Detailled semantic labeling (2D) result


Name Y. Yu
Affiliation Chinese Academy of Sciences, Institute of Software, China
Abbreviation LLYT2
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
0.896
0.033
0.047
0.018
0.005
0.001
building
0.050
0.917
0.028
0.005
0.001
0.000
low_veg
0.052
0.023
0.785
0.139
0.000
0.000
tree
0.020
0.005
0.105
0.870
0.000
0.000
car
0.260
0.023
0.008
0.005
0.702
0.002
clutter
0.274
0.284
0.008
0.007
0.036
0.391
Precision/Correctness
0.878
0.929
0.794
0.844
0.811
0.916
Recall/Completeness
0.896
0.917
0.785
0.870
0.702
0.391
F1
0.887
0.923
0.790
0.857
0.752
0.548

Overall accuracy 0.865

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
0.924
0.026
0.038
0.009
0.003
0.000
building
0.041
0.936
0.020
0.002
0.001
0.000
low_veg
0.041
0.015
0.819
0.125
0.000
0.000
tree
0.010
0.002
0.087
0.901
0.000
0.000
car
0.141
0.026
0.004
0.002
0.824
0.002
clutter
0.236
0.302
0.005
0.003
0.035
0.420
Precision/Correctness
0.910
0.949
0.830
0.873
0.846
0.945
Recall/Completeness
0.924
0.936
0.819
0.901
0.824
0.420
F1
0.917
0.942
0.824
0.887
0.835
0.582

Overall accuracy 0.894
=============================================================

Tile top_mosaic_09cm_area2_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9365
0.0155
0.0273
0.0154
0.0052
0.0000
building
0.0461
0.9247
0.0242
0.0037
0.0013
0.0000
low_veg
0.0606
0.0189
0.7472
0.1732
0.0001
0.0000
tree
0.0241
0.0037
0.0996
0.8708
0.0003
0.0016
car
0.3230
0.0007
0.0005
0.0019
0.6739
0.0000
clutter
0.0914
0.0000
0.0000
0.0176
0.0000
0.8910
Precision/Correctness
0.860
0.957
0.832
0.819
0.860
0.977
Recall/Completeness
0.937
0.925
0.747
0.871
0.674
0.891
F1
0.897
0.941
0.787
0.844
0.756
0.932

Overall accuracy 0.867

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
0.9637
0.0123
0.0153
0.0049
0.0039
0.0000
building
0.0380
0.9464
0.0133
0.0009
0.0014
0.0000
low_veg
0.0444
0.0113
0.7768
0.1676
0.0000
0.0000
tree
0.0118
0.0011
0.0842
0.9020
0.0002
0.0008
car
0.1813
0.0000
0.0000
0.0006
0.8181
0.0000
clutter
0.0941
0.0000
0.0000
0.0060
0.0000
0.8999
Precision/Correctness
0.899
0.974
0.870
0.844
0.880
0.989
Recall/Completeness
0.964
0.946
0.777
0.902
0.818
0.900
F1
0.930
0.960
0.821
0.872
0.848
0.942

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_area4_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9293
0.0479
0.0138
0.0052
0.0038
0.0000
building
0.0722
0.9145
0.0106
0.0012
0.0014
0.0000
low_veg
0.1227
0.0401
0.5792
0.2550
0.0030
0.0000
tree
0.0481
0.0118
0.0752
0.8649
0.0000
0.0000
car
0.3566
0.0129
0.0027
0.0031
0.6248
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.835
0.969
0.655
0.753
0.816
--
Recall/Completeness
0.929
0.915
0.579
0.865
0.625
--
F1
0.880
0.941
0.615
0.805
0.708
--

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_area4_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9573
0.0292
0.0098
0.0017
0.0020
0.0000
building
0.0588
0.9306
0.0087
0.0004
0.0015
0.0000
low_veg
0.0871
0.0117
0.6173
0.2809
0.0031
0.0000
tree
0.0227
0.0033
0.0663
0.9076
0.0000
0.0000
car
0.2323
0.0084
0.0012
0.0011
0.7570
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.867
0.984
0.691
0.781
0.843
--
Recall/Completeness
0.957
0.931
0.617
0.908
0.757
--
F1
0.910
0.956
0.652
0.839
0.798
--

