Detailled semantic labeling (2D) result

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 0.928 0.010 0.028 0.017 0.002 0.014 building 0.013 0.973 0.004 0.003 0.000 0.006 low_veg 0.039 0.008 0.865 0.071 0.000 0.017 tree 0.030 0.005 0.088 0.873 0.002 0.004 car 0.062 0.001 0.002 0.015 0.908 0.011 clutter 0.196 0.098 0.103 0.021 0.005 0.577 Precision/Correctness 0.917 0.958 0.861 0.869 0.942 0.715 Recall/Completeness 0.928 0.973 0.865 0.873 0.908 0.577 F1 0.922 0.966 0.863 0.871 0.925 0.639 Overall accuracy 0.900	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 0.945 0.007 0.023 0.012 0.000 0.013 building 0.010 0.981 0.002 0.002 0.000 0.006 low_veg 0.028 0.004 0.891 0.060 0.000 0.016 tree 0.021 0.003 0.074 0.897 0.001 0.003 car 0.007 0.001 0.000 0.010 0.970 0.012 clutter 0.186 0.083 0.091 0.017 0.005 0.618 Precision/Correctness 0.937 0.972 0.883 0.897 0.972 0.736 Recall/Completeness 0.945 0.981 0.891 0.897 0.970 0.618 F1 0.941 0.976 0.887 0.897 0.971 0.672 Overall accuracy 0.921
============================================================= Tile top_potsdam_2_13_class.tif, reference set: full_reference ↓ predicted || reference → imp_surf building low_veg tree car clutter imp_surf 0.9050 0.0102 0.0501 0.0123 0.0022 0.0202 building 0.0116 0.9672 0.0095 0.0067 0.0000 0.0050 low_veg 0.0187 0.0061 0.9171 0.0402 0.0002 0.0177 tree 0.0324 0.0061 0.1039 0.8517 0.0012 0.0047 car 0.0560 0.0007 0.0022 0.0083 0.9278 0.0050 clutter 0.1150 0.1415 0.1294 0.0258 0.0068 0.5814 Precision/Correctness 0.924 0.955 0.872 0.921 0.915 0.474 Recall/Completeness 0.905 0.967 0.917 0.852 0.928 0.581 F1 0.915 0.961 0.894 0.885 0.922 0.522 Overall accuracy 0.902 Red/green image, indicating wrongly classified pixels Original, resized true ortho image for better comparison Classified image	============================================================= Tile top_potsdam_2_13_class.tif, reference set: no_boundary ↓ predicted || reference → imp_surf building low_veg tree car clutter imp_surf 0.9260 0.0059 0.0421 0.0077 0.0001 0.0180 building 0.0078 0.9775 0.0053 0.0052 0.0000 0.0042 low_veg 0.0119 0.0031 0.9397 0.0288 0.0001 0.0166 tree 0.0239 0.0045 0.0856 0.8815 0.0008 0.0038 car 0.0125 0.0004 0.0009 0.0036 0.9775 0.0051 clutter 0.0841 0.1360 0.0975 0.0188 0.0085 0.6551 Precision/Correctness 0.950 0.972 0.897 0.945 0.962 0.455 Recall/Completeness 0.926 0.977 0.940 0.881 0.978 0.655 F1 0.938 0.975 0.918 0.912 0.970 0.537 Overall accuracy 0.926 Red/green image, indicating wrongly classified pixels Original, resized true ortho image for better comparison Classified image
============================================================= Tile top_potsdam_2_14_class.tif, reference set: full_reference ↓ predicted || reference → imp_surf building low_veg tree car clutter imp_surf 0.8889 0.0047 0.0822 0.0110 0.0011 0.0121 building 0.0057 0.9801 0.0072 0.0046 0.0000 0.0024 low_veg 0.0096 0.0025 0.9462 0.0367 0.0000 0.0050 tree 0.0135 0.0029 0.1373 0.8446 0.0007 0.0010 car 0.0465 0.0003 0.0034 0.0185 0.9301 0.0012 clutter 0.0825 0.2351 0.1372 0.0578 0.0349 0.4525 Precision/Correctness 0.934 0.949 0.862 0.945 0.912 0.267 Recall/Completeness 0.889 0.980 0.946 0.845 0.930 0.453 F1 0.911 0.964 0.902 0.892 0.921 0.335 Overall accuracy 0.902 Red/green image, indicating wrongly classified pixels Original, resized