Detailled semantic labeling (2D) result


Name M. Gerke (SVL_full_chessboard_seg_noCRF)
Affiliation University of Twente, The Netherlands
Abbreviation SVL_5
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
0.866
0.051
0.061
0.016
0.006
0.001
building
0.090
0.871
0.023
0.014
0.002
0.001
low_veg
0.096
0.032
0.706
0.163
0.002
0.000
tree
0.023
0.012
0.141
0.824
0.000
0.000
car
0.509
0.087
0.060
0.008
0.329
0.006
clutter
0.562
0.301
0.049
0.018
0.066
0.003
Precision/Correctness
0.798
0.891
0.732
0.810
0.559
0.045
Recall/Completeness
0.866
0.871
0.706
0.824
0.329
0.003
F1
0.831
0.881
0.719
0.817
0.414
0.006

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
0.899
0.040
0.047
0.009
0.004
0.000
building
0.083
0.887
0.017
0.010
0.002
0.001
low_veg
0.086
0.022
0.740
0.150
0.002
0.000
tree
0.014
0.007
0.123
0.856
0.000
0.000
car
0.452
0.098
0.057
0.005
0.382
0.006
clutter
0.555
0.316
0.047
0.013
0.067
0.003
Precision/Correctness
0.825
0.919
0.773
0.839
0.576
0.058
Recall/Completeness
0.899
0.887
0.740
0.856
0.382
0.003
F1
0.861
0.903
0.756
0.847
0.459
0.007

Overall accuracy 0.840
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8736
0.0258
0.0836
0.0154
0.0016
0.0000
building
0.0249
0.9214
0.0436
0.0094
0.0005
0.0000
low_veg
0.0800
0.0289
0.7321
0.1587
0.0003
0.0000
tree
0.0209
0.0122
0.1297
0.8372
0.0000
0.0000
car
0.6297
0.0405
0.1633
0.0095
0.1569
0.0000
clutter
0.8269
0.0415
0.0942
0.0276
0.0000
0.0097
Precision/Correctness
0.797
0.922
0.727
0.820
0.802
1.000
Recall/Completeness
0.874
0.921
0.732
0.837
0.157
0.010
F1
0.834
0.922
0.730
0.828
0.263
0.019

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_area2_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9124
0.0181
0.0616
0.0067
0.0012
0.0000
building
0.0187
0.9411
0.0344
0.0053
0.0004
0.0000
low_veg
0.0670
0.0183
0.7629
0.1515
0.0003
0.0000
tree
0.0115
0.0081
0.1099
0.8704
0.0000
0.0000
car
0.5818
0.0473
0.1701
0.0083
0.1925
0.0000
clutter
0.8512
0.0408
0.0870
0.0111
0.0000
0.0100
Precision/Correctness
0.827
0.948
0.770
0.846
0.830
1.000
Recall/Completeness
0.912
0.941
0.763
0.870
0.193
0.010
F1
0.867
0.945
0.767
0.858
0.313
0.020

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_area4_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8719
0.1103
0.0102
0.0046
0.0030
0.0000
building
0.0818
0.9064
0.0078
0.0034
0.0006
0.0000
low_veg
0.2967
0.0739
0.3822
0.2461
0.0011
0.0000
tree
0.0858
0.0192
0.0773
0.8176
0.0000
0.0000
car
0.7210
0.0516
0.0127
0.0001
0.2147
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.775
0.932
0.602
0.734
0.711
--
Recall/Completeness
0.872
0.906
0.382
0.818
0.215
--
F1
0.821
0.919
0.468
0.774
0.330
--

Overall accuracy 0.857

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
0.9057
0.0825
0.0069
0.0025
0.0024
0.0000
building
0.0712
0.9191
0.0068
0.0023
0.0005
0.0000
low_veg
0.2727
0.0439
0.4143
0.2681
0.0011
0.0000
tree
0.0564
0.0094
0.0671
0.8672
0.0000
0.0000
car
0.6878
0.0457
0.0104
0.0000
0.2561
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.804
0.954
0.642
0.761
0.730
--
Recall/Completeness
0.906
0.919
0.414
0.867
0.256
--
F1
0.852
0.936
0.504
0.811
0.379
--