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_area6_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9042
0.0467
0.0322
0.0094
0.0075
0.0000
building
0.0462
0.9367
0.0131
0.0033
0.0007
0.0000
low_veg
0.0908
0.0312
0.7206
0.1570
0.0003
0.0000
tree
0.0166
0.0042
0.0667
0.9120
0.0005
0.0000
car
0.2846
0.0121
0.0010
0.0010
0.7012
0.0002
clutter
--
--
--
--
--
--
Precision/Correctness
0.870
0.949
0.707
0.928
0.831
--
Recall/Completeness
0.904
0.937
0.721
0.912
0.701
--
F1
0.887
0.943
0.714
0.920
0.761
--

Overall accuracy 0.894

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
0.9372
0.0335
0.0223
0.0025
0.0044
0.0000
building
0.0357
0.9546
0.0083
0.0009
0.0005
0.0000
low_veg
0.0757
0.0168
0.7625
0.1449
0.0000
0.0000
tree
0.0066
0.0013
0.0533
0.9385
0.0003
0.0000
car
0.1536
0.0112
0.0008
0.0001
0.8343
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.909
0.969
0.754
0.949
0.882
--
Recall/Completeness
0.937
0.955
0.762
0.939
0.834
--
F1
0.923
0.962
0.758
0.944
0.857
--

Overall accuracy 0.925

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
0.0240
0.0731
0.0104
0.0052
0.0000
building
0.0347
0.9414
0.0203
0.0032
0.0003
0.0000
low_veg
0.0500
0.0130
0.8613
0.0752
0.0005
0.0000
tree
0.0274
0.0058
0.0887
0.8780
0.0001
0.0000
car
0.2749
0.0105
0.0228
0.0028
0.6891
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.906
0.949
0.775
0.918
0.864
--
Recall/Completeness
0.887
0.941
0.861
0.878
0.689
--
F1
0.896
0.945
0.816
0.897
0.767
--

Overall accuracy 0.889

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area8_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9151
0.0167
0.0613
0.0035
0.0033
0.0000
building
0.0254
0.9615
0.0117
0.0012
0.0002
0.0000
low_veg
0.0353
0.0058
0.8937
0.0650
0.0001
0.0000
tree
0.0124
0.0025
0.0677
0.9175
0.0000
0.0000
car
0.1434
0.0092
0.0132
0.0013
0.8329
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.942
0.970
0.819
0.940
0.906
--
Recall/Completeness
0.915
0.962
0.894
0.917
0.833
--
F1
0.928
0.966
0.855
0.929
0.868
--

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_area10_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8218
0.0566
0.0991
0.0190
0.0035
0.0000
building
0.0338
0.9369
0.0170
0.0117
0.0006
0.0000
low_veg
0.0901
0.0337
0.7284
0.1476
0.0001
0.0000
tree
0.0178
0.0076
0.0977
0.8767
0.0001
0.0000
car
0.2251
0.0414
0.0126
0.0003
0.7206
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.914
0.884
0.676
0.834
0.772
--
Recall/Completeness
0.822
0.937
0.728
0.877
0.721
--
F1
0.865
0.910
0.701
0.855
0.746
--

Overall accuracy 0.843

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
0.8510
0.0442
0.0943
0.0083
0.0022
0.0000
building
0.0283
0.9505
0.0120
0.0087
0.0004
0.0000
low_veg
0.0878
0.0205
0.7679
0.1237
0.0001
0.0000
tree
0.0085
0.0038
0.0750
0.9127
0.0001
0.0000
car
0.1186
0.0462
0.0079
0.0000
0.8273
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.932
0.914
0.705
0.874
0.816
--
Recall/Completeness
0.851
0.951
0.768
0.913
0.827
--
F1
0.890
0.932
0.735
0.893
0.822
--

