Detailled semantic labeling (2D) result


Name W. Sun
Affiliation Univ. of Calgary, Canada
Abbreviation UCal
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
0.859
0.047
0.043
0.042
0.009
0.000
building
0.071
0.885
0.029
0.015
0.000
0.000
low_veg
0.079
0.051
0.608
0.262
0.000
0.000
tree
0.026
0.009
0.054
0.911
0.000
0.000
car
0.616
0.046
0.021
0.020
0.297
0.000
clutter
0.554
0.313
0.012
0.023
0.014
0.083
Precision/Correctness
0.815
0.886
0.805
0.740
0.573
0.992
Recall/Completeness
0.859
0.885
0.608
0.911
0.297
0.083
F1
0.837
0.886
0.693
0.817
0.392
0.154

Overall accuracy 0.809

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
0.890
0.039
0.037
0.028
0.007
0.000
building
0.061
0.907
0.023
0.009
0.000
0.000
low_veg
0.067
0.042
0.647
0.244
0.000
0.000
tree
0.016
0.005
0.045
0.934
0.000
0.000
car
0.594
0.049
0.019
0.015
0.324
0.000
clutter
0.536
0.331
0.009
0.015
0.015
0.094
Precision/Correctness
0.848
0.909
0.837
0.773
0.605
0.997
Recall/Completeness
0.890
0.907
0.647
0.934
0.324
0.094
F1
0.868
0.908
0.730
0.846
0.422
0.172

Overall accuracy 0.841
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8834
0.0263
0.0410
0.0409
0.0085
0.0000
building
0.0529
0.9040
0.0285
0.0145
0.0001
0.0000
low_veg
0.1009
0.0454
0.5971
0.2562
0.0004
0.0000
tree
0.0323
0.0125
0.0594
0.8956
0.0000
0.0001
car
0.7117
0.0446
0.0014
0.0075
0.2349
0.0000
clutter
0.6198
0.0000
0.0000
0.0382
0.0000
0.3420
Precision/Correctness
0.766
0.906
0.823
0.742
0.619
0.995
Recall/Completeness
0.883
0.904
0.597
0.896
0.235
0.342
F1
0.821
0.905
0.692
0.811
0.341
0.509

Overall accuracy 0.801

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
0.9157
0.0217
0.0316
0.0246
0.0064
0.0000
building
0.0456
0.9260
0.0208
0.0075
0.0001
0.0000
low_veg
0.0868
0.0341
0.6337
0.2451
0.0003
0.0000
tree
0.0191
0.0087
0.0519
0.9202
0.0000
0.0001
car
0.6883
0.0482
0.0007
0.0035
0.2593
0.0000
clutter
0.6270
0.0000
0.0000
0.0199
0.0000
0.3531
Precision/Correctness
0.798
0.931
0.856
0.774
0.649
0.998
Recall/Completeness
0.916
0.926
0.634
0.920
0.259
0.353
F1
0.853
0.928
0.728
0.841
0.371
0.522

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_area4_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9019
0.0599
0.0148
0.0124
0.0109
0.0000
building
0.1159
0.8697
0.0091
0.0045
0.0009
0.0000
low_veg
0.2796
0.0622
0.3266
0.3310
0.0006
0.0000
tree
0.0763
0.0173
0.0614
0.8449
0.0000
0.0000
car
0.6410
0.0250
0.0002
0.0097
0.3242
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.744
0.958
0.541
0.658
0.560
--
Recall/Completeness
0.902
0.870
0.327
0.845
0.324
--
F1
0.816
0.912
0.407
0.740
0.411
--

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_area4_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9313
0.0404
0.0129
0.0072
0.0083
0.0000
building
0.0964
0.8923
0.0079
0.0025
0.0009
0.0000
low_veg
0.2439
0.0373
0.3592
0.3591
0.0005
0.0000
tree
0.0504
0.0094
0.0623
0.8779
0.0000
0.0000
car
0.6197
0.0180
0.0000
0.0071
0.3552
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.778
0.975
0.561
0.696
0.575
--
Recall/Completeness
0.931
0.892
0.359
0.878
0.355
--
F1
0.848
0.932
0.438
0.777
0.439
--

