Detailled semantic labeling (2D) result


Name Y. Yu
Affiliation Chinese Academy of Sciences, Institute of Software, China
Abbreviation LLYT1
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
0.870
0.055
0.047
0.023
0.004
0.000
building
0.029
0.945
0.019
0.006
0.000
0.000
low_veg
0.042
0.043
0.741
0.173
0.000
0.000
tree
0.018
0.010
0.077
0.896
0.000
0.000
car
0.326
0.044
0.017
0.009
0.603
0.000
clutter
0.291
0.330
0.006
0.017
0.019
0.336
Precision/Correctness
0.898
0.890
0.818
0.816
0.835
0.959
Recall/Completeness
0.870
0.945
0.741
0.896
0.603
0.336
F1
0.884
0.917
0.778
0.854
0.700
0.498

Overall accuracy 0.860

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
0.901
0.045
0.039
0.013
0.002
0.000
building
0.023
0.959
0.014
0.003
0.000
0.000
low_veg
0.031
0.031
0.781
0.157
0.000
0.000
tree
0.008
0.005
0.062
0.924
0.000
0.000
car
0.223
0.047
0.014
0.006
0.710
0.000
clutter
0.254
0.344
0.005
0.008
0.019
0.370
Precision/Correctness
0.929
0.917
0.851
0.847
0.887
0.978
Recall/Completeness
0.901
0.959
0.781
0.924
0.710
0.370
F1
0.915
0.937
0.815
0.884
0.789
0.537

Overall accuracy 0.890
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9134
0.0321
0.0312
0.0177
0.0055
0.0000
building
0.0239
0.9550
0.0142
0.0070
0.0000
0.0000
low_veg
0.0539
0.0357
0.6836
0.2268
0.0001
0.0000
tree
0.0240
0.0092
0.0569
0.9091
0.0002
0.0006
car
0.3379
0.0210
0.0010
0.0049
0.6352
0.0000
clutter
0.0011
0.0000
0.0000
0.0294
0.0000
0.9695
Precision/Correctness
0.885
0.919
0.869
0.783
0.872
0.991
Recall/Completeness
0.913
0.955
0.684
0.909
0.635
0.969
F1
0.899
0.937
0.765
0.842
0.735
0.980

Overall accuracy 0.863

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9436
0.0254
0.0209
0.0065
0.0037
0.0000
building
0.0192
0.9690
0.0089
0.0029
0.0000
0.0000
low_veg
0.0377
0.0225
0.7219
0.2178
0.0000
0.0000
tree
0.0122
0.0045
0.0483
0.9347
0.0000
0.0002
car
0.2126
0.0206
0.0002
0.0033
0.7633
0.0000
clutter
0.0012
0.0000
0.0000
0.0098
0.0000
0.9890
Precision/Correctness
0.924
0.946
0.900
0.810
0.907
0.997
Recall/Completeness
0.944
0.969
0.722
0.935
0.763
0.989
F1
0.934
0.957
0.801
0.868
0.829
0.993

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: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8879
0.0928
0.0113
0.0051
0.0028
0.0000
building
0.0389
0.9543
0.0045
0.0021
0.0003
0.0000
low_veg
0.1208
0.1148
0.4558
0.3085
0.0001
0.0000
tree
0.0436
0.0340
0.0518
0.8704
0.0003
0.0000
car
0.4244
0.0549
0.0053
0.0051
0.5103
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.880
0.939
0.708
0.717
0.878
--
Recall/Completeness
0.888
0.954
0.456
0.870
0.510
--
F1
0.884
0.947
0.555
0.786
0.645
--

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: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9231
0.0649
0.0089
0.0022
0.0009
0.0000
building
0.0282
0.9667
0.0038
0.0010
0.0003
0.0000
low_veg
0.0816
0.0695
0.5059
0.3430
0.0000
0.0000
tree
0.0197
0.0173
0.0453
0.9178
0.0000
0.0000
car
0.3337
0.0474
0.0045
0.0031
0.6114
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.915
0.962
0.745
0.742
0.939
--
Recall/Completeness
0.923
0.967
0.506
0.918
0.611
--
F1
0.919
0.964
0.602
0.821
0.740
--