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_area6_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8747
0.0717
0.0375
0.0068
0.0092
0.0000
building
0.0784
0.8937
0.0181
0.0076
0.0021
0.0000
low_veg
0.1508
0.0445
0.6407
0.1627
0.0012
0.0000
tree
0.0231
0.0102
0.1011
0.8654
0.0002
0.0000
car
0.5618
0.0409
0.0119
0.0015
0.3839
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.794
0.917
0.604
0.920
0.659
--
Recall/Completeness
0.875
0.894
0.641
0.865
0.384
--
F1
0.832
0.905
0.622
0.892
0.485
--

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
0.9127
0.0518
0.0259
0.0023
0.0072
0.0000
building
0.0683
0.9110
0.0142
0.0047
0.0018
0.0000
low_veg
0.1342
0.0320
0.6803
0.1530
0.0005
0.0000
tree
0.0122
0.0059
0.0852
0.8966
0.0002
0.0000
car
0.5043
0.0347
0.0106
0.0003
0.4501
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.831
0.945
0.643
0.940
0.687
--
Recall/Completeness
0.913
0.911
0.680
0.897
0.450
--
F1
0.870
0.928
0.661
0.918
0.544
--

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_area8_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8873
0.0618
0.0377
0.0086
0.0046
0.0001
building
0.0813
0.9026
0.0080
0.0072
0.0009
0.0000
low_veg
0.1504
0.0190
0.7562
0.0730
0.0014
0.0000
tree
0.0350
0.0132
0.1320
0.8197
0.0001
0.0000
car
0.5586
0.0481
0.0223
0.0027
0.3684
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.808
0.885
0.765
0.913
0.764
--
Recall/Completeness
0.887
0.903
0.756
0.820
0.368
--
F1
0.846
0.894
0.761
0.864
0.497
--

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_area8_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9143
0.0528
0.0255
0.0038
0.0035
0.0001
building
0.0674
0.9225
0.0048
0.0047
0.0006
0.0000
low_veg
0.1286
0.0106
0.7963
0.0633
0.0012
0.0000
tree
0.0196
0.0077
0.1099
0.8627
0.0001
0.0000
car
0.4896
0.0502
0.0177
0.0023
0.4403
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.846
0.913
0.812
0.934
0.792
--
Recall/Completeness
0.914
0.922
0.796
0.863
0.440
--
F1
0.879
0.918
0.804
0.897
0.566
--

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_area10_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8488
0.0776
0.0565
0.0129
0.0041
0.0000
building
0.0387
0.9300
0.0177
0.0112
0.0023
0.0000
low_veg
0.1373
0.0455
0.6834
0.1309
0.0029
0.0000
tree
0.0148
0.0114
0.1551
0.8187
0.0001
0.0000
car
0.5800
0.0485
0.0324
0.0014
0.3377
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.887
0.847
0.676
0.846
0.478
--
Recall/Completeness
0.849
0.930
0.683
0.819
0.338
--
F1
0.868
0.886
0.680
0.832
0.396
--

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_area10_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8862
0.0617
0.0429
0.0059
0.0034
0.0000
building
0.0310
0.9471
0.0116
0.0080
0.0022
0.0000
low_veg
0.1358
0.0326
0.7217
0.1067
0.0032
0.0000
tree
0.0081
0.0063
0.1238
0.8617
0.0001
0.0000
car
0.5305
0.0508
0.0321
0.0003
0.3863
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.907
0.881
0.734
0.886
0.460
--
Recall/Completeness
0.886
0.947
0.722
0.862
0.386
--
F1
0.897
0.913
0.728
0.873
0.420
--

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_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8608
0.0340
0.0642
0.0370
0.0040
0.0000
building
0.1840
0.7847
0.0123
0.0147
0.0044
0.0000
low_veg
0.1136
0.0374
0.6080
0.2384
0.0025
0.0000
tree
0.0184
0.0077
0.1302
0.8434
0.0003
0.0000
car
0.5297
0.0720
0.0178
0.0040
0.3764
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.612
0.888
0.747
0.802
0.458
--
Recall/Completeness
0.861
0.785
0.608
0.843
0.376
--
F1
0.715
0.833
0.670
0.822
0.413
--

