Detailled semantic labeling (2D) result


Name Y. Sun
Affiliation Huazhong University of Science and Technology (HUST), Wuhan, China
Abbreviation HUSTW4
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
0.896
0.032
0.052
0.016
0.005
0.000
building
0.046
0.927
0.020
0.007
0.000
0.000
low_veg
0.056
0.023
0.796
0.125
0.000
0.000
tree
0.020
0.006
0.108
0.865
0.000
0.000
car
0.263
0.050
0.010
0.005
0.672
0.000
clutter
0.600
0.341
0.016
0.007
0.037
0.000
Precision/Correctness
0.870
0.927
0.795
0.855
0.830
-nan
Recall/Completeness
0.896
0.927
0.796
0.865
0.672
0.000
F1
0.883
0.927
0.796
0.860
0.742
-nan

Overall accuracy 0.865

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
0.925
0.024
0.042
0.008
0.002
0.000
building
0.038
0.945
0.013
0.004
0.000
0.000
low_veg
0.045
0.013
0.831
0.110
0.000
0.000
tree
0.009
0.002
0.089
0.899
0.000
0.000
car
0.172
0.056
0.006
0.003
0.764
0.000
clutter
0.582
0.367
0.010
0.002
0.038
0.000
Precision/Correctness
0.900
0.949
0.834
0.884
0.876
-nan
Recall/Completeness
0.925
0.945
0.831
0.899
0.764
0.000
F1
0.912
0.947
0.832
0.892
0.816
-nan

Overall accuracy 0.895
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9434
0.0151
0.0241
0.0120
0.0054
0.0000
building
0.0285
0.9527
0.0150
0.0038
0.0000
0.0000
low_veg
0.0963
0.0265
0.7244
0.1522
0.0005
0.0000
tree
0.0317
0.0088
0.0961
0.8633
0.0001
0.0000
car
0.2974
0.0060
0.0005
0.0016
0.6944
0.0000
clutter
0.9026
0.0724
0.0020
0.0223
0.0007
0.0000
Precision/Correctness
0.799
0.940
0.842
0.837
0.877
-nan
Recall/Completeness
0.943
0.953
0.724
0.863
0.694
0.000
F1
0.865
0.947
0.779
0.850
0.775
-nan

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_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9709
0.0095
0.0125
0.0038
0.0034
0.0000
building
0.0212
0.9688
0.0081
0.0019
0.0000
0.0000
low_veg
0.0830
0.0140
0.7573
0.1451
0.0005
0.0000
tree
0.0156
0.0046
0.0826
0.8971
0.0000
0.0000
car
0.1724
0.0034
0.0000
0.0008
0.8234
0.0000
clutter
0.9235
0.0688
0.0017
0.0052
0.0008
0.0000
Precision/Correctness
0.830
0.965
0.876
0.861
0.909
-nan
Recall/Completeness
0.971
0.969
0.757
0.897
0.823
0.000
F1
0.895
0.967
0.812
0.878
0.864
-nan

Overall accuracy 0.880

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
0.8959
0.0836
0.0112
0.0051
0.0042
0.0000
building
0.0431
0.9471
0.0078
0.0017
0.0003
0.0000
low_veg
0.1600
0.0637
0.5389
0.2350
0.0024
0.0000
tree
0.0575
0.0156
0.0845
0.8418
0.0006
0.0000
car
0.3723
0.0382
0.0041
0.0013
0.5842
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.869
0.949
0.672
0.757
0.848
--
Recall/Completeness
0.896
0.947
0.539
0.842
0.584
--
F1
0.882
0.948
0.598
0.797
0.692
--

Overall accuracy 0.902

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area4_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9258
0.0613
0.0081
0.0028
0.0020
0.0000
building
0.0307
0.9617
0.0067
0.0007
0.0002
0.0000
low_veg
0.1264
0.0284
0.5851
0.2579
0.0022
0.0000
tree
0.0269
0.0049
0.0773
0.8909
0.0000
0.0000
car
0.2951
0.0318
0.0018
0.0004
0.6708
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.905
0.967
0.704
0.783
0.903
--
Recall/Completeness
0.926
0.962
0.585
0.891
0.671
--
F1
0.915
0.964
0.639
0.834
0.770
--