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
0.8638
0.0794
0.0366
0.0153
0.0048
0.0001
building
0.0296
0.9590
0.0074
0.0037
0.0002
0.0001
low_veg
0.0605
0.0745
0.6556
0.2092
0.0004
0.0000
tree
0.0115
0.0085
0.0500
0.9298
0.0002
0.0000
car
0.4234
0.0430
0.0061
0.0035
0.5239
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.893
0.910
0.727
0.907
0.860
--
Recall/Completeness
0.864
0.959
0.656
0.930
0.524
--
F1
0.878
0.934
0.689
0.918
0.651
--

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_area6_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9041
0.0592
0.0282
0.0062
0.0022
0.0000
building
0.0224
0.9709
0.0052
0.0015
0.0000
0.0000
low_veg
0.0473
0.0506
0.7116
0.1903
0.0001
0.0000
tree
0.0043
0.0033
0.0393
0.9530
0.0001
0.0000
car
0.3254
0.0365
0.0044
0.0008
0.6330
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.928
0.940
0.771
0.932
0.930
--
Recall/Completeness
0.904
0.971
0.712
0.953
0.633
--
F1
0.916
0.955
0.740
0.943
0.753
--

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
0.8614
0.0413
0.0786
0.0131
0.0056
0.0000
building
0.0208
0.9644
0.0108
0.0039
0.0001
0.0000
low_veg
0.0386
0.0257
0.8569
0.0781
0.0007
0.0000
tree
0.0222
0.0096
0.0884
0.8797
0.0002
0.0000
car
0.3128
0.0144
0.0305
0.0107
0.6308
0.0008
clutter
--
--
--
--
--
--
Precision/Correctness
0.922
0.915
0.775
0.911
0.845
--
Recall/Completeness
0.861
0.964
0.857
0.880
0.631
--
F1
0.890
0.939
0.814
0.895
0.723
--

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_area8_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8950
0.0315
0.0658
0.0051
0.0027
0.0000
building
0.0140
0.9789
0.0056
0.0015
0.0000
0.0000
low_veg
0.0239
0.0142
0.8960
0.0657
0.0002
0.0000
tree
0.0098
0.0048
0.0684
0.9169
0.0001
0.0000
car
0.2155
0.0123
0.0211
0.0085
0.7414
0.0012
clutter
--
--
--
--
--
--
Precision/Correctness
0.955
0.944
0.818
0.937
0.913
--
Recall/Completeness
0.895
0.979
0.896
0.917
0.741
--
F1
0.924
0.961
0.855
0.927
0.818
--

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_area10_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.7862
0.1197
0.0686
0.0232
0.0023
0.0000
building
0.0253
0.9516
0.0110
0.0121
0.0000
0.0000
low_veg
0.0626
0.0579
0.6791
0.2001
0.0002
0.0000
tree
0.0161
0.0122
0.0796
0.8920
0.0002
0.0000
car
0.2999
0.1123
0.0118
0.0026
0.5734
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.929
0.794
0.727
0.797
0.811
--
Recall/Completeness
0.786
0.952
0.679
0.892
0.573
--
F1
0.852
0.866
0.702
0.842
0.672
--

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_area10_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8177
0.1071
0.0619
0.0121
0.0013
0.0000
building
0.0204
0.9635
0.0075
0.0085
0.0000
0.0000
low_veg
0.0592
0.0416
0.7239
0.1750
0.0002
0.0000
tree
0.0073
0.0065
0.0608
0.9253
0.0001
0.0000
car
0.1934
0.1241
0.0070
0.0000
0.6755
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.948
0.823
0.764
0.836
0.864
--
Recall/Completeness
0.818
0.964
0.724
0.925
0.675
--
F1
0.878
0.888
0.743
0.878
0.758
--

