Detailled semantic labeling (2D) result


Name Yansong Liu et al.
Affiliation Rochester Institute of Technology
Abbreviation RIT_L6
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
0.887
0.039
0.051
0.018
0.005
0.000
building
0.082
0.877
0.034
0.005
0.002
0.000
low_veg
0.063
0.029
0.756
0.151
0.001
0.000
tree
0.020
0.005
0.100
0.875
0.000
0.000
car
0.293
0.057
0.022
0.009
0.620
0.000
clutter
0.614
0.273
0.056
0.013
0.044
0.000
Precision/Correctness
0.835
0.913
0.780
0.835
0.765
-nan
Recall/Completeness
0.887
0.877
0.756
0.875
0.620
0.000
F1
0.860
0.895
0.768
0.854
0.684
-nan

Overall accuracy 0.842

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
0.919
0.030
0.040
0.008
0.003
0.000
building
0.074
0.896
0.026
0.002
0.002
0.000
low_veg
0.052
0.019
0.792
0.137
0.001
0.000
tree
0.010
0.002
0.081
0.907
0.000
0.000
car
0.199
0.057
0.013
0.005
0.726
0.000
clutter
0.600
0.290
0.055
0.007
0.048
0.000
Precision/Correctness
0.864
0.938
0.821
0.865
0.798
-nan
Recall/Completeness
0.919
0.896
0.792
0.907
0.726
0.000
F1
0.891
0.917
0.806
0.886
0.760
-nan

Overall accuracy 0.874
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9302
0.0174
0.0328
0.0139
0.0057
0.0000
building
0.0637
0.9068
0.0243
0.0036
0.0016
0.0000
low_veg
0.0988
0.0356
0.6916
0.1736
0.0004
0.0000
tree
0.0306
0.0088
0.0999
0.8606
0.0001
0.0000
car
0.3020
0.0205
0.0115
0.0049
0.6611
0.0000
clutter
0.8489
0.0008
0.1096
0.0371
0.0036
0.0000
Precision/Correctness
0.777
0.930
0.806
0.817
0.837
-nan
Recall/Completeness
0.930
0.907
0.692
0.861
0.661
0.000
F1
0.847
0.918
0.745
0.838
0.739
-nan

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_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9613
0.0117
0.0196
0.0043
0.0031
0.0000
building
0.0540
0.9276
0.0157
0.0010
0.0016
0.0000
low_veg
0.0843
0.0243
0.7236
0.1674
0.0003
0.0000
tree
0.0161
0.0050
0.0854
0.8934
0.0000
0.0000
car
0.1885
0.0123
0.0059
0.0020
0.7913
0.0000
clutter
0.8699
0.0007
0.1126
0.0132
0.0036
0.0000
Precision/Correctness
0.808
0.956
0.844
0.842
0.877
-nan
Recall/Completeness
0.961
0.928
0.724
0.893
0.791
0.000
F1
0.878
0.942
0.779
0.867
0.832
-nan

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_area4_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9035
0.0737
0.0141
0.0036
0.0051
0.0000
building
0.0880
0.8975
0.0106
0.0020
0.0020
0.0000
low_veg
0.2161
0.0846
0.4151
0.2824
0.0018
0.0000
tree
0.0547
0.0107
0.1016
0.8319
0.0011
0.0000
car
0.4001
0.0199
0.0067
0.0025
0.5708
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.796
0.951
0.552
0.730
0.753
--
Recall/Completeness
0.904
0.897
0.415
0.832
0.571
--
F1
0.846
0.923
0.474
0.777
0.649
--

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_area4_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9382
0.0468
0.0110
0.0010
0.0030
0.0000
building
0.0758
0.9123
0.0090
0.0009
0.0020
0.0000
low_veg
0.1875
0.0497
0.4492
0.3121
0.0015
0.0000
tree
0.0240
0.0029
0.0927
0.8799
0.0006
0.0000
car
0.3100
0.0119
0.0038
0.0012
0.6731
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.825
0.972
0.583
0.756
0.778
--
Recall/Completeness
0.938
0.912
0.449
0.880
0.673
--
F1
0.878
0.941
0.508
0.813
0.722
--