Overall accuracy 0.929

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
0.8869
0.0580
0.0399
0.0100
0.0051
0.0000
building
0.0334
0.9483
0.0136
0.0044
0.0004
0.0000
low_veg
0.0672
0.0437
0.7769
0.1117
0.0004
0.0000
tree
0.0148
0.0039
0.0732
0.9080
0.0002
0.0000
car
0.3208
0.0091
0.0011
0.0014
0.6676
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.891
0.938
0.698
0.943
0.878
--
Recall/Completeness
0.887
0.948
0.777
0.908
0.668
--
F1
0.889
0.943
0.736
0.925
0.759
--

Overall accuracy 0.898

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
0.9238
0.0428
0.0289
0.0029
0.0015
0.0000
building
0.0240
0.9656
0.0079
0.0023
0.0003
0.0000
low_veg
0.0516
0.0306
0.8260
0.0917
0.0001
0.0000
tree
0.0048
0.0008
0.0568
0.9375
0.0001
0.0000
car
0.2345
0.0055
0.0006
0.0003
0.7590
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.929
0.960
0.750
0.964
0.947
--
Recall/Completeness
0.924
0.966
0.826
0.937
0.759
--
F1
0.926
0.963
0.786
0.951
0.843
--

Overall accuracy 0.931

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
0.8802
0.0277
0.0776
0.0102
0.0042
0.0000
building
0.0277
0.9485
0.0190
0.0048
0.0001
0.0000
low_veg
0.0475
0.0155
0.8824
0.0545
0.0001
0.0000
tree
0.0250
0.0070
0.0991
0.8689
0.0001
0.0000
car
0.3169
0.0151
0.0236
0.0041
0.6403
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.911
0.941
0.767
0.932
0.886
--
Recall/Completeness
0.880
0.948
0.882
0.869
0.640
--
F1
0.895
0.945
0.820
0.899
0.743
--

Overall accuracy 0.890

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
0.9072
0.0222
0.0656
0.0030
0.0019
0.0000
building
0.0171
0.9707
0.0097
0.0024
0.0001
0.0000
low_veg
0.0329
0.0074
0.9164
0.0434
0.0000
0.0000
tree
0.0110
0.0029
0.0751
0.9110
0.0000
0.0000
car
0.2192
0.0159
0.0151
0.0028
0.7471
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.947
0.962
0.812
0.956
0.939
--
Recall/Completeness
0.907
0.971
0.916
0.911
0.747
--
F1
0.927
0.966
0.861
0.933
0.832
--

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_area10_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8215
0.0652
0.0910
0.0194
0.0028
0.0000
building
0.0217
0.9473
0.0184
0.0125
0.0001
0.0000
low_veg
0.0649
0.0314
0.7631
0.1404
0.0002
0.0000
tree
0.0113
0.0076
0.0977
0.8833
0.0000
0.0000
car
0.2434
0.0500
0.0069
0.0051
0.6947
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.937
0.875
0.696
0.839
0.811
--
Recall/Completeness
0.822
0.947
0.763
0.883
0.695
--
F1
0.876
0.910
0.728
0.860
0.748
--

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_area10_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8546
0.0519
0.0842
0.0079
0.0014
0.0000
building
0.0157
0.9626
0.0126
0.0090
0.0001
0.0000
low_veg
0.0619
0.0178
0.8074
0.1127
0.0002
0.0000
tree
0.0041
0.0033
0.0757
0.9169
0.0000
0.0000
car
0.1666
0.0522
0.0045
0.0014
0.7751
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.954
0.907
0.730
0.883
0.872
--
Recall/Completeness
0.855
0.963
0.807
0.917
0.775
--
F1
0.901
0.934
0.767
0.900
0.821
--