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_area6_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8804
0.0445
0.0326
0.0301
0.0125
0.0000
building
0.1087
0.8576
0.0172
0.0160
0.0005
0.0000
low_veg
0.0978
0.0318
0.5687
0.3016
0.0002
0.0000
tree
0.0239
0.0045
0.0379
0.9338
0.0000
0.0000
car
0.6609
0.0251
0.0075
0.0220
0.2845
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.778
0.945
0.708
0.855
0.580
--
Recall/Completeness
0.880
0.858
0.569
0.934
0.285
--
F1
0.826
0.899
0.631
0.893
0.382
--

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_area6_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9181
0.0304
0.0260
0.0167
0.0088
0.0000
building
0.0934
0.8841
0.0127
0.0095
0.0002
0.0000
low_veg
0.0810
0.0191
0.6258
0.2742
0.0000
0.0000
tree
0.0135
0.0020
0.0315
0.9530
0.0000
0.0000
car
0.6453
0.0188
0.0064
0.0150
0.3144
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.815
0.967
0.750
0.892
0.630
--
Recall/Completeness
0.918
0.884
0.626
0.953
0.314
--
F1
0.864
0.924
0.682
0.921
0.419
--

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_area8_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8509
0.0295
0.0718
0.0383
0.0095
0.0000
building
0.0572
0.9059
0.0268
0.0101
0.0000
0.0000
low_veg
0.0768
0.0156
0.7735
0.1335
0.0007
0.0000
tree
0.0360
0.0058
0.0688
0.8895
0.0000
0.0000
car
0.6456
0.0165
0.0588
0.0111
0.2680
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.848
0.937
0.767
0.839
0.593
--
Recall/Completeness
0.851
0.906
0.773
0.889
0.268
--
F1
0.849
0.921
0.770
0.864
0.369
--

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_area8_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8842
0.0233
0.0624
0.0234
0.0068
0.0000
building
0.0445
0.9320
0.0181
0.0054
0.0000
0.0000
low_veg
0.0612
0.0086
0.8126
0.1172
0.0004
0.0000
tree
0.0230
0.0026
0.0566
0.9178
0.0000
0.0000
car
0.6281
0.0140
0.0517
0.0076
0.2986
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.885
0.958
0.806
0.875
0.634
--
Recall/Completeness
0.884
0.932
0.813
0.918
0.299
--
F1
0.884
0.945
0.809
0.896
0.406
--

Overall accuracy 0.882

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area10_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.7909
0.1147
0.0474
0.0400
0.0070
0.0000
building
0.0584
0.8987
0.0199
0.0227
0.0002
0.0000
low_veg
0.0931
0.0605
0.5417
0.3041
0.0007
0.0000
tree
0.0297
0.0098
0.0544
0.9061
0.0000
0.0000
car
0.5857
0.0320
0.0187
0.0374
0.3261
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.880
0.792
0.738
0.715
0.451
--
Recall/Completeness
0.791
0.899
0.542
0.906
0.326
--
F1
0.833
0.842
0.625
0.800
0.378
--

Overall accuracy 0.793

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
0.8206
0.1053
0.0424
0.0259
0.0059
0.0000
building
0.0472
0.9215
0.0146
0.0165
0.0002
0.0000
low_veg
0.0899
0.0482
0.5828
0.2785
0.0006
0.0000
tree
0.0169
0.0056
0.0421
0.9354
0.0000
0.0000
car
0.5646
0.0308
0.0177
0.0346
0.3522
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.905
0.817
0.777
0.754
0.435
--
Recall/Completeness
0.821
0.922
0.583
0.935
0.352
--
F1
0.861
0.866
0.666
0.835
0.389
--