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_area12_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8647
0.0479
0.0504
0.0342
0.0028
0.0001
building
0.0314
0.9454
0.0162
0.0070
0.0000
0.0000
low_veg
0.0465
0.0316
0.7674
0.1543
0.0001
0.0001
tree
0.0109
0.0072
0.1196
0.8622
0.0000
0.0000
car
0.1926
0.0010
0.0040
0.0014
0.8010
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.834
0.906
0.803
0.862
0.903
--
Recall/Completeness
0.865
0.945
0.767
0.862
0.801
--
F1
0.849
0.926
0.785
0.862
0.849
--

Overall accuracy 0.851

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
0.8937
0.0454
0.0408
0.0193
0.0007
0.0001
building
0.0304
0.9602
0.0072
0.0022
0.0000
0.0000
low_veg
0.0436
0.0219
0.8018
0.1326
0.0000
0.0001
tree
0.0061
0.0029
0.1028
0.8882
0.0000
0.0000
car
0.0847
0.0002
0.0014
0.0002
0.9134
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.860
0.931
0.833
0.890
0.971
--
Recall/Completeness
0.894
0.960
0.802
0.888
0.913
--
F1
0.876
0.945
0.817
0.889
0.941
--

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_area14_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.7911
0.0358
0.1317
0.0356
0.0058
0.0000
building
0.0094
0.9666
0.0182
0.0057
0.0001
0.0000
low_veg
0.0760
0.0519
0.7187
0.1530
0.0004
0.0000
tree
0.0218
0.0115
0.1446
0.8220
0.0000
0.0000
car
0.1320
0.0000
0.0000
0.0136
0.8544
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.864
0.871
0.691
0.851
0.612
--
Recall/Completeness
0.791
0.967
0.719
0.822
0.854
--
F1
0.826
0.916
0.704
0.836
0.713
--

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
0.8105
0.0307
0.1295
0.0242
0.0050
0.0000
building
0.0045
0.9854
0.0079
0.0022
0.0000
0.0000
low_veg
0.0706
0.0379
0.7475
0.1436
0.0004
0.0000
tree
0.0154
0.0053
0.1314
0.8478
0.0000
0.0000
car
0.0301
0.0000
0.0000
0.0103
0.9596
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.889
0.903
0.710
0.873
0.599
--
Recall/Completeness
0.811
0.985
0.748
0.848
0.960
--
F1
0.848
0.942
0.728
0.860
0.738
--

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_area16_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8192
0.0386
0.0822
0.0573
0.0026
0.0000
building
0.0337
0.9254
0.0315
0.0091
0.0003
0.0000
low_veg
0.0166
0.0165
0.8481
0.1179
0.0001
0.0007
tree
0.0240
0.0043
0.1219
0.8497
0.0001
0.0000
car
0.1643
0.0045
0.0142
0.0064
0.8105
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.863
0.930
0.800
0.873
0.779
--
Recall/Completeness
0.819
0.925
0.848
0.850
0.810
--
F1
0.841
0.928
0.823
0.861
0.794
--

Overall accuracy 0.858

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image


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

Tile top_mosaic_09cm_area16_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8559
0.0345
0.0713
0.0370
0.0013
0.0000
building
0.0297
0.9493
0.0177
0.0031
0.0002
0.0000
low_veg
0.0132
0.0108
0.8714
0.1038
0.0001
0.0008
tree
0.0171
0.0016
0.1066
0.8748
0.0000
0.0000
car
0.0849
0.0010
0.0131
0.0001
0.9009
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.892
0.950
0.830
0.897
0.837
--
Recall/Completeness
0.856
0.949
0.871
0.875
0.901
--
F1
0.873
0.950
0.850
0.886
0.868
--

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_area20_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8415
0.0562
0.0476
0.0504
0.0043
0.0000
building
0.0275
0.9391
0.0258
0.0076
0.0000
0.0000
low_veg
0.0422
0.0408
0.7253
0.1910
0.0002
0.0005
tree
0.0067
0.0022
0.0406
0.9505
0.0000
0.0000
car
0.1353
0.0043
0.0342
0.0090
0.8173
0.0000
clutter
0.0008
0.9982
0.0010
0.0000
0.0000
0.0000
Precision/Correctness
0.914
0.765
0.821
0.890
0.788
0.000
Recall/Completeness
0.841
0.939
0.725
0.950
0.817
0.000
F1
0.876
0.843
0.770
0.919
0.803
-nan