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_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8763
0.0267
0.0625
0.0307
0.0039
0.0000
building
0.1726
0.8031
0.0178
0.0061
0.0004
0.0000
low_veg
0.0382
0.0254
0.7771
0.1592
0.0001
0.0000
tree
0.0106
0.0072
0.1239
0.8582
0.0000
0.0000
car
0.1760
0.0000
0.0186
0.0023
0.8031
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.718
0.917
0.795
0.860
0.859
--
Recall/Completeness
0.876
0.803
0.777
0.858
0.803
--
F1
0.789
0.856
0.786
0.859
0.830
--

Overall accuracy 0.826

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
0.9084
0.0233
0.0511
0.0164
0.0007
0.0000
building
0.1810
0.8074
0.0094
0.0019
0.0004
0.0000
low_veg
0.0359
0.0155
0.8115
0.1370
0.0000
0.0000
tree
0.0057
0.0029
0.1057
0.8858
0.0000
0.0000
car
0.0837
0.0000
0.0130
0.0002
0.9031
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.731
0.947
0.826
0.888
0.946
--
Recall/Completeness
0.908
0.807
0.812
0.886
0.903
--
F1
0.810
0.872
0.819
0.887
0.924
--

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
0.8215
0.0308
0.1129
0.0296
0.0052
0.0000
building
0.0161
0.9527
0.0228
0.0085
0.0000
0.0000
low_veg
0.0819
0.0446
0.7329
0.1404
0.0002
0.0000
tree
0.0278
0.0093
0.1228
0.8401
0.0000
0.0000
car
0.1330
0.0014
0.0012
0.0069
0.8574
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.850
0.886
0.724
0.865
0.648
--
Recall/Completeness
0.822
0.953
0.733
0.840
0.857
--
F1
0.835
0.918
0.728
0.852
0.738
--

Overall accuracy 0.828

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area14_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8420
0.0265
0.1076
0.0196
0.0043
0.0000
building
0.0107
0.9752
0.0101
0.0040
0.0000
0.0000
low_veg
0.0773
0.0310
0.7639
0.1277
0.0002
0.0000
tree
0.0195
0.0040
0.1093
0.8673
0.0000
0.0000
car
0.0396
0.0004
0.0000
0.0021
0.9579
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.876
0.918
0.749
0.888
0.646
--
Recall/Completeness
0.842
0.975
0.764
0.867
0.958
--
F1
0.859
0.946
0.756
0.877
0.771
--

Overall accuracy 0.855

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area16_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.7851
0.0221
0.1452
0.0455
0.0021
0.0000
building
0.0198
0.9318
0.0335
0.0148
0.0001
0.0000
low_veg
0.0113
0.0143
0.8399
0.1345
0.0001
0.0000
tree
0.0191
0.0052
0.1233
0.8524
0.0000
0.0000
car
0.1975
0.0059
0.0298
0.0321
0.7348
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.895
0.945
0.772
0.863
0.822
--
Recall/Completeness
0.785
0.932
0.840
0.852
0.735
--
F1
0.836
0.938
0.804
0.858
0.776
--

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: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8244
0.0179
0.1304
0.0267
0.0007
0.0000
building
0.0178
0.9565
0.0192
0.0066
0.0000
0.0000
low_veg
0.0089
0.0084
0.8630
0.1197
0.0001
0.0000
tree
0.0126
0.0021
0.1070
0.8783
0.0000
0.0000
car
0.1190
0.0029
0.0205
0.0223
0.8352
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.921
0.966
0.804
0.888
0.913
--
Recall/Completeness
0.824
0.956
0.863
0.878
0.835
--
F1
0.870
0.961
0.832
0.883
0.873
--

Overall accuracy 0.880

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
0.8393
0.0229
0.0839
0.0487
0.0052
0.0000
building
0.0170
0.9362
0.0326
0.0143
0.0000
0.0000
low_veg
0.0407
0.0195
0.7847
0.1548
0.0003
0.0000
tree
0.0063
0.0013
0.0726
0.9197
0.0000
0.0000
car
0.2140
0.0234
0.0512
0.0123
0.6992
0.0000
clutter
0.0675
0.8996
0.0319
0.0010
0.0000
0.0000
Precision/Correctness
0.914
0.821
0.741
0.900
0.722
-nan
Recall/Completeness
0.839
0.936
0.785
0.920
0.699
0.000
F1
0.875
0.875
0.762
0.910
0.710
-nan

