Research on 24-Hour Dense Crowd Counting and Object Detection System Based on Multimodal Image Optimization Feature Fusion

<table class="table-group" id="tab7"><tr><td><table class="table"><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr class="thead"><td class="align_left">Method</td><td class="align_center">MAE</td><td class="align_center">MSE</td></tr><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr><td class="align_left">AGK</td><td class="align_center">22.46</td><td class="align_center">38.97</td></tr><tr><td class="align_left">AGK + RGBT-Net (front fusion)</td><td class="align_center">18.01</td><td class="align_center">31.49</td></tr><tr><td class="align_left">AGK + RGBT-Net (midrange fusion)</td><td class="align_center">18.16</td><td class="align_center">32.14</td></tr><tr><td class="align_left">AGK + RGBT-Net (end fusion)</td><td class="align_center">19.35</td><td class="align_center">34.71</td></tr><tr class="table-tr"><td colspan="3"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>Comparison of different feature fusion and normalization methods for the RGBT-CC dataset.</div>

Scientific Programming

tab7

Table 7

Table 7: Research on 24-Hour Dense Crowd Counting and Object Detection System Based on Multimodal Image Optimization Feature Fusion 