Detailled semantic labeling (2D) result


Name H. Li et al.
Affiliation Chinese Academy of Sciences, China
Abbreviation CAS_L3
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
0.916
0.035
0.030
0.016
0.003
0.000
building
0.063
0.912
0.019
0.005
0.001
0.000
low_veg
0.080
0.029
0.719
0.171
0.000
0.000
tree
0.027
0.006
0.071
0.896
0.000
0.000
car
0.276
0.036
0.007
0.005
0.676
0.001
clutter
0.347
0.339
0.020
0.007
0.032
0.256
Precision/Correctness
0.846
0.919
0.841
0.825
0.850
0.961
Recall/Completeness
0.916
0.912
0.719
0.896
0.676
0.256
F1
0.880
0.915
0.775
0.859
0.753
0.405

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
0.938
0.028
0.025
0.008
0.002
0.000
building
0.054
0.928
0.014
0.003
0.001
0.000
low_veg
0.064
0.020
0.760
0.156
0.000
0.000
tree
0.013
0.002
0.057
0.927
0.000
0.000
car
0.155
0.040
0.004
0.002
0.798
0.001
clutter
0.304
0.359
0.017
0.002
0.033
0.284
Precision/Correctness
0.881
0.940
0.872
0.854
0.874
0.970
Recall/Completeness
0.938
0.928
0.760
0.927
0.798
0.284
F1
0.908
0.934
0.812
0.889
0.834
0.440

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
0.9538
0.0163
0.0129
0.0120
0.0049
0.0000
building
0.0501
0.9296
0.0152
0.0040
0.0011
0.0000
low_veg
0.0970
0.0255
0.6556
0.2217
0.0001
0.0001
tree
0.0323
0.0057
0.0692
0.8918
0.0000
0.0010
car
0.2645
0.0203
0.0000
0.0011
0.7141
0.0000
clutter
0.0048
0.0000
0.0000
0.0212
0.0000
0.9740
Precision/Correctness
0.834
0.947
0.871
0.790
0.880
0.986
Recall/Completeness
0.954
0.930
0.656
0.892
0.714
0.974
F1
0.890
0.938
0.748
0.838
0.788
0.980

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_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9742
0.0118
0.0070
0.0032
0.0038
0.0000
building
0.0407
0.9472
0.0099
0.0010
0.0011
0.0000
low_veg
0.0769
0.0148
0.6925
0.2155
0.0001
0.0001
tree
0.0153
0.0026
0.0598
0.9218
0.0000
0.0004
car
0.1280
0.0156
0.0000
0.0003
0.8560
0.0000
clutter
0.0045
0.0000
0.0000
0.0071
0.0000
0.9884
Precision/Correctness
0.878
0.968
0.897
0.813
0.892
0.994
Recall/Completeness
0.974
0.947
0.693
0.922
0.856
0.988
F1
0.923
0.958
0.782
0.864
0.874
0.991

Overall accuracy 0.886

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area4_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9404
0.0447
0.0065
0.0046
0.0037
0.0000
building
0.0780
0.9144
0.0055
0.0014
0.0008
0.0000
low_veg
0.2192
0.0714
0.4283
0.2799
0.0012
0.0000
tree
0.0666
0.0105
0.0635
0.8592
0.0002
0.0000
car
0.3670
0.0210
0.0006
0.0016
0.6098
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.816
0.968
0.704
0.738
0.849
--
Recall/Completeness
0.940
0.914
0.428
0.859
0.610
--
F1
0.874
0.940
0.533
0.794
0.710
--

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
0.9642
0.0269
0.0047
0.0018
0.0025
0.0000
building
0.0635
0.9304
0.0048
0.0005
0.0008
0.0000
low_veg
0.1747
0.0429
0.4711
0.3102
0.0011
0.0000
tree
0.0341
0.0019
0.0622
0.9018
0.0000
0.0000
car
0.2472
0.0164
0.0000
0.0007
0.7357
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.850
0.983
0.728
0.762
0.870
--
Recall/Completeness
0.964
0.930
0.471
0.902
0.736
--
F1
0.903
0.956
0.572
0.826
0.797
--