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_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8466
0.0472
0.0617
0.0429
0.0015
0.0000
building
0.0276
0.9497
0.0144
0.0082
0.0000
0.0000
low_veg
0.0286
0.0371
0.7282
0.2060
0.0000
0.0000
tree
0.0094
0.0098
0.0842
0.8965
0.0000
0.0000
car
0.3245
0.0236
0.0311
0.0071
0.6137
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.865
0.895
0.831
0.831
0.933
--
Recall/Completeness
0.847
0.950
0.728
0.896
0.614
--
F1
0.856
0.922
0.776
0.863
0.741
--

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_area12_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8754
0.0446
0.0531
0.0265
0.0003
0.0000
building
0.0262
0.9649
0.0062
0.0027
0.0000
0.0000
low_veg
0.0260
0.0264
0.7671
0.1805
0.0000
0.0000
tree
0.0049
0.0050
0.0695
0.9206
0.0000
0.0000
car
0.2044
0.0275
0.0279
0.0011
0.7390
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.892
0.922
0.862
0.861
0.983
--
Recall/Completeness
0.875
0.965
0.767
0.921
0.739
--
F1
0.884
0.943
0.812
0.890
0.844
--

Overall accuracy 0.878

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area14_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.7808
0.0597
0.1216
0.0333
0.0046
0.0000
building
0.0073
0.9751
0.0104
0.0072
0.0000
0.0000
low_veg
0.0514
0.0750
0.7028
0.1707
0.0001
0.0000
tree
0.0185
0.0181
0.1058
0.8576
0.0000
0.0000
car
0.1796
0.0004
0.0000
0.0059
0.8141
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.895
0.815
0.733
0.846
0.662
--
Recall/Completeness
0.781
0.975
0.703
0.858
0.814
--
F1
0.834
0.888
0.717
0.852
0.730
--

Overall accuracy 0.821

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
0.7971
0.0553
0.1203
0.0233
0.0040
0.0000
building
0.0042
0.9882
0.0050
0.0026
0.0000
0.0000
low_veg
0.0451
0.0572
0.7385
0.1592
0.0001
0.0000
tree
0.0114
0.0105
0.0946
0.8834
0.0000
0.0000
car
0.0677
0.0000
0.0000
0.0022
0.9301
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.921
0.849
0.751
0.868
0.656
--
Recall/Completeness
0.797
0.988
0.738
0.883
0.930
--
F1
0.855
0.913
0.745
0.876
0.769
--

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_area16_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.7953
0.0382
0.0919
0.0730
0.0017
0.0000
building
0.0291
0.9356
0.0200
0.0153
0.0000
0.0000
low_veg
0.0134
0.0184
0.8198
0.1473
0.0000
0.0010
tree
0.0186
0.0062
0.0875
0.8878
0.0000
0.0000
car
0.2621
0.0004
0.0584
0.0231
0.6560
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.881
0.924
0.830
0.849
0.847
--
Recall/Completeness
0.795
0.936
0.820
0.888
0.656
--
F1
0.836
0.930
0.825
0.868
0.739
--

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_area16_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8317
0.0332
0.0833
0.0509
0.0007
0.0000
building
0.0254
0.9559
0.0114
0.0074
0.0000
0.0000
low_veg
0.0106
0.0116
0.8470
0.1297
0.0000
0.0011
tree
0.0121
0.0025
0.0754
0.9100
0.0000
0.0000
car
0.1455
0.0000
0.0525
0.0161
0.7859
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.910
0.948
0.856
0.876
0.917
--
Recall/Completeness
0.832
0.956
0.847
0.910
0.786
--
F1
0.869
0.952
0.851
0.892
0.846
--

