Detailled semantic labeling (2D) result


Name Y. Sun
Affiliation Huazhong University of Science and Technology (HUST), Wuhan, China
Abbreviation HUSTW
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
0.920
0.030
0.030
0.014
0.006
0.000
building
0.054
0.924
0.013
0.009
0.001
0.000
low_veg
0.092
0.027
0.753
0.128
0.001
0.000
tree
0.030
0.006
0.100
0.863
0.000
0.000
car
0.260
0.049
0.005
0.003
0.683
0.000
clutter
0.551
0.325
0.010
0.028
0.085
0.000
Precision/Correctness
0.839
0.926
0.825
0.852
0.765
-nan
Recall/Completeness
0.920
0.924
0.753
0.863
0.683
0.000
F1
0.878
0.925
0.787
0.857
0.722
-nan

Overall accuracy 0.861

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
0.943
0.023
0.025
0.007
0.003
0.000
building
0.045
0.940
0.008
0.006
0.001
0.000
low_veg
0.076
0.017
0.792
0.113
0.000
0.000
tree
0.015
0.003
0.086
0.896
0.000
0.000
car
0.179
0.054
0.003
0.002
0.762
0.000
clutter
0.529
0.349
0.009
0.025
0.088
0.000
Precision/Correctness
0.873
0.947
0.855
0.880
0.797
-nan
Recall/Completeness
0.943
0.940
0.792
0.896
0.762
0.000
F1
0.906
0.944
0.823
0.888
0.779
-nan

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
0.9575
0.0123
0.0152
0.0095
0.0055
0.0000
building
0.0406
0.9428
0.0131
0.0033
0.0002
0.0000
low_veg
0.1241
0.0221
0.7098
0.1437
0.0004
0.0000
tree
0.0395
0.0076
0.1056
0.8471
0.0002
0.0000
car
0.2832
0.0210
0.0005
0.0011
0.6942
0.0000
clutter
0.9006
0.0454
0.0008
0.0499
0.0032
0.0000
Precision/Correctness
0.773
0.949
0.841
0.842
0.871
-nan
Recall/Completeness
0.958
0.943
0.710
0.847
0.694
0.000
F1
0.855
0.946
0.770
0.845
0.773
-nan

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_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9779
0.0075
0.0085
0.0025
0.0035
0.0000
building
0.0315
0.9593
0.0079
0.0012
0.0002
0.0000
low_veg
0.1057
0.0111
0.7456
0.1373
0.0003
0.0000
tree
0.0213
0.0040
0.0934
0.8813
0.0001
0.0000
car
0.1772
0.0189
0.0000
0.0002
0.8036
0.0000
clutter
0.9256
0.0439
0.0009
0.0264
0.0032
0.0000
Precision/Correctness
0.805
0.972
0.867
0.865
0.902
-nan
Recall/Completeness
0.978
0.959
0.746
0.881
0.804
0.000
F1
0.883
0.965
0.802
0.873
0.850
-nan

Overall accuracy 0.873

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area4_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9224
0.0608
0.0069
0.0036
0.0062
0.0000
building
0.0538
0.9387
0.0057
0.0017
0.0001
0.0000
low_veg
0.2186
0.0556
0.4885
0.2349
0.0025
0.0000
tree
0.0725
0.0154
0.0924
0.8197
0.0000
0.0000
car
0.3935
0.0333
0.0010
0.0010
0.5712
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.846
0.961
0.693
0.759
0.806
--
Recall/Completeness
0.922
0.939
0.488
0.820
0.571
--
F1
0.882
0.950
0.573
0.788
0.669
--

Overall accuracy 0.901

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
0.9463
0.0425
0.0055
0.0016
0.0041
0.0000
building
0.0397
0.9545
0.0050
0.0007
0.0000
0.0000
low_veg
0.1717
0.0218
0.5482
0.2561
0.0022
0.0000
tree
0.0371
0.0059
0.0918
0.8652
0.0000
0.0000
car
0.3203
0.0274
0.0000
0.0003
0.6519
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.884
0.976
0.713
0.785
0.849
--
Recall/Completeness
0.946
0.955
0.548
0.865
0.652
--
F1
0.914
0.965
0.620
0.823
0.738
--

