0.837
0.851
0.686
--
F1
0.897
0.927
0.836
0.845
0.741
--

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: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9368
0.0260
0.0299
0.0043
0.0028
0.0003
building
0.0353
0.9345
0.0263
0.0024
0.0015
0.0000
low_veg
0.0357
0.0126
0.8716
0.0800
0.0002
0.0000
tree
0.0093
0.0009
0.0988
0.8909
0.0002
0.0000
car
0.1173
0.0512
0.0286
0.0016
0.8012
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.920
0.957
0.877
0.876
0.825
--
Recall/Completeness
0.937
0.934
0.872
0.891
0.801
--
F1
0.928
0.946
0.874
0.883
0.813
--

Overall accuracy 0.909

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image