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_area6_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8805
0.0528
0.0483
0.0123
0.0061
0.0000
building
0.0838
0.8804
0.0316
0.0033
0.0010
0.0000
low_veg
0.0581
0.0238
0.7711
0.1466
0.0004
0.0000
tree
0.0124
0.0028
0.0740
0.9105
0.0001
0.0000
car
0.2915
0.0374
0.0197
0.0045
0.6469
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.841
0.944
0.649
0.929
0.844
--
Recall/Completeness
0.880
0.880
0.771
0.911
0.647
--
F1
0.861
0.911
0.705
0.920
0.732
--

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_area6_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9231
0.0359
0.0339
0.0042
0.0029
0.0000
building
0.0738
0.9013
0.0232
0.0010
0.0007
0.0000
low_veg
0.0469
0.0103
0.8144
0.1280
0.0003
0.0000
tree
0.0044
0.0009
0.0575
0.9370
0.0001
0.0000
car
0.1950
0.0262
0.0105
0.0015
0.7667
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.873
0.967
0.702
0.953
0.902
--
Recall/Completeness
0.923
0.901
0.814
0.937
0.767
--
F1
0.897
0.933
0.754
0.945
0.829
--

Overall accuracy 0.907

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
0.8768
0.0306
0.0788
0.0091
0.0046
0.0000
building
0.0589
0.9095
0.0264
0.0037
0.0015
0.0000
low_veg
0.0649
0.0188
0.8317
0.0839
0.0007
0.0000
tree
0.0207
0.0066
0.0985
0.8741
0.0000
0.0000
car
0.3226
0.0199
0.0339
0.0097
0.6139
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.882
0.932
0.749
0.911
0.843
--
Recall/Completeness
0.877
0.909
0.832
0.874
0.614
--
F1
0.879
0.921
0.788
0.892
0.710
--

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_area8_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9097
0.0229
0.0627
0.0024
0.0023
0.0000
building
0.0490
0.9302
0.0181
0.0013
0.0014
0.0000
low_veg
0.0511
0.0103
0.8646
0.0734
0.0005
0.0000
tree
0.0081
0.0028
0.0742
0.9148
0.0000
0.0000
car
0.2268
0.0122
0.0213
0.0063
0.7334
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.915
0.957
0.800
0.935
0.889
--
Recall/Completeness
0.910
0.930
0.865
0.915
0.733
--
F1
0.912
0.943
0.831
0.925
0.804
--

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_area10_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8204
0.0886
0.0689
0.0184
0.0037
0.0000
building
0.0550
0.9030
0.0310
0.0101
0.0010
0.0000
low_veg
0.0851
0.0341
0.7299
0.1497
0.0011
0.0000
tree
0.0129
0.0079
0.1003
0.8789
0.0000
0.0000
car
0.2807
0.0210
0.0432
0.0062
0.6489
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.904
0.839
0.704
0.835
0.715
--
Recall/Completeness
0.820
0.903
0.730
0.879
0.649
--
F1
0.860
0.870
0.716
0.856
0.680
--

Overall accuracy 0.835

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
0.8548
0.0768
0.0579
0.0078
0.0027
0.0000
building
0.0472
0.9219
0.0233
0.0067
0.0008
0.0000
low_veg
0.0826
0.0222
0.7692
0.1247
0.0012
0.0000
tree
0.0054
0.0038
0.0740
0.9168
0.0000
0.0000
car
0.1830
0.0194
0.0313
0.0014
0.7649
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.923
0.867
0.752
0.877
0.736
--
Recall/Completeness
0.855
0.922
0.769
0.917
0.765
--
F1
0.888
0.894
0.760
0.896
0.750
--