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
0.9208
0.0436
0.0235
0.0081
0.0039
0.0001
building
0.0798
0.9051
0.0116
0.0032
0.0003
0.0000
low_veg
0.1255
0.0241
0.6886
0.1614
0.0003
0.0000
tree
0.0212
0.0029
0.0480
0.9276
0.0002
0.0000
car
0.3381
0.0089
0.0004
0.0017
0.6509
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.820
0.953
0.756
0.929
0.901
--
Recall/Completeness
0.921
0.905
0.689
0.928
0.651
--
F1
0.868
0.929
0.721
0.928
0.756
--

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
0.9486
0.0310
0.0163
0.0018
0.0021
0.0001
building
0.0681
0.9238
0.0071
0.0008
0.0002
0.0000
low_veg
0.1046
0.0102
0.7422
0.1429
0.0001
0.0001
tree
0.0087
0.0007
0.0363
0.9543
0.0001
0.0000
car
0.2131
0.0056
0.0001
0.0002
0.7809
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.859
0.972
0.807
0.951
0.939
--
Recall/Completeness
0.949
0.924
0.742
0.954
0.781
--
F1
0.902
0.947
0.773
0.953
0.853
--

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
0.8959
0.0325
0.0598
0.0085
0.0033
0.0000
building
0.0503
0.9308
0.0142
0.0039
0.0008
0.0000
low_veg
0.0750
0.0150
0.8124
0.0969
0.0007
0.0000
tree
0.0322
0.0060
0.0653
0.8964
0.0001
0.0000
car
0.3146
0.0162
0.0113
0.0057
0.6523
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.877
0.935
0.808
0.904
0.891
--
Recall/Completeness
0.896
0.931
0.812
0.896
0.652
--
F1
0.886
0.933
0.810
0.900
0.753
--

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
0.9182
0.0266
0.0510
0.0023
0.0019
0.0000
building
0.0387
0.9511
0.0078
0.0016
0.0008
0.0000
low_veg
0.0550
0.0069
0.8520
0.0858
0.0003
0.0000
tree
0.0142
0.0023
0.0472
0.9363
0.0000
0.0000
car
0.1881
0.0167
0.0075
0.0040
0.7837
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.918
0.956
0.850
0.927
0.920
--
Recall/Completeness
0.918
0.951
0.852
0.936
0.784
--
F1
0.918
0.954
0.851
0.931
0.846
--

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
0.8345
0.1029
0.0401
0.0184
0.0041
0.0000
building
0.0390
0.9336
0.0167
0.0100
0.0007
0.0000
low_veg
0.1028
0.0394
0.6813
0.1763
0.0002
0.0000
tree
0.0210
0.0078
0.0607
0.9105
0.0001
0.0000
car
0.2203
0.0314
0.0121
0.0035
0.7328
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.904
0.823
0.792
0.823
0.746
--
Recall/Completeness
0.834
0.934
0.681
0.911
0.733
--
F1
0.868
0.875
0.732
0.864
0.739
--

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_area10_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8613
0.0936
0.0342
0.0078
0.0032
0.0000
building
0.0324
0.9465
0.0133
0.0072
0.0007
0.0000
low_veg
0.0976
0.0259
0.7295
0.1469
0.0002
0.0000
tree
0.0095
0.0035
0.0442
0.9428
0.0000
0.0000
car
0.1176
0.0377
0.0097
0.0004
0.8346
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.925
0.847
0.830
0.865
0.754
--
Recall/Completeness
0.861
0.946
0.729
0.943
0.835
--
F1
0.892
0.894
0.777
0.902
0.792
--

