Single-Object Tracking Algorithm Based on Two-Step Spatiotemporal Deep Feature Fusion in a Complex Surveillance Scenario

<table class="table-group" id="tab3"><tr><td><table class="table"><tr><td class="thead-hr" colspan="4"><hr/></td></tr><tr class="thead"><td class="align_left">Index (average)</td><td class="align_center">YOLO-V3</td><td class="align_center">KCF</td><td class="align_center">Fusion</td></tr><tr><td class="thead-hr" colspan="4"><hr/></td></tr><tr><td class="align_left">CLE (pixel)</td><td class="align_center">16.9</td><td class="align_center">14.6</td><td class="align_center">10.5</td></tr><tr><td class="align_left">OR</td><td class="align_center">0.816</td><td class="align_center">0.752</td><td class="align_center">0.861</td></tr><tr><td class="align_left">Frame rate (FPS)</td><td class="align_center">8.7</td><td class="align_center"><b>46.0</b></td><td class="align_center">16.1</td></tr><tr class="table-tr"><td colspan="4"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>Detection and tracking results for different modules.</div>

Mathematical Problems in Engineering

tab3

Table 3

Table 3: Single-Object Tracking Algorithm Based on Two-Step Spatiotemporal Deep Feature Fusion in a Complex Surveillance Scenario 