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_area20_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8750
0.0142
0.0762
0.0308
0.0039
0.0000
building
0.0147
0.9508
0.0253
0.0092
0.0000
0.0000
low_veg
0.0343
0.0098
0.8251
0.1305
0.0003
0.0000
tree
0.0023
0.0001
0.0569
0.9407
0.0000
0.0000
car
0.1406
0.0246
0.0433
0.0036
0.7879
0.0000
clutter
0.0609
0.9159
0.0229
0.0003
0.0000
0.0000
Precision/Correctness
0.937
0.838
0.776
0.925
0.736
-nan
Recall/Completeness
0.875
0.951
0.825
0.941
0.788
0.000
F1
0.905
0.891
0.800
0.933
0.761
-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_area22_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8868
0.0246
0.0503
0.0317
0.0066
0.0000
building
0.0243
0.9544
0.0152
0.0058
0.0002
0.0000
low_veg
0.0910
0.0365
0.7306
0.1418
0.0000
0.0000
tree
0.0200
0.0035
0.0769
0.8994
0.0001
0.0000
car
0.2659
0.0082
0.0157
0.0081
0.7021
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.900
0.912
0.782
0.867
0.779
--
Recall/Completeness
0.887
0.954
0.731
0.899
0.702
--
F1
0.893
0.933
0.755
0.883
0.738
--

Overall accuracy 0.869

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
0.9217
0.0169
0.0416
0.0158
0.0040
0.0000
building
0.0168
0.9734
0.0077
0.0020
0.0001
0.0000
low_veg
0.0870
0.0237
0.7756
0.1137
0.0000
0.0000
tree
0.0074
0.0009
0.0586
0.9330
0.0000
0.0000
car
0.1680
0.0114
0.0112
0.0014
0.8080
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.927
0.944
0.827
0.906
0.831
--
Recall/Completeness
0.922
0.973
0.776
0.933
0.808
--
F1
0.924
0.959
0.800
0.919
0.819
--

Overall accuracy 0.905

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area24_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.7703
0.0408
0.1544
0.0311
0.0035
0.0000
building
0.0481
0.8890
0.0470
0.0159
0.0001
0.0000
low_veg
0.0187
0.0160
0.8944
0.0709
0.0001
0.0000
tree
0.0129
0.0073
0.1522
0.8276
0.0000
0.0000
car
0.3173
0.0001
0.0223
0.0072
0.6531
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.841
0.921
0.840
0.851
0.815
--
Recall/Completeness
0.770
0.889
0.894
0.828
0.653
--
F1
0.804
0.905
0.866
0.839
0.725
--

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_area24_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8036
0.0310
0.1418
0.0216
0.0020
0.0000
building
0.0472
0.9035
0.0367
0.0125
0.0001
0.0000
low_veg
0.0156
0.0116
0.9132
0.0594
0.0001
0.0000
tree
0.0071
0.0038
0.1284
0.8607
0.0000
0.0000
car
0.2343
0.0001
0.0122
0.0016
0.7518
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.865
0.944
0.865
0.876
0.853
--
Recall/Completeness
0.804
0.904
0.913
0.861
0.752
--
F1
0.833
0.923
0.889
0.868
0.799
--

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_area27_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9381
0.0266
0.0195
0.0069
0.0090
0.0000
building
0.0519
0.9298
0.0121
0.0061
0.0002
0.0000
low_veg
0.0931
0.0324
0.7010
0.1733
0.0002
0.0000
tree
0.0112
0.0079
0.0487
0.9320
0.0003
0.0000
car
0.2533
0.0111
0.0039
0.0058
0.7260
0.0000
clutter
0.6950
0.1254
0.0929
0.0090
0.0778
0.0000
Precision/Correctness
0.863
0.952
0.897
0.708
0.881
-nan
Recall/Completeness
0.938
0.930
0.701
0.932
0.726
0.000
F1
0.899
0.941
0.787
0.805
0.796
-nan