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_area20_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8462
0.0603
0.0222
0.0691
0.0023
0.0000
building
0.0035
0.9841
0.0034
0.0090
0.0000
0.0000
low_veg
0.0344
0.0570
0.6372
0.2710
0.0003
0.0000
tree
0.0069
0.0025
0.0236
0.9670
0.0000
0.0000
car
0.2356
0.0531
0.0404
0.0208
0.6501
0.0000
clutter
0.0000
0.9993
0.0002
0.0005
0.0000
0.0000
Precision/Correctness
0.939
0.758
0.892
0.854
0.840
0.000
Recall/Completeness
0.846
0.984
0.637
0.967
0.650
0.000
F1
0.890
0.856
0.743
0.907
0.733
-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
0.8827
0.0493
0.0207
0.0466
0.0007
0.0000
building
0.0013
0.9942
0.0015
0.0031
0.0000
0.0000
low_veg
0.0286
0.0414
0.6905
0.2391
0.0003
0.0000
tree
0.0033
0.0007
0.0170
0.9790
0.0000
0.0000
car
0.1367
0.0560
0.0358
0.0131
0.7584
0.0000
clutter
0.0000
1.0000
0.0000
0.0000
0.0000
0.0000
Precision/Correctness
0.961
0.782
0.917
0.883
0.920
0.000
Recall/Completeness
0.883
0.994
0.691
0.979
0.758
0.000
F1
0.920
0.875
0.788
0.929
0.831
-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
0.8716
0.0416
0.0425
0.0395
0.0048
0.0000
building
0.0278
0.9538
0.0106
0.0078
0.0000
0.0000
low_veg
0.0595
0.0659
0.6960
0.1786
0.0000
0.0000
tree
0.0209
0.0072
0.0542
0.9177
0.0000
0.0000
car
0.3226
0.0139
0.0389
0.0198
0.6049
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.913
0.855
0.817
0.840
0.810
--
Recall/Completeness
0.872
0.954
0.696
0.918
0.605
--
F1
0.892
0.902
0.752
0.877
0.693
--

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_area22_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9059
0.0327
0.0359
0.0222
0.0033
0.0000
building
0.0227
0.9686
0.0046
0.0041
0.0000
0.0000
low_veg
0.0560
0.0512
0.7436
0.1492
0.0000
0.0000
tree
0.0102
0.0035
0.0400
0.9463
0.0000
0.0000
car
0.2237
0.0173
0.0284
0.0117
0.7189
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.937
0.890
0.857
0.880
0.846
--
Recall/Completeness
0.906
0.969
0.744
0.946
0.719
--
F1
0.921
0.928
0.796
0.912
0.777
--

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_area24_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.7723
0.0696
0.1126
0.0424
0.0030
0.0000
building
0.0411
0.9097
0.0404
0.0088
0.0000
0.0000
low_veg
0.0116
0.0289
0.8660
0.0935
0.0000
0.0000
tree
0.0134
0.0147
0.1187
0.8531
0.0000
0.0000
car
0.3208
0.0264
0.0436
0.0032
0.6060
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.868
0.869
0.868
0.824
0.835
--
Recall/Completeness
0.772
0.910
0.866
0.853
0.606
--
F1
0.817
0.889
0.867
0.838
0.702
--

Overall accuracy 0.856

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area24_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8048
0.0575
0.1046
0.0312
0.0019
0.0000
building
0.0396
0.9204
0.0342
0.0059
0.0000
0.0000
low_veg
0.0090
0.0228
0.8882
0.0800
0.0000
0.0000
tree
0.0078
0.0097
0.1002
0.8822
0.0000
0.0000
car
0.1995
0.0348
0.0337
0.0009
0.7310
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.893
0.897
0.888
0.849
0.876
--
Recall/Completeness
0.805
0.920
0.888
0.882
0.731
--
F1
0.847
0.908
0.888
0.865
0.797
--

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_area27_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9028
0.0603
0.0227
0.0074
0.0068
0.0000
building
0.0450
0.9332
0.0176
0.0040
0.0001
0.0000
low_veg
0.0672
0.0558
0.6605
0.2163
0.0002
0.0000
tree
0.0162
0.0094
0.0525
0.9218
0.0001
0.0000
car
0.3881
0.0206
0.0087
0.0063
0.5763
0.0000
clutter
0.4671
0.4024
0.0876
0.0062
0.0364
0.0002
Precision/Correctness
0.867
0.909
0.871
0.666
0.888
1.000
Recall/Completeness
0.903
0.933
0.660
0.922
0.576
0.000
F1
0.885
0.921
0.751
0.773
0.699
0.000

