Predicting Pedestrian Counts for Crossing Scenario Based on Fused Infrared-Visual Videos

<table class="fixed-width table-group" id="tab7"><tr><td><table class="table"><colgroup><col style="width:12.42em"/><col style="width:3.64em"/><col style="width:5.19em"/></colgroup><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr class="thead"><td class="align_left"><b>Paper</b></td><td class="align_center"><b>MSE</b></td><td class="align_center"><b>Accuracy</b></td></tr><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr><td class="align_left">[<a href="/journals/jat/2018/8703576/#B12" target="_blank">12</a>]</td><td class="align_center">0. 726</td><td class="align_center">62.50%</td></tr><tr><td class="align_left">[<a href="/journals/jat/2018/8703576/#B15" target="_blank">15</a>]</td><td class="align_center">0.412</td><td class="align_center">76.88%</td></tr><tr><td class="align_left">Proposed method in this study</td><td class="align_center">0.246</td><td class="align_center">85.21%</td></tr><tr class="table-tr"><td colspan="3"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>The comparison of MSE and accuracy.</div>

Journal of Advanced Transportation

tab7

Table 7

Table 7: Predicting Pedestrian Counts for Crossing Scenario Based on Fused Infrared-Visual Videos 