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_area27_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9669
0.0168
0.0118
0.0025
0.0021
0.0000
building
0.0397
0.9490
0.0070
0.0041
0.0001
0.0000
low_veg
0.0775
0.0178
0.7432
0.1614
0.0000
0.0000
tree
0.0042
0.0029
0.0304
0.9625
0.0000
0.0000
car
0.1575
0.0096
0.0017
0.0043
0.8270
0.0000
clutter
0.7204
0.1201
0.0677
0.0051
0.0867
0.0000
Precision/Correctness
0.898
0.973
0.937
0.741
0.958
-nan
Recall/Completeness
0.967
0.949
0.743
0.963
0.827
0.000
F1
0.931
0.961
0.829
0.837
0.888
-nan

Overall accuracy 0.912

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
0.9358
0.0175
0.0290
0.0127
0.0050
0.0000
building
0.0534
0.9285
0.0120
0.0059
0.0002
0.0000
low_veg
0.0577
0.0223
0.6343
0.2856
0.0001
0.0000
tree
0.0047
0.0024
0.0289
0.9640
0.0000
0.0000
car
0.2625
0.0068
0.0012
0.0102
0.7194
0.0000
clutter
0.6200
0.3288
0.0200
0.0051
0.0262
0.0000
Precision/Correctness
0.897
0.924
0.830
0.681
0.765
-nan
Recall/Completeness
0.936
0.928
0.634
0.964
0.719
0.000
F1
0.916
0.926
0.719
0.798
0.742
-nan

Overall accuracy 0.861

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
0.9586
0.0113
0.0210
0.0058
0.0033
0.0000
building
0.0492
0.9412
0.0067
0.0028
0.0001
0.0000
low_veg
0.0384
0.0092
0.6785
0.2739
0.0000
0.0000
tree
0.0010
0.0004
0.0200
0.9786
0.0000
0.0000
car
0.1735
0.0042
0.0001
0.0075
0.8147
0.0000
clutter
0.6151
0.3448
0.0111
0.0008
0.0283
0.0000
Precision/Correctness
0.917
0.945
0.874
0.718
0.789
-nan
Recall/Completeness
0.959
0.941
0.678
0.979
0.815
0.000
F1
0.937
0.943
0.764
0.828
0.801
-nan

Overall accuracy 0.890

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
0.9657
0.0105
0.0156
0.0028
0.0053
0.0000
building
0.0678
0.9195
0.0098
0.0014
0.0015
0.0000
low_veg
0.0425
0.0049
0.9328
0.0193
0.0005
0.0000
tree
0.0390
0.0032
0.1430
0.8141
0.0008
0.0000
car
0.1670
0.2206
0.0118
0.0062
0.5943
0.0000
clutter
0.5443
0.3802
0.0211
0.0084
0.0460
0.0000
Precision/Correctness
0.875
0.908
0.842
0.950
0.836
-nan
Recall/Completeness
0.966
0.920
0.933
0.814
0.594
0.000
F1
0.918
0.914
0.885
0.877
0.695
-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_area31_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9805
0.0062
0.0113
0.0004
0.0016
0.0000
building
0.0551
0.9401
0.0033
0.0003
0.0012
0.0000
low_veg
0.0254
0.0025
0.9584
0.0135
0.0003
0.0000
tree
0.0137
0.0005
0.1183
0.8673
0.0002
0.0000
car
0.0976
0.2464
0.0054
0.0024
0.6483
0.0000
clutter
0.4940
0.4375
0.0153
0.0031
0.0501
0.0000
Precision/Correctness
0.907
0.922
0.883
0.975
0.879
-nan
Recall/Completeness
0.980
0.940
0.958
0.867
0.648
0.000
F1
0.943
0.931
0.919
0.918
0.746
-nan