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: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9317
0.0463
0.0160
0.0033
0.0027
0.0000
building
0.0363
0.9484
0.0137
0.0016
0.0001
0.0000
low_veg
0.0497
0.0369
0.7067
0.2067
0.0000
0.0000
tree
0.0080
0.0041
0.0388
0.9490
0.0000
0.0000
car
0.2795
0.0192
0.0063
0.0062
0.6887
0.0000
clutter
0.4675
0.4134
0.0749
0.0028
0.0411
0.0003
Precision/Correctness
0.905
0.937
0.904
0.694
0.945
1.000
Recall/Completeness
0.932
0.948
0.707
0.949
0.689
0.000
F1
0.918
0.942
0.793
0.802
0.797
0.001

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
0.9189
0.0295
0.0311
0.0163
0.0042
0.0000
building
0.0219
0.9552
0.0156
0.0072
0.0000
0.0000
low_veg
0.0554
0.0296
0.6107
0.3039
0.0003
0.0000
tree
0.0035
0.0035
0.0353
0.9577
0.0000
0.0000
car
0.3503
0.0152
0.0025
0.0097
0.6222
0.0000
clutter
0.3935
0.4275
0.0181
0.0263
0.0255
0.1091
Precision/Correctness
0.927
0.896
0.805
0.657
0.763
0.994
Recall/Completeness
0.919
0.955
0.611
0.958
0.622
0.109
F1
0.923
0.925
0.695
0.779
0.685
0.197

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_area29_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9448
0.0207
0.0232
0.0085
0.0028
0.0000
building
0.0178
0.9679
0.0103
0.0039
0.0000
0.0000
low_veg
0.0384
0.0162
0.6520
0.2933
0.0001
0.0000
tree
0.0009
0.0011
0.0262
0.9717
0.0000
0.0000
car
0.2453
0.0118
0.0013
0.0078
0.7338
0.0000
clutter
0.3603
0.4540
0.0172
0.0148
0.0250
0.1288
Precision/Correctness
0.948
0.920
0.847
0.695
0.797
0.999
Recall/Completeness
0.945
0.968
0.652
0.972
0.734
0.129
F1
0.946
0.943
0.737
0.810
0.764
0.228

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
0.9419
0.0244
0.0138
0.0102
0.0095
0.0003
building
0.0205
0.9666
0.0069
0.0030
0.0021
0.0008
low_veg
0.0402
0.0125
0.9029
0.0433
0.0008
0.0003
tree
0.0185
0.0120
0.0684
0.9006
0.0006
0.0000
car
0.1960
0.1302
0.0092
0.0122
0.6523
0.0000
clutter
0.4526
0.2928
0.0040
0.0299
0.0461
0.1746
Precision/Correctness
0.910
0.908
0.897
0.890
0.796
0.941
Recall/Completeness
0.942
0.967
0.903
0.901
0.652
0.175
F1
0.926
0.936
0.900
0.895
0.717
0.295

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_area31_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9646
0.0174
0.0098
0.0041
0.0041
0.0001
building
0.0133
0.9794
0.0041
0.0006
0.0019
0.0007
low_veg
0.0252
0.0061
0.9338
0.0346
0.0003
0.0000
tree
0.0042
0.0060
0.0544
0.9354
0.0001
0.0000
car
0.1183
0.1474
0.0051
0.0057
0.7235
0.0000
clutter
0.4113
0.3156
0.0021
0.0177
0.0489
0.2044
Precision/Correctness
0.940
0.928
0.926
0.931
0.850
0.964
Recall/Completeness
0.965
0.979
0.934
0.935
0.724
0.204
F1
0.952
0.953
0.930
0.933
0.782
0.337