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_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9013
0.0363
0.0360
0.0240
0.0020
0.0004
building
0.0947
0.8900
0.0099
0.0054
0.0000
0.0000
low_veg
0.0621
0.0282
0.7094
0.1998
0.0002
0.0003
tree
0.0168
0.0067
0.0811
0.8954
0.0000
0.0000
car
0.2593
0.0005
0.0088
0.0063
0.7187
0.0064
clutter
--
--
--
--
--
--
Precision/Correctness
0.746
0.915
0.847
0.841
0.915
--
Recall/Completeness
0.901
0.890
0.709
0.895
0.719
--
F1
0.816
0.902
0.772
0.868
0.805
--

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_area12_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9238
0.0327
0.0309
0.0113
0.0009
0.0005
building
0.0965
0.8977
0.0045
0.0014
0.0000
0.0000
low_veg
0.0576
0.0171
0.7499
0.1749
0.0002
0.0004
tree
0.0095
0.0024
0.0667
0.9214
0.0000
0.0000
car
0.1028
0.0000
0.0068
0.0008
0.8801
0.0095
clutter
--
--
--
--
--
--
Precision/Correctness
0.772
0.944
0.876
0.869
0.951
--
Recall/Completeness
0.924
0.898
0.750
0.921
0.880
--
F1
0.841
0.920
0.808
0.895
0.914
--

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_area14_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8446
0.0328
0.0866
0.0315
0.0044
0.0000
building
0.0207
0.9581
0.0154
0.0058
0.0001
0.0000
low_veg
0.1018
0.0492
0.6849
0.1634
0.0006
0.0001
tree
0.0303
0.0119
0.1038
0.8539
0.0001
0.0000
car
0.1692
0.0000
0.0029
0.0028
0.8251
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.828
0.875
0.752
0.852
0.646
--
Recall/Completeness
0.845
0.958
0.685
0.854
0.825
--
F1
0.836
0.915
0.717
0.853
0.725
--

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_area14_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8630
0.0281
0.0843
0.0207
0.0039
0.0000
building
0.0153
0.9749
0.0079
0.0019
0.0001
0.0000
low_veg
0.0961
0.0340
0.7173
0.1519
0.0006
0.0001
tree
0.0213
0.0056
0.0924
0.8807
0.0000
0.0000
car
0.0495
0.0000
0.0012
0.0007
0.9486
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.856
0.909
0.773
0.874
0.637
--
Recall/Completeness
0.863
0.975
0.717
0.881
0.949
--
F1
0.860
0.941
0.744
0.877
0.762
--

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_area16_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8349
0.0333
0.0794
0.0508
0.0016
0.0000
building
0.0439
0.9112
0.0339
0.0109
0.0001
0.0000
low_veg
0.0289
0.0173
0.8021
0.1505
0.0001
0.0012
tree
0.0304
0.0049
0.0945
0.8700
0.0001
0.0000
car
0.2180
0.0008
0.0217
0.0038
0.7557
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.822
0.931
0.818
0.854
0.830
--
Recall/Completeness
0.835
0.911
0.802
0.870
0.756
--
F1
0.828
0.921
0.810
0.862
0.791
--

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: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8665
0.0286
0.0733
0.0310
0.0006
0.0000
building
0.0404
0.9305
0.0239
0.0052
0.0001
0.0000
low_veg
0.0231
0.0107
0.8296
0.1352
0.0001
0.0013
tree
0.0217
0.0018
0.0822
0.8942
0.0001
0.0000
car
0.1266
0.0000
0.0143
0.0001
0.8589
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.854
0.953
0.844
0.878
0.883
--
Recall/Completeness
0.866
0.931
0.830
0.894
0.859
--
F1
0.860
0.942
0.837
0.886
0.871
--

