Detailled semantic labeling (2D) result


Name Y. Sun
Affiliation Huazhong University of Science and Technology (HUST), Wuhan, China
Abbreviation HUSTW3
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
0.886
0.030
0.055
0.023
0.005
0.000
building
0.041
0.935
0.018
0.006
0.000
0.000
low_veg
0.029
0.020
0.817
0.134
0.000
0.000
tree
0.010
0.005
0.080
0.904
0.000
0.000
car
0.291
0.025
0.017
0.009
0.658
0.000
clutter
0.549
0.300
0.040
0.028
0.083
0.000
Precision/Correctness
0.898
0.935
0.821
0.846
0.783
-nan
Recall/Completeness
0.886
0.935
0.817
0.904
0.658
0.000
F1
0.892
0.935
0.819
0.874
0.715
-nan

Overall accuracy 0.877

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
0.920
0.022
0.044
0.012
0.002
0.000
building
0.036
0.951
0.010
0.003
0.000
0.000
low_veg
0.021
0.011
0.852
0.116
0.000
0.000
tree
0.004
0.002
0.063
0.931
0.000
0.000
car
0.211
0.027
0.011
0.005
0.746
0.000
clutter
0.528
0.325
0.037
0.023
0.087
0.000
Precision/Correctness
0.922
0.955
0.860
0.880
0.823
-nan
Recall/Completeness
0.920
0.951
0.852
0.931
0.746
0.000
F1
0.921
0.953
0.856
0.905
0.783
-nan

Overall accuracy 0.907
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9216
0.0105
0.0447
0.0173
0.0059
0.0000
building
0.0217
0.9506
0.0218
0.0059
0.0001
0.0000
low_veg
0.0454
0.0204
0.8113
0.1226
0.0003
0.0000
tree
0.0164
0.0055
0.0945
0.8836
0.0001
0.0000
car
0.3371
0.0019
0.0028
0.0044
0.6538
0.0000
clutter
0.9595
0.0074
0.0002
0.0327
0.0002
0.0000
Precision/Correctness
0.842
0.960
0.834
0.857
0.863
-nan
Recall/Completeness
0.922
0.951
0.811
0.884
0.654
0.000
F1
0.880
0.955
0.822
0.870
0.744
-nan

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_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9560
0.0055
0.0290
0.0058
0.0037
0.0000
building
0.0161
0.9674
0.0128
0.0036
0.0001
0.0000
low_veg
0.0342
0.0096
0.8425
0.1134
0.0003
0.0000
tree
0.0063
0.0018
0.0793
0.9126
0.0000
0.0000
car
0.2366
0.0003
0.0008
0.0014
0.7609
0.0000
clutter
0.9817
0.0075
0.0001
0.0105
0.0002
0.0000
Precision/Correctness
0.868
0.982
0.871
0.885
0.900
-nan
Recall/Completeness
0.956
0.967
0.843
0.913
0.761
0.000
F1
0.910
0.975
0.856
0.898
0.825
-nan

Overall accuracy 0.900

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
0.9098
0.0603
0.0186
0.0068
0.0045
0.0000
building
0.0488
0.9393
0.0101
0.0017
0.0001
0.0000
low_veg
0.0957
0.0522
0.6117
0.2394
0.0011
0.0000
tree
0.0347
0.0160
0.0780
0.8710
0.0002
0.0000
car
0.4678
0.0183
0.0048
0.0031
0.5060
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.869
0.962
0.646
0.754
0.837
--
Recall/Completeness
0.910
0.939
0.612
0.871
0.506
--
F1
0.889
0.950
0.628
0.808
0.631
--

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_area4_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9405
0.0389
0.0140
0.0038
0.0028
0.0000
building
0.0375
0.9534
0.0083
0.0007
0.0001
0.0000
low_veg
0.0671
0.0197
0.6544
0.2576
0.0012
0.0000
tree
0.0124
0.0051
0.0684
0.9141
0.0000
0.0000
car
0.4013
0.0114
0.0024
0.0011
0.5839
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.900
0.979
0.684
0.784
0.879
--
Recall/Completeness
0.940
0.953
0.654
0.914
0.584
--
F1
0.920
0.966
0.669
0.844
0.702
--