Overall accuracy 0.764

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
0.0288
0.0507
0.0238
0.0027
0.0000
building
0.1891
0.7933
0.0072
0.0060
0.0045
0.0000
low_veg
0.1142
0.0275
0.6397
0.2161
0.0024
0.0000
tree
0.0124
0.0041
0.1175
0.8658
0.0002
0.0000
car
0.4591
0.0884
0.0162
0.0001
0.4363
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.629
0.918
0.776
0.830
0.443
--
Recall/Completeness
0.894
0.793
0.640
0.866
0.436
--
F1
0.738
0.851
0.701
0.848
0.440
--

Overall accuracy 0.790

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
0.8176
0.0435
0.1190
0.0158
0.0040
0.0000
building
0.0363
0.9154
0.0414
0.0045
0.0024
0.0000
low_veg
0.1021
0.0615
0.7663
0.0661
0.0039
0.0001
tree
0.0315
0.0144
0.3023
0.6511
0.0007
0.0001
car
0.3079
0.0207
0.0239
0.0007
0.6468
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.811
0.841
0.589
0.911
0.404
--
Recall/Completeness
0.818
0.915
0.766
0.651
0.647
--
F1
0.814
0.876
0.666
0.760
0.497
--

Overall accuracy 0.765

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
0.8459
0.0377
0.1026
0.0107
0.0031
0.0000
building
0.0290
0.9383
0.0287
0.0023
0.0018
0.0000
low_veg
0.0985
0.0475
0.7911
0.0591
0.0037
0.0001
tree
0.0254
0.0089
0.2860
0.6790
0.0006
0.0001
car
0.2159
0.0256
0.0139
0.0000
0.7445
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.836
0.873
0.610
0.929
0.406
--
Recall/Completeness
0.846
0.938
0.791
0.679
0.745
--
F1
0.841
0.905
0.689
0.785
0.525
--

Overall accuracy 0.792

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
0.7849
0.0373
0.1432
0.0277
0.0067
0.0001
building
0.0501
0.8915
0.0453
0.0119
0.0012
0.0000
low_veg
0.0594
0.0200
0.8254
0.0905
0.0046
0.0001
tree
0.0281
0.0078
0.2587
0.7041
0.0013
0.0000
car
0.2735
0.0495
0.0559
0.0059
0.5953
0.0200
clutter
--
--
--
--
--
--
Precision/Correctness
0.764
0.915
0.662
0.886
0.302
--
Recall/Completeness
0.785
0.891
0.825
0.704
0.595
--
F1
0.774
0.903
0.735
0.785
0.400
--

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_area16_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8255
0.0312
0.1214
0.0172
0.0046
0.0001
building
0.0450
0.9143
0.0336
0.0063
0.0008
0.0000
low_veg
0.0559
0.0131
0.8457
0.0808
0.0045
0.0001
tree
0.0216
0.0043
0.2414
0.7316
0.0010
0.0000
car
0.2224
0.0507
0.0310
0.0026
0.6733
0.0200
clutter
--
--
--
--
--
--
Precision/Correctness
0.791
0.941
0.689
0.907
0.296
--
Recall/Completeness
0.826
0.914
0.846
0.732
0.673
--
F1
0.808
0.927
0.760
0.810
0.411
--

Overall accuracy 0.813

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
0.7495
0.0581
0.1106
0.0765
0.0053
0.0000
building
0.0130
0.9285
0.0220
0.0357
0.0008
0.0000
low_veg
0.0669
0.0294
0.6015
0.2984
0.0037
0.0000
tree
0.0042
0.0042
0.0421
0.9494
0.0001
0.0000
car
0.3282
0.1393
0.0269
0.0218
0.4837
0.0000
clutter
0.4447
0.4275
0.0820
0.0361
0.0098
0.0000
Precision/Correctness
0.833
0.829
0.719
0.830
0.473
-nan
Recall/Completeness
0.750
0.929
0.602
0.949
0.484
0.000
F1
0.789
0.876
0.655
0.885
0.479
-nan