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_area20_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8647
0.0465
0.0393
0.0470
0.0026
0.0000
building
0.0293
0.9524
0.0117
0.0066
0.0000
0.0000
low_veg
0.0649
0.0342
0.7060
0.1946
0.0003
0.0000
tree
0.0096
0.0021
0.0417
0.9466
0.0000
0.0000
car
0.1483
0.0126
0.0122
0.0155
0.8113
0.0000
clutter
0.0459
0.9499
0.0018
0.0024
0.0000
0.0000
Precision/Correctness
0.883
0.785
0.835
0.889
0.855
0.000
Recall/Completeness
0.865
0.952
0.706
0.947
0.811
0.000
F1
0.874
0.861
0.765
0.917
0.833
-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_area20_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8958
0.0375
0.0376
0.0281
0.0010
0.0000
building
0.0260
0.9635
0.0084
0.0021
0.0000
0.0000
low_veg
0.0582
0.0226
0.7544
0.1646
0.0003
0.0000
tree
0.0042
0.0004
0.0309
0.9645
0.0000
0.0000
car
0.0498
0.0109
0.0019
0.0075
0.9300
0.0000
clutter
0.0438
0.9533
0.0013
0.0016
0.0000
0.0000
Precision/Correctness
0.908
0.805
0.864
0.917
0.916
0.000
Recall/Completeness
0.896
0.964
0.754
0.965
0.930
0.000
F1
0.902
0.877
0.806
0.940
0.923
-nan

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_area22_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9174
0.0203
0.0279
0.0300
0.0043
0.0000
building
0.0521
0.9317
0.0100
0.0056
0.0006
0.0000
low_veg
0.1120
0.0397
0.6810
0.1668
0.0004
0.0000
tree
0.0288
0.0037
0.0447
0.9228
0.0000
0.0000
car
0.2583
0.0102
0.0124
0.0114
0.7077
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.872
0.914
0.853
0.857
0.830
--
Recall/Completeness
0.917
0.932
0.681
0.923
0.708
--
F1
0.894
0.923
0.757
0.889
0.764
--

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
0.9464
0.0129
0.0237
0.0144
0.0026
0.0000
building
0.0451
0.9474
0.0046
0.0023
0.0006
0.0000
low_veg
0.1067
0.0264
0.7306
0.1360
0.0003
0.0000
tree
0.0137
0.0010
0.0311
0.9542
0.0000
0.0000
car
0.1468
0.0123
0.0085
0.0031
0.8294
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.900
0.947
0.891
0.896
0.868
--
Recall/Completeness
0.946
0.947
0.731
0.954
0.829
--
F1
0.923
0.947
0.803
0.924
0.848
--

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
0.8430
0.0428
0.0710
0.0388
0.0044
0.0000
building
0.0755
0.8654
0.0428
0.0163
0.0001
0.0000
low_veg
0.0320
0.0247
0.8246
0.1185
0.0002
0.0000
tree
0.0187
0.0067
0.1070
0.8675
0.0000
0.0000
car
0.2866
0.0000
0.0040
0.0049
0.7045
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.787
0.900
0.882
0.793
0.777
--
Recall/Completeness
0.843
0.865
0.825
0.868
0.704
--
F1
0.814
0.882
0.852
0.829
0.739
--

Overall accuracy 0.845

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area24_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8717
0.0317
0.0661
0.0270
0.0036
0.0000
building
0.0730
0.8752
0.0384
0.0133
0.0001
0.0000
low_veg
0.0279
0.0195
0.8476
0.1047
0.0002
0.0000
tree
0.0117
0.0029
0.0900
0.8953
0.0000
0.0000
car
0.1569
0.0000
0.0005
0.0010
0.8416
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.811
0.926
0.900
0.817
0.783
--
Recall/Completeness
0.872
0.875
0.848
0.895
0.842
--
F1
0.841
0.900
0.873
0.854
0.811
--

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: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9423
0.0313
0.0152
0.0060
0.0052
0.0000
building
0.0873
0.8909
0.0160
0.0049
0.0010
0.0000
low_veg
0.1197
0.0311
0.6215
0.2271
0.0007
0.0000
tree
0.0172
0.0052
0.0430
0.9344
0.0001
0.0000
car
0.3007
0.0092
0.0026
0.0050
0.6825
0.0000
clutter
0.5977
0.2570
0.0807
0.0033
0.0614
0.0000
Precision/Correctness
0.818
0.947
0.890
0.660
0.907
0.000
Recall/Completeness
0.942
0.891
0.621
0.934
0.683
0.000
F1
0.876
0.918
0.732
0.774
0.779
-nan

