High-Level Interpretation of Urban Road Maps Fusing Deep Learning-Based Pixelwise Scene Segmentation and Digital Navigation Maps

<table class="fixed-width table-group" id="tab5"><tr><td><table class="table"><colgroup><col style="width:6.56em"/><col style="width:4.08em"/><col style="width:4.15em"/><col style="width:3.88em"/><col style="width:4.16em"/></colgroup><tr><td class="thead-hr" colspan="5"><hr/></td></tr><tr class="thead"><td class="align_left"><b>Type of road </b></td><td class="align_center"><b>UM</b></td><td class="align_center"><b>UMM</b></td><td class="align_center"><b>UU</b></td><td class="align_center"><b>All</b></td></tr><tr><td class="thead-hr" colspan="5"><hr/></td></tr><tr><td class="align_left">F-measure</td><td class="align_center">94.16%</td><td class="align_center">95.45%</td><td class="align_center">91.17%</td><td class="align_center">93.98%</td></tr><tr class="table-tr"><td colspan="5"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>F-measure score for urban marked road, urban multiple marked lane, and urban unmarked road respectively of the KITTI test benchmark.</div>

Journal of Advanced Transportation

tab5

Table 5

Table 5: High-Level Interpretation of Urban Road Maps Fusing Deep Learning-Based Pixelwise Scene Segmentation and Digital Navigation Maps 