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_area20_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8753
0.0484
0.0437
0.0304
0.0022
0.0000
building
0.0245
0.9527
0.0202
0.0026
0.0000
0.0000
low_veg
0.0372
0.0280
0.7719
0.1621
0.0002
0.0006
tree
0.0027
0.0005
0.0305
0.9663
0.0000
0.0000
car
0.0517
0.0009
0.0245
0.0011
0.9218
0.0000
clutter
0.0000
0.9997
0.0003
0.0000
0.0000
0.0000
Precision/Correctness
0.935
0.785
0.851
0.917
0.850
0.000
Recall/Completeness
0.875
0.953
0.772
0.966
0.922
0.000
F1
0.904
0.861
0.810
0.941
0.884
-nan

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_area22_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8939
0.0246
0.0415
0.0338
0.0062
0.0000
building
0.0391
0.9394
0.0138
0.0074
0.0003
0.0000
low_veg
0.0873
0.0397
0.7334
0.1393
0.0002
0.0000
tree
0.0230
0.0040
0.0718
0.9011
0.0001
0.0000
car
0.2576
0.0017
0.0083
0.0147
0.7178
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.893
0.908
0.802
0.865
0.790
--
Recall/Completeness
0.894
0.939
0.733
0.901
0.718
--
F1
0.894
0.923
0.766
0.883
0.752
--

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_area22_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9266
0.0178
0.0340
0.0172
0.0044
0.0000
building
0.0322
0.9592
0.0043
0.0040
0.0003
0.0000
low_veg
0.0842
0.0282
0.7745
0.1131
0.0001
0.0000
tree
0.0107
0.0012
0.0540
0.9341
0.0000
0.0000
car
0.1391
0.0022
0.0027
0.0085
0.8476
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.919
0.937
0.847
0.904
0.821
--
Recall/Completeness
0.927
0.959
0.774
0.934
0.848
--
F1
0.923
0.948
0.809
0.919
0.834
--

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_area24_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.8004
0.0486
0.1101
0.0360
0.0049
0.0000
building
0.0646
0.8780
0.0467
0.0105
0.0002
0.0000
low_veg
0.0237
0.0215
0.8728
0.0813
0.0007
0.0000
tree
0.0151
0.0063
0.1702
0.8083
0.0001
0.0000
car
0.2231
0.0077
0.0153
0.0048
0.7490
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.814
0.904
0.841
0.835
0.726
--
Recall/Completeness
0.800
0.878
0.873
0.808
0.749
--
F1
0.807
0.891
0.856
0.821
0.737
--

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
0.8314
0.0397
0.1002
0.0251
0.0036
0.0000
building
0.0614
0.8926
0.0380
0.0079
0.0002
0.0000
low_veg
0.0200
0.0172
0.8915
0.0705
0.0008
0.0000
tree
0.0090
0.0029
0.1491
0.8390
0.0000
0.0000
car
0.0986
0.0116
0.0079
0.0007
0.8811
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.840
0.926
0.864
0.858
0.731
--
Recall/Completeness
0.831
0.893
0.892
0.839
0.881
--
F1
0.836
0.909
0.877
0.849
0.799
--

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_area27_class.tif, reference set: full_reference