true ortho image for better comparison Classified image	============================================================= Tile top_potsdam_2_14_class.tif, reference set: no_boundary ↓ predicted || reference → imp_surf building low_veg tree car clutter imp_surf 0.9144 0.0023 0.0660 0.0062 0.0000 0.0111 building 0.0034 0.9895 0.0027 0.0027 0.0000 0.0017 low_veg 0.0054 0.0009 0.9605 0.0287 0.0000 0.0045 tree 0.0098 0.0021 0.1203 0.8665 0.0004 0.0008 car 0.0021 0.0000 0.0003 0.0128 0.9838 0.0009 clutter 0.0583 0.2643 0.1060 0.0609 0.0441 0.4664 Precision/Correctness 0.957 0.970 0.881 0.959 0.944 0.233 Recall/Completeness 0.914 0.989 0.961 0.867 0.984 0.466 F1 0.935 0.979 0.919 0.911 0.964 0.311 Overall accuracy 0.921 Red/green image, indicating wrongly classified pixels Original, resized true ortho image for better comparison Classified image
============================================================= Tile top_potsdam_3_13_class.tif, reference set: full_reference ↓ predicted || reference → imp_surf building low_veg tree car clutter imp_surf 0.8959 0.0153 0.0428 0.0207 0.0029 0.0224 building 0.0093 0.9811 0.0032 0.0041 0.0000 0.0022 low_veg 0.0471 0.0165 0.8564 0.0681 0.0001 0.0119 tree 0.0232 0.0055 0.0694 0.8967 0.0015 0.0037 car 0.0515 0.0074 0.0011 0.0224 0.9147 0.0028 clutter 0.1967 0.1158 0.1517 0.0223 0.0032 0.5103 Precision/Correctness 0.903 0.954 0.864 0.901 0.931 0.552 Recall/Completeness 0.896 0.981 0.856 0.897 0.915 0.510 F1 0.900 0.967 0.860 0.899 0.923 0.530 Overall accuracy 0.899 Red/green image, indicating wrongly classified pixels Original, resized true ortho image for better comparison Classified image	============================================================= Tile top_potsdam_3_13_class.tif, reference set: no_boundary ↓ predicted || reference → imp_surf building low_veg tree car clutter imp_surf 0.9214 0.0093 0.0356 0.0130 0.0001 0.0206 building 0.0072 0.9877 0.0007 0.0028 0.0000 0.0015 low_veg 0.0362 0.0078 0.8929 0.0547 0.0000 0.0084 tree 0.0161 0.0041 0.0555 0.9206 0.0010 0.0027 car 0.0036 0.0086 0.0003 0.0142 0.9712 0.0022 clutter 0.1946 0.1071 0.1293 0.0125 0.0037 0.5528 Precision/Correctness 0.930 0.973 0.891 0.929 0.977 0.557 Recall/Completeness 0.921 0.988 0.893 0.921 0.971 0.553 F1 0.925 0.980 0.892 0.925 0.974 0.555 Overall accuracy 0.926 Red/green image, indicating wrongly classified pixels Original, resized true ortho image for better comparison Classified image
============================================================= Tile top_potsdam_3_14_class.tif, reference set: full_reference ↓ predicted || reference → imp_surf building low_veg tree car clutter imp_surf 0.8933 0.0134 0.0494 0.0230 0.0028 0.0181 building 0.0074 0.9834 0.0035 0.0039 0.0000 0.0018 low_veg 0.0233 0.0082 0.8999 0.0603 0.0000 0.0083 tree 0.0187 0.0027 0.1291 0.8442 0.0009 0.0043 car 0.0502 0.0003 0.0018 0.0318 0.8955 0.0205 clutter 0.1791 0.1477 0.1389 0.0335 0.0043 0.4965 Precision/Correctness 0.909 0.955 0.834 0.903 0.917 0.658 Recall/Completeness 0.893 0.983 0.900 0.844 0.895 0.496 F1 0.901 0.969 0.865 0.873 0.906 0.566 Overall accuracy 0.890 Red/green image, indicating wrongly classified pixels Original, resized true ortho image for better comparison Classified image	============================================================= Tile top_potsdam_3_14_class.tif, reference