Overall accuracy 0.928

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
0.9123
0.0590
0.0149
0.0070
0.0068
0.0000
building
0.0463
0.9427
0.0070
0.0039
0.0001
0.0000
low_veg
0.1401
0.0524
0.6516
0.1543
0.0017
0.0000
tree
0.0258
0.0042
0.0581
0.9116
0.0002
0.0000
car
0.2980
0.0085
0.0005
0.0011
0.6919
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.845
0.934
0.752
0.931
0.848
--
Recall/Completeness
0.912
0.943
0.652
0.912
0.692
--
F1
0.878
0.938
0.698
0.921
0.762
--

Overall accuracy 0.891

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area6_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9416
0.0434
0.0098
0.0019
0.0033
0.0000
building
0.0360
0.9586
0.0041
0.0012
0.0001
0.0000
low_veg
0.1152
0.0369
0.7080
0.1388
0.0012
0.0000
tree
0.0104
0.0016
0.0484
0.9395
0.0001
0.0000
car
0.2128
0.0031
0.0003
0.0002
0.7836
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.889
0.957
0.791
0.951
0.909
--
Recall/Completeness
0.942
0.959
0.708
0.940
0.784
--
F1
0.915
0.958
0.747
0.945
0.842
--

Overall accuracy 0.922

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
0.8977
0.0253
0.0644
0.0077
0.0049
0.0000
building
0.0297
0.9528
0.0119
0.0053
0.0004
0.0000
low_veg
0.0825
0.0230
0.8378
0.0564
0.0003
0.0000
tree
0.0347
0.0069
0.0950
0.8633
0.0001
0.0000
car
0.2998
0.0046
0.0118
0.0038
0.6800
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.885
0.939
0.782
0.933
0.871
--
Recall/Completeness
0.898
0.953
0.838
0.863
0.680
--
F1
0.892
0.946
0.809
0.897
0.764
--

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_area8_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9191
0.0196
0.0569
0.0019
0.0025
0.0000
building
0.0184
0.9727
0.0061
0.0025
0.0003
0.0000
low_veg
0.0620
0.0150
0.8746
0.0484
0.0000
0.0000
tree
0.0151
0.0033
0.0762
0.9054
0.0000
0.0000
car
0.2098
0.0043
0.0088
0.0024
0.7747
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.927
0.959
0.818
0.953
0.919
--
Recall/Completeness
0.919
0.973
0.875
0.905
0.775
--
F1
0.923
0.966
0.846
0.929
0.841
--

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_area10_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8672
0.0634
0.0472
0.0171
0.0051
0.0000
building
0.0212
0.9515
0.0126
0.0131
0.0016
0.0000
low_veg
0.1068
0.0378
0.7151
0.1396
0.0007
0.0000
tree
0.0206
0.0081
0.0760
0.8953
0.0000
0.0000
car
0.2305
0.0411
0.0102
0.0022
0.7160
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.916
0.874
0.776
0.844
0.676
--
Recall/Completeness
0.867
0.951
0.715
0.895
0.716
--
F1
0.891
0.911
0.744
0.869
0.695
--

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_area10_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8957
0.0514
0.0422
0.0070
0.0037
0.0000
building
0.0139
0.9666
0.0086
0.0093
0.0015
0.0000
low_veg
0.1000
0.0245
0.7630
0.1118
0.0008
0.0000
tree
0.0090
0.0038
0.0593
0.9279
0.0000
0.0000
car
0.1571
0.0427
0.0086
0.0000
0.7915
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.938
0.904
0.810
0.886
0.683
--
Recall/Completeness
0.896
0.967
0.763
0.928
0.792
--
F1
0.916
0.934
0.786
0.907
0.734
--