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_area6_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8738
0.0627
0.0448
0.0142
0.0045
0.0000
building
0.0216
0.9581
0.0167
0.0035
0.0001
0.0000
low_veg
0.0305
0.0383
0.7818
0.1492
0.0003
0.0000
tree
0.0073
0.0033
0.0523
0.9370
0.0001
0.0000
car
0.3450
0.0159
0.0041
0.0018
0.6333
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.925
0.937
0.722
0.929
0.894
--
Recall/Completeness
0.874
0.958
0.782
0.937
0.633
--
F1
0.899
0.947
0.751
0.933
0.741
--

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_area6_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9142
0.0465
0.0340
0.0039
0.0014
0.0000
building
0.0143
0.9741
0.0104
0.0012
0.0001
0.0000
low_veg
0.0204
0.0250
0.8336
0.1210
0.0000
0.0000
tree
0.0016
0.0007
0.0396
0.9580
0.0000
0.0000
car
0.2539
0.0095
0.0027
0.0002
0.7336
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.956
0.959
0.773
0.956
0.961
--
Recall/Completeness
0.914
0.974
0.834
0.958
0.734
--
F1
0.935
0.966
0.802
0.957
0.832
--

Overall accuracy 0.938

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
0.8670
0.0315
0.0778
0.0183
0.0054
0.0000
building
0.0237
0.9500
0.0212
0.0047
0.0004
0.0000
low_veg
0.0323
0.0137
0.8968
0.0570
0.0000
0.0000
tree
0.0114
0.0062
0.0774
0.9050
0.0000
0.0000
car
0.3372
0.0078
0.0311
0.0087
0.6151
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.931
0.939
0.785
0.922
0.854
--
Recall/Completeness
0.867
0.950
0.897
0.905
0.615
--
F1
0.898
0.945
0.837
0.914
0.715
--

Overall accuracy 0.897

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area8_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8999
0.0254
0.0664
0.0061
0.0022
0.0000
building
0.0150
0.9712
0.0114
0.0021
0.0003
0.0000
low_veg
0.0204
0.0065
0.9302
0.0428
0.0000
0.0000
tree
0.0029
0.0027
0.0584
0.9360
0.0000
0.0000
car
0.2580
0.0090
0.0196
0.0070
0.7064
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.961
0.959
0.827
0.954
0.921
--
Recall/Completeness
0.900
0.971
0.930
0.936
0.706
--
F1
0.929
0.965
0.876
0.945
0.799
--

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_area10_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8424
0.0627
0.0637
0.0276
0.0035
0.0000
building
0.0106
0.9605
0.0156
0.0130
0.0003
0.0000
low_veg
0.0265
0.0278
0.7843
0.1612
0.0002
0.0000
tree
0.0062
0.0074
0.0704
0.9161
0.0000
0.0000
car
0.2833
0.0320
0.0258
0.0093
0.6496
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.968
0.883
0.766
0.818
0.763
--
Recall/Completeness
0.842
0.960
0.784
0.916
0.650
--
F1
0.901
0.920
0.775
0.864
0.702
--

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_area10_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8832
0.0492
0.0530
0.0124
0.0021
0.0000
building
0.0057
0.9758
0.0089
0.0094
0.0002
0.0000
low_veg
0.0228
0.0158
0.8337
0.1275
0.0002
0.0000
tree
0.0024
0.0032
0.0532
0.9412
0.0000
0.0000
car
0.2096
0.0341
0.0242
0.0031
0.7291
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.980
0.913
0.809
0.868
0.809
--
Recall/Completeness
0.883
0.976
0.834
0.941
0.729
--
F1
0.929
0.943
0.821
0.903
0.767
--