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9380
0.0281
0.0208
0.0071
0.0060
0.0000
building
0.0732
0.8978
0.0252
0.0033
0.0005
0.0000
low_veg
0.0788
0.0245
0.7182
0.1776
0.0009
0.0000
tree
0.0134
0.0042
0.0831
0.8992
0.0001
0.0000
car
0.3256
0.0056
0.0040
0.0053
0.6594
0.0000
clutter
0.6658
0.1490
0.0648
0.0028
0.1177
0.0000
Precision/Correctness
0.846
0.955
0.854
0.702
0.892
-nan
Recall/Completeness
0.938
0.898
0.718
0.899
0.659
0.000
F1
0.890
0.926
0.780
0.788
0.758
-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_area27_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9623
0.0191
0.0134
0.0028
0.0025
0.0000
building
0.0612
0.9181
0.0191
0.0011
0.0004
0.0000
low_veg
0.0598
0.0119
0.7594
0.1681
0.0008
0.0000
tree
0.0056
0.0009
0.0644
0.9291
0.0000
0.0000
car
0.1942
0.0051
0.0014
0.0049
0.7945
0.0000
clutter
0.6721
0.1463
0.0469
0.0003
0.1345
0.0000
Precision/Correctness
0.884
0.974
0.891
0.732
0.935
-nan
Recall/Completeness
0.962
0.918
0.759
0.929
0.794
0.000
F1
0.921
0.945
0.820
0.819
0.859
-nan

Overall accuracy 0.898

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
0.9357
0.0186
0.0256
0.0128
0.0069
0.0003
building
0.0321
0.9472
0.0151
0.0055
0.0001
0.0000
low_veg
0.0607
0.0193
0.6686
0.2507
0.0007
0.0000
tree
0.0058
0.0020
0.0503
0.9419
0.0000
0.0000
car
0.2582
0.0022
0.0001
0.0083
0.7079
0.0234
clutter
0.3833
0.3954
0.0263
0.0088
0.0356
0.1505
Precision/Correctness
0.923
0.919
0.824
0.699
0.697
0.907
Recall/Completeness
0.936
0.947
0.669
0.942
0.708
0.151
F1
0.929
0.933
0.738
0.802
0.702
0.258

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: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9586
0.0119
0.0180
0.0057
0.0055
0.0002
building
0.0267
0.9613
0.0092
0.0026
0.0001
0.0000
low_veg
0.0398
0.0079
0.7152
0.2366
0.0005
0.0000
tree
0.0019
0.0003
0.0409
0.9569
0.0000
0.0000
car
0.1446
0.0004
0.0001
0.0054
0.8202
0.0293
clutter
0.3486
0.4202
0.0183
0.0042
0.0340
0.1748
Precision/Correctness
0.945
0.939
0.866
0.740
0.713
0.921
Recall/Completeness
0.959
0.961
0.715
0.957
0.820
0.175
F1
0.952
0.950
0.783
0.835
0.763
0.294

Overall accuracy 0.903

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
0.9628
0.0093
0.0099
0.0064
0.0098
0.0019
building
0.0892
0.8926
0.0112
0.0024
0.0015
0.0031
low_veg
0.0403
0.0021
0.9148
0.0416
0.0009
0.0004
tree
0.0295
0.0042
0.0884
0.8770
0.0009
0.0000
car
0.1675
0.0999
0.0028
0.0064
0.7215
0.0019
clutter
0.3885
0.2202
0.0045
0.0125
0.0730
0.3013
Precision/Correctness
0.876
0.941
0.888
0.909
0.790
0.856
Recall/Completeness
0.963
0.893
0.915
0.877
0.721
0.301
F1
0.917
0.916
0.901
0.893
0.754
0.446

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: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9790
0.0068
0.0065
0.0017
0.0051
0.0009
building
0.0789
0.9115
0.0055
0.0004
0.0011
0.0027
low_veg
0.0215
0.0002
0.9432
0.0350
0.0001
0.0000
tree
0.0116
0.0012
0.0687
0.9184
0.0001
0.0000
car
0.0807
0.1143
0.0004
0.0018
0.8007
0.0021
clutter
0.3392
0.2441
0.0023
0.0041
0.0745
0.3359
Precision/Correctness
0.905
0.951
0.923
0.942
0.834
0.897
Recall/Completeness
0.979
0.911
0.943
0.918
0.801
0.336
F1
0.941
0.931
0.933
0.930
0.817
0.489