Overall accuracy 0.825

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
0.8645
0.0433
0.0223
0.0581
0.0117
0.0000
building
0.0994
0.8687
0.0129
0.0190
0.0000
0.0000
low_veg
0.0373
0.0543
0.5719
0.3362
0.0002
0.0000
tree
0.0110
0.0115
0.0466
0.9310
0.0000
0.0000
car
0.4757
0.0029
0.0115
0.0166
0.4933
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.772
0.864
0.879
0.759
0.591
--
Recall/Completeness
0.865
0.869
0.572
0.931
0.493
--
F1
0.816
0.866
0.693
0.836
0.538
--

Overall accuracy 0.803

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
0.8940
0.0398
0.0185
0.0392
0.0084
0.0000
building
0.1027
0.8813
0.0075
0.0085
0.0000
0.0000
low_veg
0.0343
0.0403
0.6158
0.3095
0.0001
0.0000
tree
0.0055
0.0061
0.0379
0.9505
0.0000
0.0000
car
0.4436
0.0008
0.0122
0.0071
0.5363
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.793
0.898
0.905
0.788
0.616
--
Recall/Completeness
0.894
0.881
0.616
0.951
0.536
--
F1
0.840
0.890
0.733
0.862
0.573
--

Overall accuracy 0.832

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
0.7895
0.0487
0.1082
0.0492
0.0044
0.0000
building
0.0276
0.9222
0.0298
0.0205
0.0000
0.0000
low_veg
0.0668
0.0567
0.6030
0.2731
0.0004
0.0000
tree
0.0195
0.0143
0.0641
0.9021
0.0000
0.0000
car
0.4687
0.0000
0.0229
0.0708
0.4376
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.860
0.842
0.748
0.781
0.511
--
Recall/Completeness
0.789
0.922
0.603
0.902
0.438
--
F1
0.823
0.880
0.668
0.837
0.471
--

Overall accuracy 0.802

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
0.8087
0.0450
0.1068
0.0359
0.0037
0.0000
building
0.0223
0.9461
0.0204
0.0112
0.0000
0.0000
low_veg
0.0613
0.0409
0.6376
0.2598
0.0005
0.0000
tree
0.0122
0.0083
0.0560
0.9235
0.0000
0.0000
car
0.4233
0.0000
0.0249
0.0638
0.4881
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.887
0.875
0.770
0.806
0.499
--
Recall/Completeness
0.809
0.946
0.638
0.924
0.488
--
F1
0.846
0.909
0.697
0.861
0.493
--

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_area16_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.7767
0.0689
0.0610
0.0862
0.0072
0.0000
building
0.0368
0.9251
0.0153
0.0225
0.0004
0.0000
low_veg
0.0361
0.0373
0.6537
0.2727
0.0002
0.0000
tree
0.0236
0.0081
0.0569
0.9113
0.0001
0.0000
car
0.3998
0.0225
0.0280
0.0247
0.5250
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.817
0.869
0.854
0.773
0.479
--
Recall/Completeness
0.777
0.925
0.654
0.911
0.525
--
F1
0.797
0.896
0.741
0.836
0.501
--

Overall accuracy 0.815

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
0.8166
0.0616
0.0562
0.0602
0.0053
0.0000
building
0.0327
0.9474
0.0077
0.0119
0.0003
0.0000
low_veg
0.0332
0.0299
0.6808
0.2560
0.0001
0.0000
tree
0.0174
0.0036
0.0506
0.9284
0.0000
0.0000
car
0.3721
0.0164
0.0237
0.0163
0.5715
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.844
0.897
0.876
0.796
0.505
--
Recall/Completeness
0.817
0.947
0.681
0.928
0.572
--
F1
0.830
0.921
0.766
0.857
0.536
--