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_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8544
0.0389
0.0655
0.0370
0.0042
0.0000
building
0.1289
0.8424
0.0213
0.0069
0.0005
0.0000
low_veg
0.0445
0.0349
0.7514
0.1678
0.0014
0.0000
tree
0.0094
0.0065
0.1080
0.8758
0.0002
0.0000
car
0.2199
0.0720
0.0131
0.0107
0.6843
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.742
0.897
0.803
0.854
0.747
--
Recall/Completeness
0.854
0.842
0.751
0.876
0.684
--
F1
0.794
0.869
0.776
0.865
0.714
--

Overall accuracy 0.829

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
0.8894
0.0342
0.0542
0.0206
0.0016
0.0000
building
0.1321
0.8550
0.0103
0.0022
0.0004
0.0000
low_veg
0.0421
0.0234
0.7895
0.1437
0.0014
0.0000
tree
0.0046
0.0024
0.0898
0.9031
0.0002
0.0000
car
0.1162
0.0943
0.0054
0.0033
0.7809
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.762
0.929
0.838
0.884
0.790
--
Recall/Completeness
0.889
0.855
0.789
0.903
0.781
--
F1
0.821
0.890
0.813
0.893
0.785
--

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_area14_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8411
0.0270
0.0921
0.0350
0.0049
0.0000
building
0.0480
0.9114
0.0329
0.0067
0.0010
0.0000
low_veg
0.0905
0.0451
0.6882
0.1746
0.0016
0.0000
tree
0.0316
0.0078
0.1205
0.8399
0.0001
0.0000
car
0.1836
0.0003
0.0005
0.0154
0.8002
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.819
0.888
0.722
0.840
0.549
--
Recall/Completeness
0.841
0.911
0.688
0.840
0.800
--
F1
0.830
0.899
0.705
0.840
0.651
--

Overall accuracy 0.814

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
0.8618
0.0215
0.0880
0.0244
0.0042
0.0000
building
0.0412
0.9353
0.0202
0.0024
0.0010
0.0000
low_veg
0.0849
0.0304
0.7198
0.1632
0.0017
0.0000
tree
0.0223
0.0033
0.1074
0.8669
0.0001
0.0000
car
0.0701
0.0000
0.0000
0.0116
0.9183
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.848
0.923
0.748
0.863
0.530
--
Recall/Completeness
0.862
0.935
0.720
0.867
0.918
--
F1
0.855
0.929
0.734
0.865
0.672
--

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_area16_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.7978
0.0402
0.1063
0.0525
0.0032
0.0000
building
0.0563
0.8871
0.0445
0.0112
0.0009
0.0000
low_veg
0.0200
0.0235
0.8185
0.1364
0.0017
0.0000
tree
0.0201
0.0066
0.1154
0.8577
0.0001
0.0000
car
0.1883
0.0101
0.0268
0.0209
0.7538
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.839
0.910
0.784
0.861
0.580
--
Recall/Completeness
0.798
0.887
0.818
0.858
0.754
--
F1
0.818
0.898
0.801
0.860
0.655
--

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_area16_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8381
0.0339
0.0947
0.0314
0.0019
0.0000
building
0.0536
0.9084
0.0329
0.0042
0.0008
0.0000
low_veg
0.0168
0.0158
0.8432
0.1226
0.0017
0.0000
tree
0.0130
0.0025
0.1010
0.8833
0.0001
0.0000
car
0.0854
0.0043
0.0128
0.0080
0.8895
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.866
0.938
0.814
0.886
0.590
--
Recall/Completeness
0.838
0.908
0.843
0.883
0.890
--
F1
0.852
0.923
0.828
0.885
0.709
--

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_area20_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8124
0.0655
0.0756
0.0426
0.0039
0.0000
building
0.0122
0.9396
0.0390
0.0084
0.0008
0.0000
low_veg
0.0478
0.0340
0.7474
0.1702
0.0006
0.0000
tree
0.0065
0.0020
0.0525
0.9389
0.0001
0.0000
car
0.1296
0.1011
0.0328
0.0223
0.7142
0.0000
clutter
0.2944
0.6398
0.0609
0.0047
0.0002
0.0000
Precision/Correctness
0.880
0.800
0.763
0.899
0.738
-nan
Recall/Completeness
0.812
0.940
0.747
0.939
0.714
0.000
F1
0.845
0.864
0.755
0.919
0.726
-nan