set: no_boundary ↓ predicted || reference → imp_surf building low_veg tree car clutter imp_surf 0.9218 0.0077 0.0388 0.0154 0.0003 0.0161 building 0.0057 0.9898 0.0010 0.0025 0.0000 0.0010 low_veg 0.0140 0.0034 0.9296 0.0471 0.0000 0.0060 tree 0.0137 0.0019 0.1149 0.8652 0.0007 0.0035 car 0.0049 0.0001 0.0007 0.0204 0.9526 0.0213 clutter 0.1735 0.1387 0.1159 0.0261 0.0052 0.5405 Precision/Correctness 0.936 0.972 0.857 0.930 0.960 0.687 Recall/Completeness 0.922 0.990 0.930 0.865 0.953 0.540 F1 0.929 0.981 0.892 0.896 0.956 0.605 Overall accuracy 0.915 Red/green image, indicating wrongly classified pixels Original, resized true ortho image for better comparison Classified image
============================================================= Tile top_potsdam_4_13_class.tif, reference set: full_reference ↓ predicted || reference → imp_surf building low_veg tree car clutter imp_surf 0.9357 0.0054 0.0256 0.0276 0.0009 0.0048 building 0.0096 0.9752 0.0044 0.0056 0.0000 0.0052 low_veg 0.0405 0.0056 0.8191 0.1285 0.0001 0.0062 tree 0.0178 0.0012 0.0254 0.9534 0.0011 0.0011 car 0.0573 0.0005 0.0017 0.0250 0.9126 0.0029 clutter 0.4354 0.0945 0.1480 0.0678 0.0026 0.2518 Precision/Correctness 0.871 0.973 0.841 0.782 0.970 0.798 Recall/Completeness 0.936 0.975 0.819 0.953 0.913 0.252 F1 0.902 0.974 0.830 0.859 0.940 0.383 Overall accuracy 0.887 Red/green image, indicating wrongly classified pixels Original, resized true ortho image for better comparison Classified image	============================================================= Tile top_potsdam_4_13_class.tif, reference set: no_boundary ↓ predicted || reference → imp_surf building low_veg tree car clutter imp_surf 0.9535 0.0029 0.0202 0.0199 0.0000 0.0034 building 0.0051 0.9852 0.0010 0.0041 0.0000 0.0046 low_veg 0.0317 0.0019 0.8456 0.1159 0.0000 0.0048 tree 0.0088 0.0004 0.0165 0.9731 0.0005 0.0006 car 0.0034 0.0001 0.0001 0.0149 0.9790 0.0024 clutter 0.4534 0.0812 0.1397 0.0580 0.0027 0.2651 Precision/Correctness 0.892 0.982 0.873 0.819 0.987 0.825 Recall/Completeness 0.954 0.985 0.846 0.973 0.979 0.265 F1 0.922 0.984 0.859 0.889 0.983 0.401 Overall accuracy 0.911 Red/green image, indicating wrongly classified pixels Original, resized true ortho image for better comparison Classified image
============================================================= Tile top_potsdam_4_14_class.tif, reference set: full_reference ↓ predicted || reference → imp_surf building low_veg tree car clutter imp_surf 0.8925 0.0177 0.0456 0.0143 0.0024 0.0275 building 0.0052 0.9799 0.0027 0.0048 0.0000 0.0074 low_veg 0.0672 0.0131 0.7850 0.0863 0.0001 0.0482 tree 0.0263 0.0044 0.0816 0.8761 0.0017 0.0099 car 0.0568 0.0027 0.0009 0.0206 0.8989 0.0201 clutter 0.1628 0.0394 0.1095 0.0127 0.0002 0.6754 Precision/Correctness 0.854 0.941 0.825 0.863 0.955 0.753 Recall/Completeness 0.893 0.980 0.785 0.876 0.899 0.675 F1 0.873 0.960 0.804 0.869 0.926 0.712 Overall accuracy 0.861 Red/green image, indicating wrongly classified pixels Original, resized true ortho image for better comparison Classified image	============================================================= Tile top_potsdam_4_14_class.tif, reference set: no_boundary ↓ predicted || reference → imp_surf building low_veg tree car clutter imp_surf 0.9097 0.0128 0.0418 0.0092 0.0002 0.0262 