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_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8494
0.0322
0.0648
0.0493
0.0043
0.0000
building
0.1550
0.8157
0.0226
0.0067
0.0001
0.0000
low_veg
0.0244
0.0234
0.7542
0.1979
0.0001
0.0000
tree
0.0044
0.0061
0.0802
0.9094
0.0000
0.0000
car
0.1736
0.0000
0.0064
0.0159
0.8042
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.755
0.920
0.835
0.837
0.861
--
Recall/Completeness
0.849
0.816
0.754
0.909
0.804
--
F1
0.799
0.865
0.793
0.871
0.832
--

Overall accuracy 0.837

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
0.8853
0.0285
0.0563
0.0285
0.0013
0.0000
building
0.1653
0.8198
0.0125
0.0023
0.0001
0.0000
low_veg
0.0224
0.0152
0.7930
0.1693
0.0001
0.0000
tree
0.0014
0.0022
0.0655
0.9310
0.0000
0.0000
car
0.0783
0.0000
0.0055
0.0084
0.9077
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.763
0.945
0.866
0.868
0.939
--
Recall/Completeness
0.885
0.820
0.793
0.931
0.908
--
F1
0.820
0.878
0.828
0.899
0.923
--

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_area14_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8340
0.0333
0.0834
0.0461
0.0033
0.0000
building
0.0064
0.9558
0.0290
0.0087
0.0000
0.0000
low_veg
0.0380
0.0422
0.7600
0.1596
0.0001
0.0000
tree
0.0139
0.0091
0.0978
0.8792
0.0000
0.0000
car
0.1279
0.0014
0.0008
0.0047
0.8651
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.924
0.887
0.772
0.848
0.744
--
Recall/Completeness
0.834
0.956
0.760
0.879
0.865
--
F1
0.877
0.920
0.766
0.863
0.800
--

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_area14_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8595
0.0286
0.0773
0.0325
0.0021
0.0000
building
0.0037
0.9780
0.0147
0.0037
0.0000
0.0000
low_veg
0.0336
0.0298
0.7924
0.1441
0.0001
0.0000
tree
0.0082
0.0042
0.0846
0.9030
0.0000
0.0000
car
0.0450
0.0003
0.0000
0.0003
0.9543
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.944
0.917
0.800
0.874
0.782
--
Recall/Completeness
0.859
0.978
0.792
0.903
0.954
--
F1
0.900
0.946
0.796
0.888
0.860
--

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_area16_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.7691
0.0243
0.1259
0.0784
0.0023
0.0000
building
0.0113
0.9442
0.0287
0.0157
0.0000
0.0000
low_veg
0.0060
0.0111
0.7888
0.1933
0.0007
0.0000
tree
0.0101
0.0038
0.0597
0.9265
0.0000
0.0000
car
0.1597
0.0049
0.0550
0.0266
0.7538
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.938
0.952
0.834
0.825
0.750
--
Recall/Completeness
0.769
0.944
0.789
0.926
0.754
--
F1
0.845
0.948
0.811
0.873
0.752
--

Overall accuracy 0.864

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
0.8116
0.0195
0.1172
0.0510
0.0007
0.0000
building
0.0095
0.9680
0.0155
0.0070
0.0000
0.0000
low_veg
0.0035
0.0062
0.8153
0.1743
0.0007
0.0000
tree
0.0054
0.0013
0.0478
0.9455
0.0000
0.0000
car
0.0991
0.0012
0.0402
0.0149
0.8446
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.962
0.971
0.864
0.851
0.805
--
Recall/Completeness
0.812
0.968
0.815
0.946
0.845
--
F1
0.880
0.969
0.839
0.896
0.824
--

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_area20_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8070
0.0217
0.1142
0.0540
0.0032
0.0000
building
0.0116
0.9559
0.0243
0.0081
0.0000
0.0000
low_veg
0.0279
0.0141
0.7949
0.1631
0.0000
0.0000
tree
0.0042
0.0011
0.0422
0.9525
0.0000
0.0000
car
0.2231
0.0039
0.0590
0.0261
0.6879
0.0000
clutter
0.0143
0.7843
0.2004
0.0010
0.0000
0.0000
Precision/Correctness
0.940
0.845
0.755
0.899
0.815
-nan
Recall/Completeness
0.807
0.956
0.795
0.953
0.688
0.000
F1
0.869
0.897
0.774
0.925
0.746
-nan