Overall accuracy 0.923

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
0.9568
0.0211
0.0093
0.0039
0.0035
0.0054
building
0.0680
0.8462
0.0795
0.0032
0.0012
0.0018
low_veg
0.0593
0.0074
0.8406
0.0910
0.0006
0.0010
tree
0.0403
0.0057
0.1510
0.8028
0.0000
0.0000
car
0.2142
0.0096
0.0036
0.0007
0.7665
0.0055
clutter
0.3317
0.0501
0.0021
0.0006
0.0402
0.5753
Precision/Correctness
0.873
0.951
0.752
0.836
0.713
0.917
Recall/Completeness
0.957
0.846
0.841
0.803
0.766
0.575
F1
0.913
0.895
0.794
0.819
0.739
0.707

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_area33_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9729
0.0184
0.0038
0.0014
0.0019
0.0017
building
0.0599
0.8593
0.0769
0.0012
0.0011
0.0016
low_veg
0.0307
0.0029
0.8732
0.0916
0.0005
0.0011
tree
0.0174
0.0026
0.1385
0.8416
0.0000
0.0000
car
0.0849
0.0067
0.0016
0.0003
0.9008
0.0056
clutter
0.2909
0.0486
0.0011
0.0001
0.0431
0.6161
Precision/Correctness
0.904
0.962
0.773
0.854
0.732
0.958
Recall/Completeness
0.973
0.859
0.873
0.842
0.901
0.616
F1
0.937
0.908
0.820
0.848
0.808
0.750

Overall accuracy 0.892

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
0.8587
0.0593
0.0601
0.0202
0.0016
0.0000
building
0.0362
0.9376
0.0206
0.0052
0.0004
0.0000
low_veg
0.0577
0.0163
0.7054
0.2205
0.0001
0.0000
tree
0.0329
0.0063
0.1201
0.8405
0.0002
0.0000
car
0.2831
0.0005
0.0000
0.0086
0.7078
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.864
0.925
0.782
0.763
0.899
--
Recall/Completeness
0.859
0.938
0.705
0.840
0.708
--
F1
0.862
0.931
0.742
0.800
0.792
--

Overall accuracy 0.836

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
0.9017
0.0540
0.0382
0.0053
0.0007
0.0000
building
0.0257
0.9627
0.0101
0.0011
0.0005
0.0000
low_veg
0.0432
0.0081
0.7353
0.2133
0.0000
0.0000
tree
0.0125
0.0020
0.0945
0.8910
0.0001
0.0000
car
0.1471
0.0000
0.0000
0.0030
0.8500
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.912
0.945
0.842
0.791
0.938
--
Recall/Completeness
0.902
0.963
0.735
0.891
0.850
--
F1
0.907
0.954
0.785
0.838
0.892
--

Overall accuracy 0.876

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
0.8956
0.0288
0.0534
0.0165
0.0054
0.0003
building
0.0375
0.8882
0.0684
0.0044
0.0011
0.0004
low_veg
0.0299
0.0140
0.8587
0.0971
0.0003
0.0000
tree
0.0200
0.0043
0.1382
0.8373
0.0002
0.0000
car
0.2249
0.0224
0.0336
0.0068
0.7123
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.909
0.947
0.803
0.833
0.789
--
Recall/Completeness
0.896
0.888
0.859
0.837
0.712
--
F1
0.902
0.916
0.830
0.835
0.749
--

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_area38_class.tif, reference set: no_boundary


↓ predicted || reference →
imp_surf
building
low_veg
tree
car
clutter
imp_surf
0.9269
0.0269
0.0365
0.0058
0.0035
0.0004
building
0.0298
0.9146
0.0525
0.0018
0.0010
0.0003
low_veg
0.0161
0.0087
0.8913
0.0838
0.0001
0.0000
tree
0.0076
0.0014
0.1124
0.8785
0.0001
0.0000
car
0.1152
0.0265
0.0229
0.0010
0.8343
0.0000
clutter
--
--
--
--
--
--
Precision/Correctness
0.945
0.960
0.845
0.869
0.830
--
Recall/Completeness
0.927
0.915
0.891
0.878
0.834
--
F1
0.936
0.937
0.868
0.874
0.832
--

Overall accuracy 0.904

Red/green image, indicating wrongly classified pixels


Original, resized true ortho image for better comparison


Classified image