building 0.0033 0.9863 0.0009 0.0035 0.0000 0.0061 low_veg 0.0555 0.0079 0.8121 0.0765 0.0000 0.0480 tree 0.0185 0.0031 0.0674 0.9014 0.0011 0.0086 car 0.0138 0.0020 0.0000 0.0141 0.9486 0.0215 clutter 0.1589 0.0359 0.0993 0.0099 0.0001 0.6958 Precision/Correctness 0.875 0.958 0.845 0.888 0.985 0.772 Recall/Completeness 0.910 0.986 0.812 0.901 0.949 0.696 F1 0.892 0.972 0.828 0.895 0.967 0.732 Overall accuracy 0.882 Red/green image, indicating wrongly classified pixels Original, resized true ortho image for better comparison Classified image
============================================================= Tile top_potsdam_4_15_class.tif, reference set: full_reference ↓ predicted || reference → imp_surf building low_veg tree car clutter imp_surf 0.9410 0.0165 0.0318 0.0044 0.0016 0.0047 building 0.0022 0.9918 0.0023 0.0021 0.0000 0.0016 low_veg 0.0580 0.0216 0.8652 0.0461 0.0003 0.0089 tree 0.0632 0.0083 0.0844 0.8338 0.0055 0.0048 car 0.0722 0.0014 0.0023 0.0057 0.9154 0.0030 clutter 0.3100 0.2471 0.1017 0.0125 0.0019 0.3269 Precision/Correctness 0.917 0.946 0.848 0.913 0.942 0.690 Recall/Completeness 0.941 0.992 0.865 0.834 0.915 0.327 F1 0.929 0.969 0.857 0.871 0.929 0.444 Overall accuracy 0.912 Red/green image, indicating wrongly classified pixels Original, resized true ortho image for better comparison Classified image	============================================================= Tile top_potsdam_4_15_class.tif, reference set: no_boundary ↓ predicted || reference → imp_surf building low_veg tree car clutter imp_surf 0.9565 0.0100 0.0278 0.0023 0.0001 0.0033 building 0.0007 0.9958 0.0009 0.0014 0.0000 0.0012 low_veg 0.0386 0.0116 0.9045 0.0390 0.0000 0.0063 tree 0.0457 0.0065 0.0657 0.8745 0.0038 0.0038 car 0.0078 0.0007 0.0002 0.0022 0.9861 0.0028 clutter 0.3296 0.2529 0.0968 0.0084 0.0013 0.3110 Precision/Correctness 0.942 0.964 0.874 0.936 0.971 0.709 Recall/Completeness 0.956 0.996 0.905 0.875 0.986 0.311 F1 0.949 0.980 0.889 0.904 0.978 0.432 Overall accuracy 0.936 Red/green image, indicating wrongly classified pixels Original, resized true ortho image for better comparison Classified image
============================================================= Tile top_potsdam_5_13_class.tif, reference set: full_reference ↓ predicted || reference → imp_surf building low_veg tree car clutter imp_surf 0.9371 0.0100 0.0181 0.0236 0.0011 0.0101 building 0.0105 0.9784 0.0037 0.0031 0.0000 0.0043 low_veg 0.0743 0.0085 0.8131 0.0913 0.0000 0.0128 tree 0.0384 0.0038 0.0701 0.8836 0.0022 0.0019 car 0.0826 0.0003 0.0004 0.0076 0.8991 0.0101 clutter 0.2276 0.1922 0.0985 0.0148 0.0336 0.4333 Precision/Correctness 0.909 0.960 0.891 0.803 0.930 0.649 Recall/Completeness 0.937 0.978 0.813 0.884 0.899 0.433 F1 0.923 0.969 0.851 0.841 0.914 0.520 Overall accuracy 0.901 Red/green image, indicating wrongly classified pixels Original, resized true ortho image for better comparison Classified image	============================================================= Tile top_potsdam_5_13_class.tif, reference set: no_boundary ↓ predicted || reference → imp_surf building low_veg tree car clutter imp_surf 0.9543 0.0055 0.0143 0.0175 0.0000 0.0083 building 0.0066 0.9851 0.0024 0.0022 0.0000 0.0037 low_veg 0.0676 0.0042 0.8376 0.0803 0.0000 0.0104 tree 0.0243 0.0022 0.0589 0.9116 0.0016 0.0014 car 0.0067 0.0001 0.0000 0.0050 0.9776 0.0105 clutter 0.2029 0.1724 0.0888 0.0121 0.0416 0.4822 Precision/Correctness 0.932 0.976 0.915 0.833 0.944 0.660 Recall/Completeness 0.954 0.985 0.838 0.912 0.978 0.482 F1 0.943 0.980 0.875 0.870 0.960 0.557 Overall accuracy 0.924 Red/green image, indicating wrongly classified pixels Original, resized true ortho image for better comparison Classified image