Overall accuracy 0.866

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area20_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8432
0.0141
0.1097
0.0315
0.0015
0.0000
building
0.0099
0.9709
0.0159
0.0033
0.0000
0.0000
low_veg
0.0222
0.0060
0.8441
0.1276
0.0000
0.0000
tree
0.0014
0.0001
0.0307
0.9678
0.0000
0.0000
car
0.1514
0.0003
0.0431
0.0164
0.7887
0.0000
clutter
0.0069
0.8091
0.1838
0.0002
0.0000
0.0000
Precision/Correctness
0.960
0.858
0.784
0.930
0.881
-nan
Recall/Completeness
0.843
0.971
0.844
0.968
0.789
0.000
F1
0.898
0.911
0.813
0.948
0.832
-nan

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_area22_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8640
0.0269
0.0587
0.0446
0.0058
0.0000
building
0.0139
0.9589
0.0189
0.0082
0.0001
0.0000
low_veg
0.0454
0.0293
0.7614
0.1639
0.0001
0.0000
tree
0.0114
0.0028
0.0470
0.9388
0.0000
0.0000
car
0.3031
0.0060
0.0413
0.0178
0.6318
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.938
0.917
0.810
0.847
0.786
--
Recall/Completeness
0.864
0.959
0.761
0.939
0.632
--
F1
0.900
0.938
0.785
0.890
0.701
--

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_area22_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9035
0.0194
0.0509
0.0230
0.0032
0.0000
building
0.0095
0.9780
0.0084
0.0041
0.0000
0.0000
low_veg
0.0420
0.0173
0.8098
0.1309
0.0000
0.0000
tree
0.0039
0.0007
0.0317
0.9637
0.0000
0.0000
car
0.2295
0.0075
0.0305
0.0083
0.7242
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.958
0.947
0.852
0.891
0.849
--
Recall/Completeness
0.903
0.978
0.810
0.964
0.724
--
F1
0.930
0.962
0.831
0.926
0.782
--

Overall accuracy 0.915

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
0.7440
0.0332
0.1615
0.0572
0.0041
0.0000
building
0.0397
0.9077
0.0426
0.0100
0.0000
0.0000
low_veg
0.0078
0.0148
0.8800
0.0972
0.0002
0.0000
tree
0.0074
0.0066
0.0870
0.8991
0.0000
0.0000
car
0.3189
0.0000
0.0203
0.0128
0.6480
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.887
0.931
0.871
0.820
0.785
--
Recall/Completeness
0.744
0.908
0.880
0.899
0.648
--
F1
0.809
0.919
0.875
0.858
0.710
--

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_area24_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.7833
0.0223
0.1512
0.0411
0.0021
0.0000
building
0.0398
0.9217
0.0325
0.0059
0.0000
0.0000
low_veg
0.0062
0.0108
0.9021
0.0807
0.0002
0.0000
tree
0.0036
0.0034
0.0691
0.9239
0.0000
0.0000
car
0.2477
0.0000
0.0087
0.0050
0.7386
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.905
0.954
0.893
0.850
0.842
--
Recall/Completeness
0.783
0.922
0.902
0.924
0.739
--
F1
0.840
0.937
0.898
0.885
0.787
--

