Human Detection via Image Denoising for 5G-Enabled Intelligent Applications

<table class="table-group" id="tab4"><tr><td><table class="table"><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr class="thead"><td class="align_left">Detection method</td><td class="align_center">AP</td></tr><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr><td class="align_left">SSD</td><td class="align_center">0.635</td></tr><tr><td class="align_left">YOLO</td><td class="align_center">0.794</td></tr><tr><td class="align_left">Fast RCNN</td><td class="align_center">0.825</td></tr><tr><td class="align_left">Faster RCNN</td><td class="align_center">0.829</td></tr><tr><td class="align_left">Mask RCNN</td><td class="align_center">0.833</td></tr><tr><td class="align_left">Cascade RCNN</td><td class="align_center">0.843</td></tr><tr><td class="align_left">Ours</td><td class="align_center">0.861</td></tr><tr class="table-tr"><td colspan="2"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>Comparison of the results of mainstream object detection algorithms on the PASCAL VOC dataset.</div>

Wireless Communications and Mobile Computing

tab4

Table 4

Table 4: Human Detection via Image Denoising for 5G-Enabled Intelligent Applications 