============================================================= Tile top_potsdam_5_14_class.tif, reference set: full_reference ↓ predicted || reference → imp_surf building low_veg tree car clutter imp_surf 0.9263 0.0068 0.0161 0.0294 0.0006 0.0208 building 0.0099 0.9823 0.0034 0.0013 0.0001 0.0030 low_veg 0.0588 0.0114 0.8028 0.1016 0.0001 0.0253 tree 0.0347 0.0055 0.0511 0.8976 0.0028 0.0082 car 0.0782 0.0018 0.0023 0.0173 0.8654 0.0349 clutter 0.1622 0.1972 0.1062 0.0335 0.0012 0.4997 Precision/Correctness 0.879 0.926 0.883 0.831 0.955 0.730 Recall/Completeness 0.926 0.982 0.803 0.898 0.865 0.500 F1 0.902 0.953 0.841 0.863 0.908 0.593 Overall accuracy 0.877 Red/green image, indicating wrongly classified pixels Original, resized true ortho image for better comparison Classified image	============================================================= Tile top_potsdam_5_14_class.tif, reference set: no_boundary ↓ predicted || reference → imp_surf building low_veg tree car clutter imp_surf 0.9440 0.0040 0.0109 0.0221 0.0000 0.0190 building 0.0081 0.9868 0.0017 0.0008 0.0000 0.0026 low_veg 0.0455 0.0083 0.8280 0.0949 0.0000 0.0234 tree 0.0257 0.0044 0.0431 0.9179 0.0020 0.0069 car 0.0058 0.0022 0.0005 0.0108 0.9428 0.0380 clutter 0.1465 0.1698 0.0964 0.0301 0.0012 0.5561 Precision/Correctness 0.906 0.945 0.906 0.855 0.971 0.753 Recall/Completeness 0.944 0.987 0.828 0.918 0.943 0.556 F1 0.925 0.966 0.865 0.885 0.957 0.640 Overall accuracy 0.900 Red/green image, indicating wrongly classified pixels Original, resized true ortho image for better comparison Classified image
============================================================= Tile top_potsdam_5_15_class.tif, reference set: full_reference ↓ predicted || reference → imp_surf building low_veg tree car clutter imp_surf 0.9279 0.0092 0.0336 0.0182 0.0009 0.0101 building 0.0108 0.9788 0.0032 0.0036 0.0000 0.0035 low_veg 0.0367 0.0046 0.7925 0.1293 0.0001 0.0368 tree 0.0314 0.0039 0.0509 0.9080 0.0015 0.0043 car 0.0945 0.0002 0.0017 0.0159 0.8714 0.0164 clutter 0.1911 0.1471 0.0736 0.0123 0.0005 0.5753 Precision/Correctness 0.931 0.941 0.818 0.791 0.975 0.784 Recall/Completeness 0.928 0.979 0.793 0.908 0.871 0.575 F1 0.929 0.960 0.805 0.845 0.920 0.664 Overall accuracy 0.893 Red/green image, indicating wrongly classified pixels Original, resized true ortho image for better comparison Classified image	============================================================= Tile top_potsdam_5_15_class.tif, reference set: no_boundary ↓ predicted || reference → imp_surf building low_veg tree car clutter imp_surf 0.9410 0.0055 0.0300 0.0136 0.0004 0.0094 building 0.0071 0.9858 0.0017 0.0024 0.0000 0.0030 low_veg 0.0215 0.0013 0.8189 0.1218 0.0000 0.0366 tree 0.0208 0.0022 0.0429 0.9296 0.0010 0.0035 car 0.0137 0.0000 0.0001 0.0126 0.9554 0.0182 clutter 0.1806 0.1163 0.0634 0.0100 0.0004 0.6293 Precision/Correctness 0.952 0.961 0.839 0.820 0.984 0.799 Recall/Completeness 0.941 0.986 0.819 0.930 0.955 0.629 F1 0.946 0.973 0.829 0.871 0.970 0.704 Overall accuracy 0.914 Red/green image, indicating wrongly classified pixels Original, resized true ortho image for better comparison Classified image