Overall accuracy 0.811

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
0.7888
0.0478
0.1051
0.0545
0.0038
0.0000
building
0.0106
0.9444
0.0189
0.0253
0.0008
0.0000
low_veg
0.0650
0.0192
0.6461
0.2659
0.0039
0.0000
tree
0.0020
0.0020
0.0335
0.9624
0.0001
0.0000
car
0.2597
0.1547
0.0193
0.0093
0.5570
0.0000
clutter
0.4462
0.4386
0.0738
0.0317
0.0097
0.0000
Precision/Correctness
0.850
0.854
0.747
0.860
0.464
-nan
Recall/Completeness
0.789
0.944
0.646
0.962
0.557
0.000
F1
0.818
0.897
0.693
0.909
0.506
-nan

Overall accuracy 0.838

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
0.8910
0.0305
0.0348
0.0401
0.0037
0.0000
building
0.0889
0.8855
0.0093
0.0159
0.0004
0.0000
low_veg
0.1791
0.0390
0.5143
0.2659
0.0016
0.0000
tree
0.0276
0.0057
0.0464
0.9201
0.0002
0.0000
car
0.6773
0.0450
0.0269
0.0165
0.2342
0.0001
clutter
--
--
--
--
--
--
Precision/Correctness
0.808
0.889
0.797
0.792
0.610
--
Recall/Completeness
0.891
0.886
0.514
0.920
0.234
--
F1
0.848
0.887
0.625
0.852
0.338
--

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_area22_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9218
0.0233
0.0288
0.0230
0.0031
0.0000
building
0.0762
0.9086
0.0067
0.0083
0.0002
0.0000
low_veg
0.1761
0.0273
0.5578
0.2371
0.0017
0.0000
tree
0.0142
0.0030
0.0367
0.9459
0.0001
0.0000
car
0.6375
0.0564
0.0241
0.0097
0.2722
0.0001
clutter
--
--
--
--
--
--
Precision/Correctness
0.839
0.921
0.837
0.831
0.610
--
Recall/Completeness
0.922
0.909
0.558
0.946
0.272
--
F1
0.878
0.915
0.669
0.885
0.376
--

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_area24_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8323
0.0511
0.0606
0.0519
0.0040
0.0000
building
0.1142
0.8424
0.0101
0.0323
0.0009
0.0000
low_veg
0.0780
0.0164
0.7127
0.1918
0.0010
0.0000
tree
0.0301
0.0122
0.1111
0.8463
0.0004
0.0000
car
0.5353
0.0146
0.0086
0.0032
0.4383
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.657
0.901
0.883
0.699
0.566
--
Recall/Completeness
0.832
0.842
0.713
0.846
0.438
--
F1
0.734
0.871
0.789
0.766
0.494
--

Overall accuracy 0.787

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
0.8620
0.0414
0.0546
0.0392
0.0027
0.0000
building
0.1043
0.8602
0.0073
0.0275
0.0008
0.0000
low_veg
0.0719
0.0124
0.7373
0.1774
0.0009
0.0000
tree
0.0232
0.0088
0.1002
0.8675
0.0003
0.0000
car
0.4654
0.0167
0.0057
0.0002
0.5119
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.684
0.925
0.900
0.718
0.576
--
Recall/Completeness
0.862
0.860
0.737
0.867
0.512
--
F1
0.763
0.891
0.811
0.786
0.542
--

Overall accuracy 0.810

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
0.9076
0.0508
0.0277
0.0074
0.0065
0.0000
building
0.0731
0.9006
0.0143
0.0109
0.0010
0.0000
low_veg
0.1450
0.0454
0.6026
0.2063
0.0008
0.0000
tree
0.0176
0.0180
0.0599
0.9045
0.0001
0.0000
car
0.5975
0.0415
0.0193
0.0072
0.3344
0.0000
clutter
0.6398
0.1928
0.0704
0.0244
0.0726
0.0000
Precision/Correctness
0.791
0.916
0.851
0.659
0.797
0.000
Recall/Completeness
0.908
0.901
0.603
0.904
0.334
0.000
F1
0.845
0.908
0.706
0.763
0.471
-nan