Overall accuracy 0.914

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area33_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9804
0.0082
0.0064
0.0032
0.0018
0.0000
building
0.0998
0.8502
0.0292
0.0184
0.0024
0.0000
low_veg
0.0863
0.0084
0.8622
0.0420
0.0011
0.0000
tree
0.0412
0.0096
0.1710
0.7782
0.0000
0.0000
car
0.3131
0.0076
0.0073
0.0012
0.6709
0.0000
clutter
0.7354
0.1889
0.0018
0.0005
0.0734
0.0000
Precision/Correctness
0.807
0.940
0.821
0.862
0.609
-nan
Recall/Completeness
0.980
0.850
0.862
0.778
0.671
0.000
F1
0.885
0.893
0.841
0.818
0.639
-nan

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_area33_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9915
0.0052
0.0017
0.0010
0.0005
0.0000
building
0.0935
0.8611
0.0255
0.0177
0.0021
0.0000
low_veg
0.0543
0.0026
0.9014
0.0405
0.0012
0.0000
tree
0.0163
0.0032
0.1556
0.8249
0.0000
0.0000
car
0.2123
0.0084
0.0032
0.0002
0.7759
0.0000
clutter
0.7151
0.2033
0.0008
0.0002
0.0806
0.0000
Precision/Correctness
0.834
0.952
0.848
0.877
0.604
-nan
Recall/Completeness
0.992
0.861
0.901
0.825
0.776
0.000
F1
0.906
0.904
0.874
0.850
0.679
-nan

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_area35_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8715
0.0422
0.0669
0.0178
0.0015
0.0000
building
0.0536
0.9287
0.0138
0.0034
0.0005
0.0000
low_veg
0.0529
0.0181
0.7288
0.2001
0.0002
0.0000
tree
0.0293
0.0064
0.1309
0.8333
0.0001
0.0000
car
0.3401
0.0300
0.0050
0.0077
0.6172
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.856
0.936
0.779
0.780
0.887
--
Recall/Completeness
0.872
0.929
0.729
0.833
0.617
--
F1
0.864
0.933
0.753
0.806
0.728
--

Overall accuracy 0.841

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
0.9212
0.0327
0.0418
0.0041
0.0002
0.0000
building
0.0450
0.9490
0.0048
0.0007
0.0005
0.0000
low_veg
0.0396
0.0084
0.7578
0.1940
0.0001
0.0000
tree
0.0091
0.0014
0.1015
0.8879
0.0000
0.0000
car
0.2445
0.0336
0.0008
0.0019
0.7191
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.898
0.962
0.842
0.806
0.953
--
Recall/Completeness
0.921
0.949
0.758
0.888
0.719
--
F1
0.909
0.955
0.798
0.845
0.820
--

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_area38_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9050
0.0302
0.0503
0.0111
0.0034
0.0000
building
0.0178
0.9344
0.0414
0.0058
0.0005
0.0000
low_veg
0.0413
0.0165
0.8789
0.0633
0.0001
0.0000
tree
0.0216
0.0067
0.1492
0.8225
0.0000
0.0000
car
0.2423
0.0536
0.0287
0.0060
0.6693
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.915
0.942
0.822
0.878
0.856
--
Recall/Completeness
0.905
0.934
0.879
0.822
0.669
--
F1
0.910
0.938
0.849
0.850
0.751
--

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
0.9367
0.0267
0.0316
0.0033
0.0016
0.0000
building
0.0106
0.9563
0.0292
0.0034
0.0005
0.0000
low_veg
0.0286
0.0095
0.9121
0.0498
0.0000
0.0000
tree
0.0087
0.0030
0.1179
0.8704
0.0000
0.0000
car
0.1531
0.0629
0.0147
0.0015
0.7678
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.949
0.959
0.867
0.914
0.911
--
Recall/Completeness
0.937
0.956
0.912
0.870
0.768
--
F1
0.943
0.958
0.889
0.892
0.833
--

Overall accuracy 0.921

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image