Overall accuracy 0.840

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
0.8151
0.0631
0.0405
0.0771
0.0042
0.0000
building
0.0132
0.9392
0.0317
0.0159
0.0000
0.0000
low_veg
0.0442
0.0459
0.6437
0.2660
0.0002
0.0000
tree
0.0082
0.0045
0.0419
0.9454
0.0000
0.0000
car
0.6608
0.0120
0.0399
0.0287
0.2586
0.0000
clutter
0.0321
0.9606
0.0040
0.0034
0.0000
0.0000
Precision/Correctness
0.903
0.756
0.802
0.848
0.548
-nan
Recall/Completeness
0.815
0.939
0.644
0.945
0.259
0.000
F1
0.857
0.838
0.714
0.894
0.351
-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_area20_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8509
0.0533
0.0392
0.0533
0.0032
0.0000
building
0.0106
0.9534
0.0282
0.0079
0.0000
0.0000
low_veg
0.0375
0.0332
0.6941
0.2351
0.0001
0.0000
tree
0.0042
0.0021
0.0335
0.9602
0.0000
0.0000
car
0.6525
0.0045
0.0358
0.0171
0.2901
0.0000
clutter
0.0274
0.9697
0.0011
0.0017
0.0000
0.0000
Precision/Correctness
0.929
0.779
0.828
0.878
0.559
-nan
Recall/Completeness
0.851
0.953
0.694
0.960
0.290
0.000
F1
0.888
0.857
0.755
0.917
0.382
-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_area22_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8506
0.0340
0.0364
0.0718
0.0072
0.0000
building
0.0464
0.9142
0.0183
0.0210
0.0000
0.0000
low_veg
0.0838
0.0682
0.5706
0.2773
0.0002
0.0000
tree
0.0238
0.0051
0.0408
0.9302
0.0000
0.0000
car
0.5709
0.0133
0.0309
0.0372
0.3477
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.876
0.861
0.810
0.764
0.619
--
Recall/Completeness
0.851
0.914
0.571
0.930
0.348
--
F1
0.863
0.887
0.670
0.839
0.445
--

Overall accuracy 0.823

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
0.8876
0.0259
0.0317
0.0498
0.0051
0.0000
building
0.0382
0.9373
0.0112
0.0133
0.0000
0.0000
low_veg
0.0781
0.0530
0.6185
0.2504
0.0000
0.0000
tree
0.0133
0.0024
0.0309
0.9534
0.0000
0.0000
car
0.5363
0.0158
0.0287
0.0263
0.3929
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.905
0.897
0.849
0.802
0.659
--
Recall/Completeness
0.888
0.937
0.619
0.953
0.393
--
F1
0.896
0.917
0.716
0.871
0.492
--

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_area24_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.7847
0.0706
0.0683
0.0673
0.0091
0.0000
building
0.0500
0.8918
0.0428
0.0154
0.0000
0.0000
low_veg
0.0317
0.1017
0.7024
0.1642
0.0000
0.0000
tree
0.0180
0.0134
0.0831
0.8853
0.0001
0.0000
car
0.4792
0.0519
0.0097
0.0245
0.4346
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.799
0.751
0.881
0.737
0.547
--
Recall/Completeness
0.785
0.892
0.702
0.885
0.435
--
F1
0.792
0.815
0.781
0.804
0.484
--

Overall accuracy 0.795

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
0.8193
0.0609
0.0609
0.0527
0.0063
0.0000
building
0.0479
0.9057
0.0353
0.0112
0.0000
0.0000
low_veg
0.0286
0.0997
0.7243
0.1473
0.0000
0.0000
tree
0.0122
0.0086
0.0709
0.9082
0.0001
0.0000
car
0.4656
0.0596
0.0045
0.0180
0.4523
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.822
0.767
0.901
0.761
0.571
--
Recall/Completeness
0.819
0.906
0.724
0.908
0.452
--
F1
0.821
0.830
0.803
0.828
0.505
--

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_area27_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9031
0.0321
0.0260
0.0191
0.0197
0.0000
building
0.1267
0.8433
0.0156
0.0143
0.0001
0.0000
low_veg
0.1402
0.0373
0.4789
0.3430
0.0006
0.0000
tree
0.0170
0.0046
0.0110
0.9674
0.0000
0.0000
car
0.6407
0.0162
0.0137
0.0192
0.3103
0.0000
clutter
0.6071
0.2060
0.1813
0.0057
0.0000
0.0000
Precision/Correctness
0.751
0.939
0.856
0.551
0.609
-nan
Recall/Completeness
0.903
0.843
0.479
0.967
0.310
0.000
F1
0.820
0.889
0.614
0.702
0.411
-nan