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_area33_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9480
0.0330
0.0065
0.0065
0.0026
0.0035
building
0.0621
0.8620
0.0693
0.0055
0.0003
0.0008
low_veg
0.0823
0.0324
0.7622
0.1227
0.0004
0.0000
tree
0.0377
0.0090
0.1082
0.8450
0.0001
0.0000
car
0.3619
0.0279
0.0046
0.0027
0.5991
0.0038
clutter
0.4037
0.1197
0.0002
0.0027
0.0145
0.4591
Precision/Correctness
0.857
0.907
0.775
0.793
0.799
0.939
Recall/Completeness
0.948
0.862
0.762
0.845
0.599
0.459
F1
0.900
0.884
0.769
0.818
0.685
0.617

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_area33_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9643
0.0269
0.0032
0.0030
0.0013
0.0013
building
0.0559
0.8708
0.0697
0.0028
0.0002
0.0006
low_veg
0.0511
0.0210
0.8042
0.1234
0.0003
0.0000
tree
0.0177
0.0035
0.1017
0.8771
0.0000
0.0000
car
0.2437
0.0214
0.0031
0.0014
0.7259
0.0045
clutter
0.3682
0.1149
0.0000
0.0013
0.0151
0.5003
Precision/Correctness
0.887
0.930
0.789
0.812
0.841
0.971
Recall/Completeness
0.964
0.871
0.804
0.877
0.726
0.500
F1
0.924
0.899
0.796
0.843
0.779
0.660

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
0.8038
0.0989
0.0633
0.0316
0.0024
0.0000
building
0.0221
0.9546
0.0171
0.0062
0.0000
0.0000
low_veg
0.0444
0.0392
0.6386
0.2778
0.0000
0.0000
tree
0.0319
0.0111
0.0857
0.8712
0.0001
0.0000
car
0.3126
0.0262
0.0000
0.0214
0.6398
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.883
0.872
0.796
0.722
0.884
--
Recall/Completeness
0.804
0.955
0.639
0.871
0.640
--
F1
0.842
0.911
0.709
0.789
0.742
--

Overall accuracy 0.817

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
0.8494
0.0907
0.0447
0.0143
0.0009
0.0000
building
0.0157
0.9730
0.0098
0.0015
0.0000
0.0000
low_veg
0.0314
0.0259
0.6739
0.2688
0.0000
0.0000
tree
0.0125
0.0044
0.0656
0.9174
0.0001
0.0000
car
0.2166
0.0281
0.0000
0.0161
0.7392
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.928
0.902
0.852
0.750
0.949
--
Recall/Completeness
0.849
0.973
0.674
0.917
0.739
--
F1
0.887
0.936
0.752
0.825
0.831
--

Overall accuracy 0.856

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area38_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8704
0.0393
0.0642
0.0222
0.0040
0.0000
building
0.0215
0.9224
0.0490
0.0063
0.0007
0.0000
low_veg
0.0328
0.0451
0.8063
0.1156
0.0002
0.0000
tree
0.0174
0.0081
0.1123
0.8621
0.0000
0.0000
car
0.3032
0.0212
0.0781
0.0127
0.5848
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.918
0.903
0.812
0.808
0.810
--
Recall/Completeness
0.870
0.922
0.806
0.862
0.585
--
F1
0.893
0.913
0.809
0.834
0.679
--

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_area38_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9058
0.0343
0.0476
0.0104
0.0019
0.0000
building
0.0166
0.9438
0.0361
0.0030
0.0006
0.0000
low_veg
0.0193
0.0400
0.8415
0.0991
0.0001
0.0000
tree
0.0067
0.0037
0.0897
0.8999
0.0000
0.0000
car
0.2069
0.0223
0.0718
0.0049
0.6941
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.951
0.922
0.854
0.846
0.878
--
Recall/Completeness
0.906
0.944
0.842
0.900
0.694
--
F1
0.928
0.933
0.848
0.872
0.775
--

Overall accuracy 0.895

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image