Multiscale Traffic Sign Detection Method in Complex Environment Based on YOLOv4

<table class="table-group" id="tab2"><tr><td><table class="table"><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr class="thead"><td class="align_left">Method</td><td class="align_center">mAP (%)</td></tr><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr><td class="align_left">YOLOv4</td><td class="align_center">77.25</td></tr><tr><td class="align_left">YOLOv4 + classify denoizer</td><td class="align_center">79.15</td></tr><tr><td class="align_left">YOLOv4 + FT-FPN</td><td class="align_center">79.36</td></tr><tr><td class="align_left">Proposed model</td><td class="align_center">81.78</td></tr><tr class="table-tr"><td colspan="2"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

Computational Intelligence and Neuroscience

tab2

Table 2

Table 2: Multiscale Traffic Sign Detection Method in Complex Environment Based on YOLOv4 