Overall accuracy 0.784

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
0.9312
0.0234
0.0207
0.0115
0.0132
0.0000
building
0.1110
0.8690
0.0118
0.0081
0.0001
0.0000
low_veg
0.1229
0.0240
0.5203
0.3324
0.0005
0.0000
tree
0.0095
0.0022
0.0072
0.9811
0.0000
0.0000
car
0.6196
0.0126
0.0129
0.0156
0.3394
0.0000
clutter
0.6379
0.1973
0.1628
0.0020
0.0000
0.0000
Precision/Correctness
0.785
0.961
0.890
0.578
0.658
-nan
Recall/Completeness
0.931
0.869
0.520
0.981
0.339
0.000
F1
0.852
0.913
0.657
0.728
0.448
-nan

Overall accuracy 0.819

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
0.9062
0.0278
0.0287
0.0288
0.0085
0.0000
building
0.0431
0.9271
0.0140
0.0158
0.0000
0.0000
low_veg
0.1048
0.0329
0.4761
0.3853
0.0009
0.0000
tree
0.0091
0.0026
0.0130
0.9753
0.0000
0.0000
car
0.5700
0.0115
0.0017
0.0147
0.4021
0.0000
clutter
0.5774
0.3649
0.0073
0.0399
0.0106
0.0000
Precision/Correctness
0.879
0.900
0.800
0.588
0.570
-nan
Recall/Completeness
0.906
0.927
0.476
0.975
0.402
0.000
F1
0.892
0.914
0.597
0.733
0.472
-nan

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_area29_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9309
0.0207
0.0232
0.0191
0.0060
0.0000
building
0.0360
0.9445
0.0093
0.0103
0.0000
0.0000
low_veg
0.0828
0.0203
0.5191
0.3775
0.0004
0.0000
tree
0.0037
0.0011
0.0089
0.9863
0.0000
0.0000
car
0.5417
0.0095
0.0015
0.0140
0.4333
0.0000
clutter
0.5660
0.3889
0.0055
0.0283
0.0114
0.0000
Precision/Correctness
0.904
0.922
0.838
0.622
0.601
-nan
Recall/Completeness
0.931
0.944
0.519
0.986
0.433
0.000
F1
0.917
0.933
0.641
0.763
0.504
-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_area31_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9202
0.0343
0.0151
0.0130
0.0174
0.0000
building
0.0625
0.9187
0.0084
0.0087
0.0018
0.0000
low_veg
0.1159
0.0133
0.7747
0.0960
0.0002
0.0000
tree
0.0654
0.0090
0.0253
0.8994
0.0010
0.0000
car
0.5203
0.1604
0.0221
0.0229
0.2742
0.0000
clutter
0.4846
0.4102
0.0293
0.0361
0.0371
0.0026
Precision/Correctness
0.823
0.876
0.900
0.811
0.533
1.000
Recall/Completeness
0.920
0.919
0.775
0.899
0.274
0.003
F1
0.869
0.897
0.833
0.853
0.362
0.005

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_area31_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9401
0.0279
0.0129
0.0065
0.0126
0.0000
building
0.0500
0.9384
0.0059
0.0043
0.0013
0.0000
low_veg
0.0926
0.0075
0.8173
0.0826
0.0000
0.0000
tree
0.0397
0.0057
0.0192
0.9351
0.0003
0.0000
car
0.5000
0.1796
0.0173
0.0153
0.2878
0.0000
clutter
0.4472
0.4577
0.0268
0.0248
0.0405
0.0031
Precision/Correctness
0.858
0.896
0.924
0.855
0.558
1.000
Recall/Completeness
0.940
0.938
0.817
0.935
0.288
0.003
F1
0.897
0.917
0.867
0.893
0.380
0.006