============================================================= Tile top_potsdam_6_13_class.tif, reference set: full_reference ↓ predicted || reference → imp_surf building low_veg tree car clutter imp_surf 0.9394 0.0139 0.0157 0.0171 0.0009 0.0130 building 0.0310 0.9554 0.0063 0.0012 0.0000 0.0061 low_veg 0.0170 0.0040 0.9345 0.0406 0.0000 0.0039 tree 0.0453 0.0031 0.0513 0.8963 0.0014 0.0026 car 0.0523 0.0000 0.0003 0.0036 0.9404 0.0034 clutter 0.1955 0.0093 0.2400 0.0240 0.0005 0.5307 Precision/Correctness 0.943 0.971 0.923 0.864 0.957 0.588 Recall/Completeness 0.939 0.955 0.934 0.896 0.940 0.531 F1 0.941 0.963 0.929 0.880 0.948 0.558 Overall accuracy 0.929 Red/green image, indicating wrongly classified pixels Original, resized true ortho image for better comparison Classified image	============================================================= Tile top_potsdam_6_13_class.tif, reference set: no_boundary ↓ predicted || reference → imp_surf building low_veg tree car clutter imp_surf 0.9541 0.0120 0.0125 0.0106 0.0000 0.0108 building 0.0274 0.9647 0.0024 0.0006 0.0000 0.0049 low_veg 0.0108 0.0022 0.9509 0.0334 0.0000 0.0028 tree 0.0296 0.0018 0.0413 0.9241 0.0011 0.0021 car 0.0018 0.0000 0.0001 0.0017 0.9935 0.0030 clutter 0.1854 0.0070 0.2494 0.0223 0.0001 0.5358 Precision/Correctness 0.957 0.978 0.939 0.896 0.987 0.611 Recall/Completeness 0.954 0.965 0.951 0.924 0.993 0.536 F1 0.956 0.971 0.945 0.910 0.990 0.571 Overall accuracy 0.945 Red/green image, indicating wrongly classified pixels Original, resized true ortho image for better comparison Classified image
============================================================= Tile top_potsdam_6_14_class.tif, reference set: full_reference ↓ predicted || reference → imp_surf building low_veg tree car clutter imp_surf 0.9666 0.0033 0.0125 0.0118 0.0032 0.0026 building 0.0311 0.9616 0.0035 0.0013 0.0002 0.0023 low_veg 0.0501 0.0054 0.8589 0.0788 0.0002 0.0065 tree 0.0320 0.0068 0.0428 0.9143 0.0032 0.0009 car 0.0408 0.0005 0.0007 0.0136 0.9381 0.0063 clutter 0.2106 0.0961 0.2262 0.0178 0.0112 0.4381 Precision/Correctness 0.935 0.983 0.897 0.828 0.939 0.773 Recall/Completeness 0.967 0.962 0.859 0.914 0.938 0.438 F1 0.951 0.972 0.877 0.869 0.939 0.559 Overall accuracy 0.930 Red/green image, indicating wrongly classified pixels Original, resized true ortho image for better comparison Classified image	============================================================= Tile top_potsdam_6_14_class.tif, reference set: no_boundary ↓ predicted || reference → imp_surf building low_veg tree car clutter imp_surf 0.9796 0.0011 0.0090 0.0083 0.0001 0.0019 building 0.0265 0.9696 0.0013 0.0007 0.0000 0.0018 low_veg 0.0350 0.0020 0.8879 0.0704 0.0000 0.0047 tree 0.0215 0.0058 0.0336 0.9362 0.0023 0.0007 car 0.0017 0.0001 0.0001 0.0080 0.9837 0.0064 clutter 0.1855 0.1046 0.2314 0.0128 0.0108 0.4550 Precision/Correctness 0.952 0.989 0.917 0.859 0.981 0.811 Recall/Completeness 0.980 0.970 0.888 0.936 0.984 0.455 F1 0.966 0.979 0.902 0.896 0.982 0.583 Overall accuracy 0.948 Red/green image, indicating wrongly classified pixels Original, resized true ortho image for better comparison Classified image