Overall accuracy 0.850

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area27_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9639
0.0222
0.0099
0.0022
0.0018
0.0000
building
0.0751
0.9094
0.0122
0.0024
0.0009
0.0000
low_veg
0.0976
0.0180
0.6661
0.2177
0.0006
0.0000
tree
0.0074
0.0018
0.0299
0.9608
0.0000
0.0000
car
0.1751
0.0072
0.0012
0.0046
0.8119
0.0000
clutter
0.5720
0.2977
0.0532
0.0020
0.0751
0.0000
Precision/Correctness
0.855
0.967
0.922
0.686
0.944
0.000
Recall/Completeness
0.964
0.909
0.666
0.961
0.812
0.000
F1
0.906
0.937
0.773
0.801
0.873
-nan

Overall accuracy 0.881

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
0.9468
0.0202
0.0159
0.0130
0.0040
0.0000
building
0.0317
0.9537
0.0080
0.0065
0.0000
0.0000
low_veg
0.0869
0.0224
0.5589
0.3312
0.0005
0.0000
tree
0.0089
0.0016
0.0243
0.9652
0.0000
0.0000
car
0.2686
0.0353
0.0011
0.0094
0.6805
0.0051
clutter
0.5012
0.4033
0.0291
0.0097
0.0408
0.0160
Precision/Correctness
0.907
0.914
0.869
0.651
0.753
0.869
Recall/Completeness
0.947
0.954
0.559
0.965
0.681
0.016
F1
0.927
0.933
0.680
0.777
0.715
0.031

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_area29_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9660
0.0132
0.0120
0.0056
0.0032
0.0000
building
0.0252
0.9671
0.0045
0.0032
0.0000
0.0000
low_veg
0.0583
0.0093
0.6086
0.3235
0.0002
0.0000
tree
0.0036
0.0002
0.0180
0.9782
0.0000
0.0000
car
0.1553
0.0397
0.0006
0.0062
0.7909
0.0072
clutter
0.4844
0.4279
0.0218
0.0039
0.0440
0.0180
Precision/Correctness
0.933
0.935
0.903
0.685
0.758
0.868
Recall/Completeness
0.966
0.967
0.609
0.978
0.791
0.018
F1
0.949
0.951
0.727
0.806
0.774
0.035

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
0.9769
0.0103
0.0059
0.0030
0.0035
0.0003
building
0.1113
0.8759
0.0088
0.0015
0.0022
0.0004
low_veg
0.0686
0.0028
0.8777
0.0505
0.0004
0.0000
tree
0.0482
0.0047
0.0752
0.8711
0.0008
0.0000
car
0.1925
0.1399
0.0112
0.0035
0.6487
0.0042
clutter
0.4624
0.3220
0.0547
0.0056
0.0602
0.0953
Precision/Correctness
0.846
0.921
0.894
0.913
0.849
0.899
Recall/Completeness
0.977
0.876
0.878
0.871
0.649
0.095
F1
0.907
0.898
0.886
0.892
0.736
0.172

Overall accuracy 0.881

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
0.9865
0.0073
0.0042
0.0005
0.0014
0.0001
building
0.0997
0.8934
0.0045
0.0002
0.0019
0.0004
low_veg
0.0446
0.0005
0.9128
0.0421
0.0000
0.0000
tree
0.0200
0.0010
0.0586
0.9202
0.0002
0.0000
car
0.0904
0.1582
0.0062
0.0004
0.7408
0.0039
clutter
0.4061
0.3564
0.0594
0.0012
0.0661
0.1108
Precision/Correctness
0.880
0.934
0.923
0.938
0.872
0.928
Recall/Completeness
0.986
0.893
0.913
0.920
0.741
0.111
F1
0.930
0.913
0.918
0.929
0.801
0.198