Overall accuracy 0.850

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area20_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8473
0.0576
0.0700
0.0230
0.0022
0.0000
building
0.0105
0.9543
0.0314
0.0029
0.0008
0.0000
low_veg
0.0417
0.0216
0.7947
0.1415
0.0006
0.0000
tree
0.0024
0.0005
0.0393
0.9578
0.0000
0.0000
car
0.0593
0.0957
0.0204
0.0109
0.8138
0.0000
clutter
0.2890
0.6514
0.0565
0.0029
0.0002
0.0000
Precision/Correctness
0.901
0.822
0.797
0.927
0.778
-nan
Recall/Completeness
0.847
0.954
0.795
0.958
0.814
0.000
F1
0.873
0.883
0.796
0.942
0.795
-nan

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_area22_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8765
0.0322
0.0476
0.0365
0.0071
0.0000
building
0.0701
0.9031
0.0195
0.0062
0.0011
0.0000
low_veg
0.0821
0.0523
0.6934
0.1712
0.0010
0.0000
tree
0.0176
0.0044
0.0601
0.9179
0.0000
0.0000
car
0.3121
0.0339
0.0292
0.0221
0.6026
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.882
0.877
0.794
0.848
0.710
--
Recall/Completeness
0.877
0.903
0.693
0.918
0.603
--
F1
0.879
0.890
0.740
0.881
0.652
--

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_area22_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9133
0.0235
0.0396
0.0187
0.0049
0.0000
building
0.0641
0.9213
0.0110
0.0027
0.0009
0.0000
low_veg
0.0789
0.0372
0.7406
0.1424
0.0009
0.0000
tree
0.0068
0.0013
0.0426
0.9492
0.0000
0.0000
car
0.2258
0.0331
0.0180
0.0108
0.7124
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.906
0.915
0.842
0.888
0.750
--
Recall/Completeness
0.913
0.921
0.741
0.949
0.712
--
F1
0.909
0.918
0.788
0.917
0.731
--

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_area24_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8138
0.0374
0.1021
0.0394
0.0074
0.0000
building
0.0802
0.8478
0.0555
0.0150
0.0015
0.0000
low_veg
0.0295
0.0177
0.8626
0.0898
0.0004
0.0000
tree
0.0176
0.0071
0.1366
0.8386
0.0001
0.0000
car
0.2364
0.0249
0.0175
0.0090
0.7123
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.784
0.916
0.855
0.824
0.637
--
Recall/Completeness
0.814
0.848
0.863
0.839
0.712
--
F1
0.799
0.881
0.859
0.831
0.672
--

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_area24_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8468
0.0270
0.0925
0.0280
0.0057
0.0000
building
0.0761
0.8614
0.0487
0.0124
0.0014
0.0000
low_veg
0.0260
0.0122
0.8840
0.0775
0.0004
0.0000
tree
0.0117
0.0032
0.1147
0.8704
0.0001
0.0000
car
0.1387
0.0228
0.0043
0.0028
0.8313
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.809
0.944
0.878
0.849
0.639
--
Recall/Completeness
0.847
0.861
0.884
0.870
0.831
--
F1
0.827
0.901
0.881
0.859
0.723
--

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_area27_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9105
0.0438
0.0281
0.0071
0.0105
0.0000
building
0.1123
0.8558
0.0270
0.0036
0.0012
0.0000
low_veg
0.0858
0.0310
0.6922
0.1904
0.0006
0.0000
tree
0.0133
0.0053
0.0565
0.9248
0.0001
0.0000
car
0.3100
0.0397
0.0154
0.0063
0.6287
0.0000
clutter
0.3826
0.3693
0.1983
0.0028
0.0470
0.0000
Precision/Correctness
0.810
0.929
0.844
0.693
0.836
-nan
Recall/Completeness
0.911
0.856
0.692
0.925
0.629
0.000
F1
0.857
0.891
0.761
0.793
0.717
-nan