============================================================= Tile top_potsdam_6_15_class.tif, reference set: full_reference ↓ predicted || reference → imp_surf building low_veg tree car clutter imp_surf 0.9309 0.0029 0.0270 0.0075 0.0034 0.0282 building 0.0178 0.9656 0.0034 0.0012 0.0000 0.0120 low_veg 0.0443 0.0020 0.8463 0.0505 0.0007 0.0562 tree 0.0488 0.0063 0.1066 0.8272 0.0032 0.0079 car 0.0548 0.0005 0.0030 0.0099 0.9202 0.0116 clutter 0.1012 0.0139 0.0555 0.0056 0.0055 0.8183 Precision/Correctness 0.931 0.986 0.802 0.919 0.927 0.677 Recall/Completeness 0.931 0.966 0.846 0.827 0.920 0.818 F1 0.931 0.976 0.824 0.871 0.924 0.741 Overall accuracy 0.903 Red/green image, indicating wrongly classified pixels Original, resized true ortho image for better comparison Classified image	============================================================= Tile top_potsdam_6_15_class.tif, reference set: no_boundary ↓ predicted || reference → imp_surf building low_veg tree car clutter imp_surf 0.9456 0.0012 0.0226 0.0043 0.0001 0.0262 building 0.0133 0.9746 0.0010 0.0006 0.0000 0.0104 low_veg 0.0284 0.0002 0.8757 0.0400 0.0000 0.0557 tree 0.0383 0.0050 0.0927 0.8549 0.0023 0.0068 car 0.0063 0.0003 0.0003 0.0054 0.9761 0.0116 clutter 0.0928 0.0138 0.0468 0.0040 0.0058 0.8368 Precision/Correctness 0.950 0.991 0.825 0.945 0.970 0.697 Recall/Completeness 0.946 0.975 0.876 0.855 0.976 0.837 F1 0.948 0.983 0.850 0.898 0.973 0.761 Overall accuracy 0.923 Red/green image, indicating wrongly classified pixels Original, resized true ortho image for better comparison Classified image
============================================================= Tile top_potsdam_7_13_class.tif, reference set: full_reference ↓ predicted || reference → imp_surf building low_veg tree car clutter imp_surf 0.9420 0.0143 0.0050 0.0238 0.0012 0.0138 building 0.0168 0.9445 0.0017 0.0018 0.0000 0.0352 low_veg 0.0615 0.0087 0.7593 0.1531 0.0001 0.0173 tree 0.0257 0.0057 0.0855 0.8823 0.0004 0.0005 car 0.0419 0.0014 0.0003 0.0291 0.9108 0.0164 clutter 0.1240 0.0019 0.0187 0.0013 0.0046 0.8495 Precision/Correctness 0.952 0.961 0.872 0.709 0.923 0.821 Recall/Completeness 0.942 0.944 0.759 0.882 0.911 0.849 F1 0.947 0.953 0.812 0.786 0.917 0.835 Overall accuracy 0.911 Red/green image, indicating wrongly classified pixels Original, resized true ortho image for better comparison Classified image	============================================================= Tile top_potsdam_7_13_class.tif, reference set: no_boundary ↓ predicted || reference → imp_surf building low_veg tree car clutter imp_surf 0.9559 0.0112 0.0033 0.0167 0.0001 0.0128 building 0.0140 0.9500 0.0008 0.0011 0.0000 0.0342 low_veg 0.0483 0.0059 0.7858 0.1431 0.0000 0.0168 tree 0.0179 0.0041 0.0791 0.8983 0.0002 0.0004 car 0.0037 0.0013 0.0000 0.0198 0.9560 0.0192 clutter 0.1166 0.0016 0.0173 0.0009 0.0045 0.8591 Precision/Correctness 0.960 0.970 0.891 0.744 0.956 0.831 Recall/Completeness 0.956 0.950 0.786 0.898 0.956 0.859 F1 0.958 0.960 0.835 0.814 0.956 0.845 Overall accuracy 0.925 Red/green image, indicating wrongly classified pixels Original, resized true ortho image for better comparison Classified image

This webpage is generated by an unofficial python code.