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_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9117
0.0280
0.0269
0.0292
0.0042
0.0000
building
0.1796
0.8048
0.0074
0.0069
0.0013
0.0000
low_veg
0.0835
0.0306
0.7327
0.1523
0.0009
0.0000
tree
0.0183
0.0079
0.1226
0.8512
0.0000
0.0000
car
0.1527
0.0000
0.0149
0.0028
0.8296
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.662
0.907
0.807
0.864
0.790
--
Recall/Completeness
0.912
0.805
0.733
0.851
0.830
--
F1
0.767
0.853
0.768
0.857
0.809
--

Overall accuracy 0.816

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
0.9353
0.0251
0.0215
0.0171
0.0009
0.0000
building
0.1866
0.8072
0.0028
0.0020
0.0014
0.0000
low_veg
0.0795
0.0208
0.7694
0.1294
0.0009
0.0000
tree
0.0104
0.0038
0.1072
0.8786
0.0000
0.0000
car
0.0697
0.0000
0.0130
0.0000
0.9172
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.680
0.935
0.834
0.892
0.840
--
Recall/Completeness
0.935
0.807
0.769
0.879
0.917
--
F1
0.787
0.866
0.800
0.885
0.877
--

Overall accuracy 0.842

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
0.8618
0.0357
0.0672
0.0317
0.0036
0.0000
building
0.0255
0.9537
0.0122
0.0086
0.0000
0.0000
low_veg
0.1187
0.0509
0.6797
0.1501
0.0007
0.0000
tree
0.0400
0.0113
0.1147
0.8340
0.0000
0.0000
car
0.1300
0.0049
0.0000
0.0037
0.8613
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.803
0.871
0.755
0.856
0.691
--
Recall/Completeness
0.862
0.954
0.680
0.834
0.861
--
F1
0.832
0.910
0.716
0.845
0.767
--

Overall accuracy 0.822

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
0.8789
0.0319
0.0640
0.0225
0.0026
0.0000
building
0.0176
0.9730
0.0058
0.0035
0.0000
0.0000
low_veg
0.1115
0.0371
0.7121
0.1385
0.0008
0.0000
tree
0.0297
0.0055
0.1045
0.8602
0.0000
0.0000
car
0.0418
0.0013
0.0000
0.0010
0.9558
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.834
0.901
0.775
0.878
0.697
--
Recall/Completeness
0.879
0.973
0.712
0.860
0.956
--
F1
0.856
0.936
0.742
0.869
0.806
--

Overall accuracy 0.848

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
0.8651
0.0197
0.0665
0.0445
0.0042
0.0000
building
0.0396
0.9328
0.0117
0.0157
0.0002
0.0000
low_veg
0.0367
0.0154
0.7774
0.1701
0.0004
0.0000
tree
0.0313
0.0050
0.1098
0.8538
0.0000
0.0000
car
0.1299
0.0070
0.0027
0.0043
0.8561
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.818
0.946
0.814
0.839
0.708
--
Recall/Completeness
0.865
0.933
0.777
0.854
0.856
--
F1
0.841
0.939
0.795
0.846
0.775
--

Overall accuracy 0.847

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area16_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8947
0.0155
0.0608
0.0271
0.0019
0.0000
building
0.0327
0.9555
0.0050
0.0067
0.0001
0.0000
low_veg
0.0310
0.0095
0.8027
0.1564
0.0004
0.0000
tree
0.0212
0.0022
0.0990
0.8775
0.0000
0.0000
car
0.0621
0.0034
0.0039
0.0011
0.9295
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.854
0.966
0.837
0.862
0.776
--
Recall/Completeness
0.895
0.955
0.803
0.878
0.929
--
F1
0.874
0.961
0.819
0.870
0.846
--