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_area33_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9287
0.0360
0.0201
0.0124
0.0026
0.0002
building
0.0885
0.7892
0.1125
0.0098
0.0000
0.0000
low_veg
0.1329
0.0464
0.5124
0.3075
0.0009
0.0000
tree
0.0526
0.0380
0.0515
0.8578
0.0001
0.0000
car
0.7301
0.0851
0.0038
0.0139
0.1670
0.0000
clutter
0.8320
0.0401
0.0012
0.0054
0.0157
0.1056
Precision/Correctness
0.771
0.890
0.633
0.619
0.517
0.985
Recall/Completeness
0.929
0.789
0.512
0.858
0.167
0.106
F1
0.843
0.837
0.566
0.719
0.252
0.191

Overall accuracy 0.763

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
0.9468
0.0299
0.0150
0.0066
0.0016
0.0001
building
0.0793
0.8024
0.1122
0.0061
0.0000
0.0000
low_veg
0.1050
0.0390
0.5335
0.3219
0.0006
0.0000
tree
0.0304
0.0352
0.0464
0.8880
0.0000
0.0000
car
0.7184
0.0854
0.0032
0.0124
0.1806
0.0000
clutter
0.8253
0.0330
0.0005
0.0037
0.0175
0.1201
Precision/Correctness
0.800
0.911
0.646
0.630
0.531
0.997
Recall/Completeness
0.947
0.802
0.534
0.888
0.181
0.120
F1
0.867
0.853
0.584
0.737
0.269
0.214

Overall accuracy 0.786

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
0.7369
0.0661
0.0860
0.1088
0.0023
0.0000
building
0.0521
0.8945
0.0307
0.0227
0.0000
0.0000
low_veg
0.0413
0.0239
0.5382
0.3966
0.0000
0.0000
tree
0.0323
0.0061
0.0721
0.8892
0.0003
0.0000
car
0.7436
0.0181
0.0079
0.0361
0.1943
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.832
0.908
0.741
0.612
0.686
--
Recall/Completeness
0.737
0.894
0.538
0.889
0.194
--
F1
0.782
0.901
0.624
0.725
0.303
--

Overall accuracy 0.761

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
0.7976
0.0576
0.0692
0.0740
0.0015
0.0000
building
0.0442
0.9240
0.0198
0.0121
0.0000
0.0000
low_veg
0.0330
0.0138
0.5681
0.3851
0.0000
0.0000
tree
0.0181
0.0028
0.0575
0.9215
0.0002
0.0000
car
0.7233
0.0160
0.0061
0.0242
0.2304
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.872
0.934
0.795
0.645
0.760
--
Recall/Completeness
0.798
0.924
0.568
0.922
0.230
--
F1
0.833
0.929
0.663
0.759
0.354
--

Overall accuracy 0.802

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
0.8534
0.0410
0.0517
0.0475
0.0063
0.0000
building
0.0357
0.8820
0.0642
0.0179
0.0001
0.0000
low_veg
0.0938
0.0650
0.6442
0.1969
0.0002
0.0000
tree
0.0387
0.0085
0.0696
0.8830
0.0001
0.0000
car
0.6153
0.0105
0.0703
0.0211
0.2828
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.824
0.878
0.802
0.704
0.603
--
Recall/Completeness
0.853
0.882
0.644
0.883
0.283
--
F1
0.839
0.880
0.715
0.783
0.385
--

Overall accuracy 0.803

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
0.8868
0.0364
0.0415
0.0308
0.0045
0.0000
building
0.0276
0.9086
0.0539
0.0098
0.0001
0.0000
low_veg
0.0768
0.0604
0.6860
0.1767
0.0001
0.0000
tree
0.0236
0.0057
0.0570
0.9137
0.0000
0.0000
car
0.5839
0.0084
0.0726
0.0135
0.3216
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.865
0.897
0.838
0.744
0.650
--
Recall/Completeness
0.887
0.909
0.686
0.914
0.322
--
F1
0.876
0.903
0.754
0.820
0.430
--

Overall accuracy 0.838

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image