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_area27_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9265
0.0241
0.0295
0.0087
0.0112
0.0000
building
0.0481
0.9302
0.0133
0.0078
0.0005
0.0000
low_veg
0.0502
0.0245
0.7589
0.1658
0.0006
0.0000
tree
0.0065
0.0065
0.0378
0.9490
0.0002
0.0000
car
0.3053
0.0048
0.0081
0.0079
0.6739
0.0000
clutter
0.7147
0.0914
0.0860
0.0111
0.0968
0.0000
Precision/Correctness
0.884
0.960
0.890
0.713
0.841
-nan
Recall/Completeness
0.926
0.930
0.759
0.949
0.674
0.000
F1
0.905
0.945
0.819
0.814
0.748
-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_area27_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9589
0.0143
0.0198
0.0034
0.0037
0.0000
building
0.0383
0.9491
0.0066
0.0056
0.0004
0.0000
low_veg
0.0385
0.0113
0.7998
0.1499
0.0005
0.0000
tree
0.0020
0.0023
0.0234
0.9722
0.0000
0.0000
car
0.2304
0.0034
0.0043
0.0062
0.7557
0.0000
clutter
0.7289
0.0863
0.0618
0.0094
0.1136
0.0000
Precision/Correctness
0.914
0.980
0.931
0.750
0.919
-nan
Recall/Completeness
0.959
0.949
0.800
0.972
0.756
0.000
F1
0.936
0.964
0.860
0.847
0.829
-nan

Overall accuracy 0.919

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area29_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9302
0.0146
0.0336
0.0153
0.0063
0.0000
building
0.0180
0.9635
0.0124
0.0061
0.0000
0.0000
low_veg
0.0304
0.0220
0.6754
0.2721
0.0001
0.0000
tree
0.0026
0.0028
0.0214
0.9732
0.0000
0.0000
car
0.2662
0.0066
0.0061
0.0106
0.7106
0.0000
clutter
0.5196
0.3103
0.0238
0.0176
0.1287
0.0000
Precision/Correctness
0.932
0.932
0.828
0.685
0.594
-nan
Recall/Completeness
0.930
0.963
0.675
0.973
0.711
0.000
F1
0.931
0.948
0.744
0.804
0.647
-nan

Overall accuracy 0.875

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
0.9561
0.0077
0.0250
0.0071
0.0041
0.0000
building
0.0144
0.9759
0.0066
0.0031
0.0000
0.0000
low_veg
0.0155
0.0083
0.7192
0.2570
0.0000
0.0000
tree
0.0007
0.0007
0.0146
0.9840
0.0000
0.0000
car
0.1891
0.0045
0.0049
0.0074
0.7941
0.0000
clutter
0.4978
0.3296
0.0189
0.0104
0.1433
0.0000
Precision/Correctness
0.950
0.953
0.870
0.726
0.590
-nan
Recall/Completeness
0.956
0.976
0.719
0.984
0.794
0.000
F1
0.953
0.964
0.787
0.836
0.677
-nan

Overall accuracy 0.904

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
0.9586
0.0108
0.0158
0.0062
0.0086
0.0000
building
0.1023
0.8859
0.0073
0.0017
0.0027
0.0000
low_veg
0.0214
0.0030
0.9561
0.0192
0.0003
0.0000
tree
0.0183
0.0036
0.0995
0.8783
0.0003
0.0000
car
0.1648
0.0992
0.0124
0.0096
0.7141
0.0000
clutter
0.4791
0.3388
0.0186
0.0482
0.1153
0.0000
Precision/Correctness
0.870
0.925
0.874
0.928
0.762
-nan
Recall/Completeness
0.959
0.886
0.956
0.878
0.714
0.000
F1
0.912
0.905
0.913
0.903
0.737
-nan

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_area31_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9775
0.0074
0.0107
0.0011
0.0033
0.0000
building
0.0964
0.8990
0.0022
0.0003
0.0021
0.0000
low_veg
0.0101
0.0011
0.9780
0.0106
0.0001
0.0000
tree
0.0060
0.0008
0.0775
0.9158
0.0000
0.0000
car
0.0996
0.1082
0.0048
0.0040
0.7833
0.0000
clutter
0.4281
0.3876
0.0127
0.0467
0.1248
0.0000
Precision/Correctness
0.892
0.936
0.914
0.965
0.798
-nan
Recall/Completeness
0.978
0.899
0.978
0.916
0.783
0.000
F1
0.933
0.917
0.945
0.940
0.791
-nan