Overall accuracy 0.872

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
0.8621
0.0262
0.0636
0.0412
0.0069
0.0000
building
0.0227
0.9465
0.0188
0.0119
0.0001
0.0000
low_veg
0.0798
0.0200
0.7304
0.1697
0.0000
0.0000
tree
0.0117
0.0010
0.0588
0.9285
0.0000
0.0000
car
0.2550
0.0008
0.0242
0.0076
0.7124
0.0000
clutter
0.0905
0.8570
0.0509
0.0016
0.0000
0.0000
Precision/Correctness
0.863
0.825
0.773
0.898
0.676
-nan
Recall/Completeness
0.862
0.946
0.730
0.929
0.712
0.000
F1
0.863
0.882
0.751
0.913
0.694
-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
0.8916
0.0179
0.0611
0.0239
0.0054
0.0000
building
0.0190
0.9606
0.0149
0.0055
0.0001
0.0000
low_veg
0.0730
0.0099
0.7762
0.1408
0.0000
0.0000
tree
0.0055
0.0002
0.0473
0.9470
0.0000
0.0000
car
0.1947
0.0004
0.0184
0.0018
0.7847
0.0000
clutter
0.0852
0.8674
0.0469
0.0005
0.0000
0.0000
Precision/Correctness
0.891
0.842
0.800
0.926
0.678
-nan
Recall/Completeness
0.892
0.961
0.776
0.947
0.785
0.000
F1
0.891
0.897
0.788
0.936
0.727
-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_area22_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9181
0.0252
0.0242
0.0269
0.0055
0.0000
building
0.0371
0.9464
0.0101
0.0062
0.0002
0.0000
low_veg
0.1551
0.0341
0.6778
0.1327
0.0002
0.0000
tree
0.0328
0.0034
0.0572
0.9065
0.0001
0.0000
car
0.3320
0.0069
0.0059
0.0031
0.6521
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.852
0.913
0.840
0.877
0.792
--
Recall/Completeness
0.918
0.946
0.678
0.907
0.652
--
F1
0.884
0.930
0.750
0.892
0.715
--

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_area22_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9446
0.0185
0.0203
0.0135
0.0032
0.0000
building
0.0297
0.9641
0.0042
0.0020
0.0001
0.0000
low_veg
0.1506
0.0217
0.7231
0.1044
0.0002
0.0000
tree
0.0151
0.0010
0.0425
0.9413
0.0001
0.0000
car
0.2553
0.0085
0.0036
0.0001
0.7325
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.881
0.943
0.878
0.915
0.846
--
Recall/Completeness
0.945
0.964
0.723
0.941
0.733
--
F1
0.912
0.953
0.793
0.928
0.785
--

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_area24_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8251
0.0389
0.0953
0.0358
0.0049
0.0000
building
0.0582
0.8950
0.0288
0.0174
0.0007
0.0000
low_veg
0.0374
0.0213
0.8740
0.0669
0.0004
0.0000
tree
0.0225
0.0090
0.1623
0.8061
0.0000
0.0000
car
0.3180
0.0000
0.0108
0.0042
0.6670
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.783
0.910
0.856
0.850
0.714
--
Recall/Completeness
0.825
0.895
0.874
0.806
0.667
--
F1
0.804
0.902
0.865
0.828
0.690
--

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_area24_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8527
0.0296
0.0885
0.0262
0.0029
0.0000
building
0.0549
0.9078
0.0228
0.0138
0.0007
0.0000
low_veg
0.0331
0.0161
0.8931
0.0572
0.0004
0.0000
tree
0.0149
0.0056
0.1398
0.8398
0.0000
0.0000
car
0.2478
0.0000
0.0089
0.0009
0.7424
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.809
0.933
0.878
0.874
0.731
--
Recall/Completeness
0.853
0.908
0.893
0.840
0.742
--
F1
0.831
0.920
0.885
0.856
0.737
--

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_area27_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9459
0.0244
0.0122
0.0056
0.0120
0.0000
building
0.0640
0.9219
0.0080
0.0054
0.0007
0.0000
low_veg
0.1326
0.0302
0.6700
0.1670
0.0002
0.0000
tree
0.0196
0.0059
0.0501
0.9242
0.0002
0.0000
car
0.2591
0.0128
0.0012
0.0050
0.7218
0.0000
clutter
0.7624
0.0845
0.0124
0.0141
0.1266
0.0000
Precision/Correctness
0.833
0.956
0.918
0.717
0.841
-nan
Recall/Completeness
0.946
0.922
0.670
0.924
0.722
0.000
F1
0.886
0.939
0.775
0.808
0.777
-nan