Overall accuracy 0.839

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
0.9444
0.0306
0.0183
0.0025
0.0042
0.0000
building
0.1016
0.8762
0.0197
0.0013
0.0012
0.0000
low_veg
0.0705
0.0174
0.7327
0.1791
0.0003
0.0000
tree
0.0056
0.0021
0.0372
0.9550
0.0000
0.0000
car
0.2189
0.0313
0.0102
0.0044
0.7352
0.0000
clutter
0.3715
0.3821
0.1801
0.0011
0.0652
0.0000
Precision/Correctness
0.840
0.956
0.889
0.726
0.902
-nan
Recall/Completeness
0.944
0.876
0.733
0.955
0.735
0.000
F1
0.889
0.914
0.803
0.825
0.810
-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_area29_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9262
0.0260
0.0298
0.0137
0.0043
0.0000
building
0.0516
0.9279
0.0139
0.0057
0.0010
0.0000
low_veg
0.0579
0.0266
0.6420
0.2730
0.0004
0.0000
tree
0.0054
0.0016
0.0426
0.9505
0.0000
0.0000
car
0.2922
0.0283
0.0190
0.0151
0.6453
0.0000
clutter
0.5448
0.3671
0.0412
0.0069
0.0401
0.0000
Precision/Correctness
0.901
0.905
0.809
0.684
0.722
-nan
Recall/Completeness
0.926
0.928
0.642
0.951
0.645
0.000
F1
0.913
0.916
0.716
0.795
0.681
-nan

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_area29_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9518
0.0181
0.0208
0.0064
0.0028
0.0000
building
0.0444
0.9438
0.0081
0.0029
0.0009
0.0000
low_veg
0.0363
0.0129
0.6894
0.2611
0.0004
0.0000
tree
0.0017
0.0004
0.0318
0.9661
0.0000
0.0000
car
0.1978
0.0267
0.0092
0.0131
0.7531
0.0000
clutter
0.5291
0.3895
0.0329
0.0029
0.0456
0.0000
Precision/Correctness
0.924
0.929
0.858
0.722
0.735
-nan
Recall/Completeness
0.952
0.944
0.689
0.966
0.753
0.000
F1
0.938
0.936
0.765
0.827
0.744
-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_area31_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9534
0.0175
0.0184
0.0042
0.0064
0.0000
building
0.1336
0.8455
0.0143
0.0028
0.0038
0.0000
low_veg
0.0702
0.0066
0.8788
0.0439
0.0004
0.0000
tree
0.0310
0.0035
0.1002
0.8651
0.0002
0.0000
car
0.2350
0.1828
0.0192
0.0093
0.5537
0.0000
clutter
0.6244
0.2293
0.0643
0.0205
0.0616
0.0000
Precision/Correctness
0.822
0.912
0.838
0.908
0.777
-nan
Recall/Completeness
0.953
0.846
0.879
0.865
0.554
0.000
F1
0.883
0.878
0.858
0.886
0.647
-nan

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_area31_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9708
0.0127
0.0130
0.0008
0.0027
0.0000
building
0.1218
0.8656
0.0082
0.0008
0.0035
0.0000
low_veg
0.0480
0.0035
0.9130
0.0354
0.0001
0.0000
tree
0.0095
0.0010
0.0796
0.9099
0.0000
0.0000
car
0.1574
0.2015
0.0102
0.0042
0.6268
0.0000
clutter
0.5912
0.2586
0.0682
0.0124
0.0696
0.0000
Precision/Correctness
0.852
0.929
0.881
0.940
0.811
-nan
Recall/Completeness
0.971
0.866
0.913
0.910
0.627
0.000
F1
0.907
0.896
0.897
0.925
0.707
-nan