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_area33_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9756
0.0164
0.0035
0.0030
0.0012
0.0004
building
0.0720
0.8546
0.0633
0.0074
0.0022
0.0004
low_veg
0.0922
0.0244
0.7788
0.1044
0.0003
0.0000
tree
0.0485
0.0192
0.1027
0.8295
0.0000
0.0000
car
0.3262
0.0113
0.0033
0.0016
0.6577
0.0000
clutter
0.4908
0.1805
0.0025
0.0003
0.0358
0.2901
Precision/Correctness
0.841
0.918
0.797
0.817
0.733
0.983
Recall/Completeness
0.976
0.855
0.779
0.830
0.658
0.290
F1
0.904
0.885
0.788
0.823
0.693
0.448

Overall accuracy 0.854

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
0.9852
0.0119
0.0015
0.0007
0.0007
0.0001
building
0.0649
0.8638
0.0629
0.0059
0.0021
0.0004
low_veg
0.0561
0.0146
0.8232
0.1059
0.0003
0.0000
tree
0.0207
0.0156
0.0934
0.8703
0.0000
0.0000
car
0.1961
0.0081
0.0026
0.0009
0.7923
0.0000
clutter
0.4436
0.1905
0.0020
0.0000
0.0388
0.3251
Precision/Correctness
0.875
0.935
0.810
0.831
0.732
0.992
Recall/Completeness
0.985
0.864
0.823
0.870
0.792
0.325
F1
0.927
0.898
0.817
0.850
0.761
0.490

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_area35_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8978
0.0501
0.0335
0.0176
0.0010
0.0000
building
0.0487
0.9370
0.0079
0.0056
0.0009
0.0000
low_veg
0.1055
0.0155
0.6082
0.2708
0.0001
0.0000
tree
0.0442
0.0052
0.0727
0.8778
0.0001
0.0000
car
0.3257
0.0056
0.0006
0.0093
0.6587
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.813
0.934
0.846
0.738
0.901
--
Recall/Completeness
0.898
0.937
0.608
0.878
0.659
--
F1
0.853
0.935
0.708
0.802
0.761
--

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: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9280
0.0455
0.0214
0.0048
0.0004
0.0000
building
0.0352
0.9604
0.0026
0.0009
0.0009
0.0000
low_veg
0.0843
0.0063
0.6455
0.2639
0.0000
0.0000
tree
0.0171
0.0011
0.0530
0.9288
0.0000
0.0000
car
0.2038
0.0060
0.0000
0.0036
0.7866
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.865
0.954
0.897
0.762
0.931
--
Recall/Completeness
0.928
0.960
0.646
0.929
0.787
--
F1
0.895
0.957
0.751
0.837
0.853
--

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_area38_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9196
0.0311
0.0316
0.0159
0.0019
0.0000
building
0.0501
0.9016
0.0409
0.0059
0.0015
0.0000
low_veg
0.0648
0.0426
0.7676
0.1245
0.0004
0.0001
tree
0.0296
0.0044
0.0726
0.8934
0.0000
0.0000
car
0.2706
0.0380
0.0200
0.0055
0.6660
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.863
0.914
0.866
0.811
0.866
--
Recall/Completeness
0.920
0.902
0.768
0.893
0.666
--
F1
0.890
0.908
0.814
0.850
0.753
--

Overall accuracy 0.865

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
0.9408
0.0294
0.0226
0.0063
0.0009
0.0000
building
0.0418
0.9246
0.0298
0.0024
0.0014
0.0000
low_veg
0.0440
0.0402
0.8092
0.1062
0.0003
0.0001
tree
0.0120
0.0017
0.0557
0.9306
0.0000
0.0000
car
0.1508
0.0449
0.0112
0.0017
0.7915
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.905
0.926
0.901
0.848
0.892
--
Recall/Completeness
0.941
0.925
0.809
0.931
0.792
--
F1
0.922
0.925
0.853
0.887
0.839
--

Overall accuracy 0.897

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image