Overall accuracy 0.872

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
0.9703
0.0163
0.0079
0.0018
0.0037
0.0000
building
0.0502
0.9417
0.0043
0.0032
0.0005
0.0000
low_veg
0.1109
0.0160
0.7187
0.1544
0.0001
0.0000
tree
0.0090
0.0019
0.0342
0.9549
0.0000
0.0000
car
0.1809
0.0120
0.0002
0.0044
0.8025
0.0000
clutter
0.7550
0.0824
0.0030
0.0107
0.1489
0.0000
Precision/Correctness
0.870
0.975
0.948
0.750
0.922
-nan
Recall/Completeness
0.970
0.942
0.719
0.955
0.803
0.000
F1
0.917
0.958
0.818
0.840
0.858
-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_area29_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9458
0.0166
0.0207
0.0108
0.0061
0.0000
building
0.0402
0.9444
0.0082
0.0063
0.0009
0.0000
low_veg
0.0937
0.0286
0.6091
0.2682
0.0004
0.0000
tree
0.0097
0.0024
0.0246
0.9633
0.0000
0.0000
car
0.2549
0.0039
0.0003
0.0072
0.7336
0.0000
clutter
0.5335
0.3294
0.0036
0.0079
0.1256
0.0000
Precision/Correctness
0.899
0.923
0.867
0.695
0.598
-nan
Recall/Completeness
0.946
0.944
0.609
0.963
0.734
0.000
F1
0.922
0.934
0.716
0.807
0.659
-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_area29_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9653
0.0102
0.0161
0.0045
0.0039
0.0000
building
0.0345
0.9573
0.0044
0.0031
0.0008
0.0000
low_veg
0.0647
0.0146
0.6650
0.2555
0.0003
0.0000
tree
0.0036
0.0005
0.0175
0.9783
0.0000
0.0000
car
0.1824
0.0009
0.0000
0.0051
0.8116
0.0000
clutter
0.5156
0.3427
0.0018
0.0017
0.1382
0.0000
Precision/Correctness
0.923
0.945
0.900
0.733
0.594
-nan
Recall/Completeness
0.965
0.957
0.665
0.978
0.812
0.000
F1
0.944
0.951
0.765
0.838
0.686
-nan

Overall accuracy 0.895

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
0.9737
0.0114
0.0063
0.0014
0.0072
0.0000
building
0.0654
0.9248
0.0050
0.0012
0.0036
0.0000
low_veg
0.0728
0.0092
0.8957
0.0219
0.0004
0.0000
tree
0.0624
0.0053
0.1250
0.8062
0.0011
0.0000
car
0.1690
0.2069
0.0027
0.0023
0.6192
0.0000
clutter
0.4765
0.3525
0.0075
0.0719
0.0916
0.0000
Precision/Correctness
0.867
0.909
0.879
0.932
0.759
-nan
Recall/Completeness
0.974
0.925
0.896
0.806
0.619
0.000
F1
0.917
0.917
0.887
0.865
0.682
-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_area31_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9849
0.0073
0.0048
0.0001
0.0029
0.0000
building
0.0530
0.9428
0.0010
0.0001
0.0031
0.0000
low_veg
0.0458
0.0061
0.9311
0.0169
0.0001
0.0000
tree
0.0262
0.0020
0.1076
0.8640
0.0003
0.0000
car
0.1064
0.2301
0.0010
0.0005
0.6620
0.0000
clutter
0.4159
0.4025
0.0047
0.0799
0.0970
0.0000
Precision/Correctness
0.904
0.923
0.908
0.949
0.792
-nan
Recall/Completeness
0.985
0.943
0.931
0.864
0.662
0.000
F1
0.943
0.933
0.919
0.905
0.721
-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_area33_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9861
0.0064
0.0023
0.0022
0.0030
0.0000
building
0.1257
0.8007
0.0147
0.0559
0.0030
0.0000
low_veg
0.1125
0.0132
0.8276
0.0445
0.0022
0.0000
tree
0.0525
0.0071
0.1451
0.7953
0.0000
0.0000
car
0.2548
0.0403
0.0026
0.0010
0.7013
0.0000
clutter
0.6531
0.1939
0.0007
0.0109
0.1415
0.0000
Precision/Correctness
0.795
0.935
0.862
0.773
0.473
-nan
Recall/Completeness
0.986
0.801
0.828
0.795
0.701
0.000
F1
0.880
0.863
0.844
0.784
0.565
-nan