Overall accuracy 0.886

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area33_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9630
0.0200
0.0128
0.0025
0.0017
0.0000
building
0.1237
0.7670
0.1011
0.0040
0.0041
0.0000
low_veg
0.0842
0.0547
0.6509
0.2088
0.0014
0.0000
tree
0.0457
0.0040
0.1456
0.8046
0.0002
0.0000
car
0.3345
0.0458
0.0096
0.0042
0.6059
0.0000
clutter
0.7070
0.1944
0.0155
0.0035
0.0796
0.0000
Precision/Correctness
0.794
0.889
0.665
0.709
0.549
-nan
Recall/Completeness
0.963
0.767
0.651
0.805
0.606
0.000
F1
0.870
0.824
0.658
0.754
0.576
-nan

Overall accuracy 0.785

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
0.9792
0.0136
0.0062
0.0005
0.0006
0.0000
building
0.1177
0.7776
0.0988
0.0019
0.0039
0.0000
low_veg
0.0551
0.0496
0.6709
0.2232
0.0013
0.0000
tree
0.0208
0.0013
0.1274
0.8504
0.0001
0.0000
car
0.2231
0.0430
0.0072
0.0011
0.7256
0.0000
clutter
0.6818
0.2092
0.0157
0.0031
0.0902
0.0000
Precision/Correctness
0.821
0.908
0.688
0.715
0.540
-nan
Recall/Completeness
0.979
0.778
0.671
0.850
0.726
0.000
F1
0.893
0.838
0.679
0.777
0.619
-nan

Overall accuracy 0.807

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
0.8522
0.0452
0.0808
0.0195
0.0023
0.0000
building
0.0976
0.8714
0.0245
0.0053
0.0012
0.0000
low_veg
0.0485
0.0202
0.7183
0.2128
0.0002
0.0000
tree
0.0294
0.0046
0.1416
0.8244
0.0001
0.0000
car
0.3459
0.0433
0.0070
0.0132
0.5907
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.818
0.929
0.748
0.765
0.821
--
Recall/Completeness
0.852
0.871
0.718
0.824
0.591
--
F1
0.835
0.899
0.733
0.794
0.687
--

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_area35_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9044
0.0383
0.0508
0.0055
0.0010
0.0000
building
0.0841
0.9008
0.0124
0.0016
0.0012
0.0000
low_veg
0.0351
0.0101
0.7477
0.2069
0.0002
0.0000
tree
0.0107
0.0014
0.1081
0.8798
0.0000
0.0000
car
0.2402
0.0432
0.0042
0.0040
0.7084
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.860
0.953
0.818
0.793
0.869
--
Recall/Completeness
0.904
0.901
0.748
0.880
0.708
--
F1
0.882
0.926
0.781
0.834
0.781
--

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_area38_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8847
0.0316
0.0649
0.0148
0.0041
0.0000
building
0.0702
0.8530
0.0692
0.0054
0.0021
0.0000
low_veg
0.0528
0.0206
0.8182
0.1079
0.0006
0.0000
tree
0.0203
0.0028
0.1216
0.8552
0.0001
0.0000
car
0.2855
0.0341
0.0589
0.0135
0.6080
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.858
0.935
0.795
0.824
0.765
--
Recall/Completeness
0.885
0.853
0.818
0.855
0.608
--
F1
0.871
0.892
0.806
0.839
0.677
--

Overall accuracy 0.850

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area38_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9208
0.0268
0.0454
0.0045
0.0024
0.0000
building
0.0626
0.8789
0.0542
0.0021
0.0021
0.0000
low_veg
0.0396
0.0131
0.8549
0.0918
0.0005
0.0000
tree
0.0077
0.0007
0.0953
0.8962
0.0000
0.0000
car
0.1929
0.0303
0.0462
0.0056
0.7250
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.891
0.954
0.840
0.862
0.796
--
Recall/Completeness
0.921
0.879
0.855
0.896
0.725
--
F1
0.905
0.915
0.848
0.879
0.759
--

Overall accuracy 0.886

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image