Overall accuracy 0.824

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
0.9369
0.0368
0.0197
0.0032
0.0034
0.0000
building
0.0631
0.9176
0.0109
0.0076
0.0007
0.0000
low_veg
0.1301
0.0309
0.6432
0.1953
0.0005
0.0000
tree
0.0094
0.0117
0.0437
0.9352
0.0000
0.0000
car
0.5412
0.0429
0.0172
0.0049
0.3938
0.0000
clutter
0.6544
0.1888
0.0627
0.0186
0.0755
0.0000
Precision/Correctness
0.825
0.943
0.890
0.691
0.858
0.000
Recall/Completeness
0.937
0.918
0.643
0.935
0.394
0.000
F1
0.878
0.930
0.747
0.795
0.540
-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_area29_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9133
0.0378
0.0351
0.0057
0.0081
0.0000
building
0.0722
0.9044
0.0106
0.0047
0.0079
0.0002
low_veg
0.0736
0.0506
0.7141
0.1580
0.0037
0.0001
tree
0.0057
0.0310
0.1025
0.8606
0.0001
0.0000
car
0.5128
0.0498
0.0479
0.0018
0.3878
0.0000
clutter
0.5625
0.3027
0.0340
0.0048
0.0957
0.0003
Precision/Correctness
0.876
0.870
0.775
0.776
0.367
0.118
Recall/Completeness
0.913
0.904
0.714
0.861
0.388
0.000
F1
0.894
0.887
0.743
0.816
0.377
0.001

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_area29_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9409
0.0275
0.0228
0.0027
0.0061
0.0000
building
0.0686
0.9149
0.0063
0.0024
0.0077
0.0002
low_veg
0.0582
0.0342
0.7540
0.1506
0.0029
0.0000
tree
0.0027
0.0265
0.0766
0.8942
0.0001
0.0000
car
0.4624
0.0431
0.0470
0.0002
0.4472
0.0000
clutter
0.5597
0.3101
0.0253
0.0007
0.1039
0.0003
Precision/Correctness
0.896
0.901
0.831
0.809
0.364
0.103
Recall/Completeness
0.941
0.915
0.754
0.894
0.447
0.000
F1
0.918
0.908
0.791
0.849
0.401
0.001

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_area31_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9414
0.0243
0.0128
0.0067
0.0128
0.0020
building
0.3396
0.6384
0.0023
0.0070
0.0096
0.0032
low_veg
0.0947
0.0090
0.7877
0.1047
0.0037
0.0002
tree
0.0366
0.0057
0.0467
0.9092
0.0017
0.0001
car
0.3160
0.2604
0.0100
0.0132
0.3772
0.0232
clutter
0.4164
0.4375
0.0415
0.0288
0.0687
0.0071
Precision/Correctness
0.727
0.833
0.903
0.827
0.559
0.086
Recall/Completeness
0.941
0.638
0.788
0.909
0.377
0.007
F1
0.820
0.723
0.841
0.866
0.451
0.013

Overall accuracy 0.779

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
0.9624
0.0171
0.0091
0.0019
0.0079
0.0016
building
0.3380
0.6459
0.0012
0.0033
0.0085
0.0031
low_veg
0.0697
0.0053
0.8312
0.0911
0.0026
0.0000
tree
0.0195
0.0022
0.0337
0.9436
0.0009
0.0000
car
0.2533
0.2981
0.0054
0.0078
0.4137
0.0217
clutter
0.3651
0.4937
0.0435
0.0226
0.0667
0.0083
Precision/Correctness
0.744
0.857
0.932
0.864
0.596
0.105
Recall/Completeness
0.962
0.646
0.831
0.944
0.414
0.008
F1
0.839
0.737
0.879
0.902
0.489
0.015