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
0.9734
0.0073
0.0142
0.0034
0.0017
0.0000
building
0.1313
0.8593
0.0056
0.0026
0.0012
0.0000
low_veg
0.0500
0.0116
0.9236
0.0145
0.0003
0.0000
tree
0.0314
0.0084
0.1629
0.7974
0.0000
0.0000
car
0.3362
0.0007
0.0118
0.0008
0.6505
0.0000
clutter
0.6643
0.1846
0.0015
0.0312
0.1183
0.0000
Precision/Correctness
0.808
0.942
0.854
0.933
0.528
-nan
Recall/Completeness
0.973
0.859
0.924
0.797
0.651
0.000
F1
0.883
0.899
0.887
0.860
0.583
-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_area33_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9875
0.0034
0.0077
0.0008
0.0006
0.0000
building
0.1295
0.8663
0.0021
0.0010
0.0010
0.0000
low_veg
0.0255
0.0063
0.9564
0.0115
0.0003
0.0000
tree
0.0112
0.0034
0.1480
0.8374
0.0000
0.0000
car
0.2366
0.0002
0.0058
0.0001
0.7574
0.0000
clutter
0.6333
0.2007
0.0004
0.0356
0.1301
0.0000
Precision/Correctness
0.830
0.954
0.885
0.954
0.515
-nan
Recall/Completeness
0.987
0.866
0.956
0.837
0.757
0.000
F1
0.902
0.908
0.919
0.892
0.613
-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_area35_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8511
0.0390
0.0805
0.0266
0.0027
0.0000
building
0.0269
0.9469
0.0216
0.0039
0.0006
0.0000
low_veg
0.0205
0.0119
0.7783
0.1893
0.0000
0.0000
tree
0.0141
0.0046
0.1200
0.8612
0.0001
0.0000
car
0.3551
0.0078
0.0146
0.0126
0.6100
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.921
0.948
0.781
0.786
0.844
--
Recall/Completeness
0.851
0.947
0.778
0.861
0.610
--
F1
0.885
0.947
0.780
0.822
0.708
--

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_area35_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9075
0.0320
0.0520
0.0075
0.0011
0.0000
building
0.0195
0.9709
0.0083
0.0009
0.0005
0.0000
low_veg
0.0118
0.0047
0.8050
0.1785
0.0000
0.0000
tree
0.0030
0.0009
0.0889
0.9072
0.0000
0.0000
car
0.2710
0.0095
0.0106
0.0051
0.7038
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.955
0.967
0.847
0.819
0.904
--
Recall/Completeness
0.907
0.971
0.805
0.907
0.704
--
F1
0.930
0.969
0.826
0.861
0.791
--

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_area38_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8895
0.0336
0.0552
0.0177
0.0041
0.0000
building
0.0138
0.9599
0.0214
0.0045
0.0005
0.0000
low_veg
0.0235
0.0147
0.9016
0.0601
0.0001
0.0000
tree
0.0103
0.0054
0.1335
0.8507
0.0000
0.0000
car
0.2647
0.0474
0.0543
0.0135
0.6201
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.942
0.943
0.844
0.879
0.828
--
Recall/Completeness
0.889
0.960
0.902
0.851
0.620
--
F1
0.915
0.951
0.872
0.865
0.709
--

Overall accuracy 0.900

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
0.9257
0.0299
0.0363
0.0058
0.0023
0.0000
building
0.0088
0.9808
0.0079
0.0021
0.0004
0.0000
low_veg
0.0136
0.0081
0.9341
0.0442
0.0000
0.0000
tree
0.0024
0.0021
0.1052
0.8903
0.0000
0.0000
car
0.1901
0.0542
0.0380
0.0057
0.7120
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.969
0.959
0.890
0.921
0.878
--
Recall/Completeness
0.926
0.981
0.934
0.890
0.712
--
F1
0.947
0.970
0.911
0.906
0.786
--

Overall accuracy 0.934

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image