Overall accuracy 0.831

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
0.9937
0.0039
0.0006
0.0004
0.0015
0.0000
building
0.1184
0.8094
0.0131
0.0564
0.0027
0.0000
low_veg
0.0731
0.0064
0.8767
0.0418
0.0020
0.0000
tree
0.0236
0.0016
0.1380
0.8368
0.0000
0.0000
car
0.1643
0.0482
0.0004
0.0002
0.7869
0.0000
clutter
0.6233
0.2122
0.0003
0.0121
0.1520
0.0000
Precision/Correctness
0.824
0.947
0.879
0.781
0.457
-nan
Recall/Completeness
0.994
0.809
0.877
0.837
0.787
0.000
F1
0.901
0.873
0.878
0.808
0.578
-nan

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_area35_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9037
0.0403
0.0395
0.0152
0.0013
0.0000
building
0.0747
0.9087
0.0108
0.0046
0.0012
0.0000
low_veg
0.0902
0.0178
0.6894
0.2023
0.0004
0.0000
tree
0.0405
0.0060
0.1226
0.8308
0.0001
0.0000
car
0.3452
0.0104
0.0040
0.0055
0.6348
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.807
0.938
0.805
0.779
0.861
--
Recall/Completeness
0.904
0.909
0.689
0.831
0.635
--
F1
0.852
0.923
0.743
0.804
0.731
--

Overall accuracy 0.833

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area35_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9366
0.0336
0.0257
0.0037
0.0004
0.0000
building
0.0621
0.9318
0.0041
0.0008
0.0011
0.0000
low_veg
0.0690
0.0093
0.7263
0.1951
0.0004
0.0000
tree
0.0143
0.0016
0.1009
0.8832
0.0000
0.0000
car
0.2499
0.0129
0.0009
0.0013
0.7350
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.855
0.960
0.853
0.805
0.894
--
Recall/Completeness
0.937
0.932
0.726
0.883
0.735
--
F1
0.894
0.946
0.785
0.842
0.807
--

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_area38_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9293
0.0312
0.0259
0.0093
0.0042
0.0000
building
0.0211
0.9393
0.0312
0.0071
0.0013
0.0000
low_veg
0.0765
0.0283
0.8298
0.0651
0.0004
0.0000
tree
0.0308
0.0057
0.1398
0.8237
0.0000
0.0000
car
0.2363
0.0585
0.0204
0.0025
0.6823
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.877
0.930
0.846
0.877
0.808
--
Recall/Completeness
0.929
0.939
0.830
0.824
0.682
--
F1
0.902
0.935
0.838
0.849
0.740
--

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: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9501
0.0280
0.0168
0.0027
0.0024
0.0000
building
0.0127
0.9601
0.0224
0.0037
0.0011
0.0000
low_veg
0.0589
0.0222
0.8663
0.0523
0.0003
0.0000
tree
0.0126
0.0024
0.1168
0.8682
0.0000
0.0000
car
0.1506
0.0650
0.0139
0.0002
0.7703
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.917
0.946
0.880
0.911
0.845
--
Recall/Completeness
0.950
0.960
0.866
0.868
0.770
--
F1
0.933
0.953
0.873
0.889
0.806
--

Overall accuracy 0.913

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image