Overall accuracy 0.804

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
0.9393
0.0368
0.0149
0.0033
0.0058
0.0000
building
0.2195
0.7210
0.0030
0.0531
0.0034
0.0000
low_veg
0.0912
0.0318
0.6355
0.2397
0.0018
0.0000
tree
0.0218
0.0380
0.1405
0.7992
0.0004
0.0000
car
0.5458
0.0578
0.0294
0.0075
0.3595
0.0000
clutter
0.5828
0.2824
0.0195
0.0033
0.1121
0.0000
Precision/Correctness
0.753
0.842
0.811
0.609
0.325
-nan
Recall/Completeness
0.939
0.721
0.635
0.799
0.359
0.000
F1
0.836
0.777
0.713
0.691
0.341
-nan

Overall accuracy 0.756

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
0.9601
0.0265
0.0082
0.0011
0.0042
0.0000
building
0.2210
0.7226
0.0018
0.0516
0.0030
0.0000
low_veg
0.0605
0.0217
0.6625
0.2540
0.0013
0.0000
tree
0.0105
0.0261
0.1260
0.8372
0.0003
0.0000
car
0.4761
0.0601
0.0334
0.0059
0.4245
0.0000
clutter
0.5631
0.2963
0.0197
0.0025
0.1185
0.0000
Precision/Correctness
0.771
0.873
0.848
0.611
0.327
-nan
Recall/Completeness
0.960
0.723
0.662
0.837
0.425
0.000
F1
0.855
0.791
0.744
0.707
0.369
-nan

Overall accuracy 0.778

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
0.8272
0.0900
0.0543
0.0167
0.0042
0.0076
building
0.0594
0.9111
0.0079
0.0075
0.0024
0.0116
low_veg
0.1045
0.0326
0.6201
0.2369
0.0012
0.0047
tree
0.0303
0.0148
0.1351
0.8163
0.0003
0.0031
car
0.4947
0.1303
0.0206
0.0082
0.2846
0.0616
clutter
--
--
--
--
--
--
Precision/Correctness
0.798
0.873
0.764
0.746
0.507
--
Recall/Completeness
0.827
0.911
0.620
0.816
0.285
--
F1
0.812
0.892
0.685
0.780
0.364
--

Overall accuracy 0.792

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
0.8775
0.0776
0.0308
0.0049
0.0030
0.0062
building
0.0474
0.9350
0.0029
0.0025
0.0018
0.0104
low_veg
0.0877
0.0218
0.6557
0.2305
0.0009
0.0033
tree
0.0135
0.0071
0.1062
0.8711
0.0001
0.0019
car
0.4274
0.1489
0.0195
0.0021
0.3327
0.0695
clutter
--
--
--
--
--
--
Precision/Correctness
0.842
0.907
0.830
0.773
0.563
--
Recall/Completeness
0.878
0.935
0.656
0.871
0.333
--
F1
0.860
0.921
0.733
0.819
0.418
--

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_area38_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.7762
0.0418
0.1642
0.0122
0.0055
0.0000
building
0.0200
0.8753
0.0805
0.0219
0.0022
0.0000
low_veg
0.0273
0.0243
0.8549
0.0926
0.0009
0.0000
tree
0.0099
0.0117
0.1955
0.7828
0.0001
0.0000
car
0.2482
0.0909
0.3527
0.0149
0.2933
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.924
0.913
0.693
0.814
0.550
--
Recall/Completeness
0.776
0.875
0.855
0.783
0.293
--
F1
0.844
0.894
0.766
0.798
0.383
--

Overall accuracy 0.820

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
0.8252
0.0364
0.1292
0.0046
0.0047
0.0000
building
0.0159
0.9024
0.0624
0.0174
0.0018
0.0000
low_veg
0.0200
0.0173
0.8842
0.0777
0.0008
0.0000
tree
0.0053
0.0087
0.1575
0.8284
0.0000
0.0000
car
0.2026
0.1024
0.3387
0.0101
0.3462
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.948
0.934
0.745
0.852
0.563
--
Recall/Completeness
0.825
0.902
0.884
0.828
0.346
--
F1
0.882
0.918
0.809
0.840
0.429
--

Overall accuracy 0.859

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image