Visual Tracking Using Max-Average Pooling and Weight-Selection Strategy

<table class="table-group" width="800px"><tr class="fig-image" id="a"><td><img alt="828907.fig.005a" src="https://static.hindawi.com/articles/jam/volume-2014/828907/figures/828907.fig.005a.jpg"/></td></tr><tr class="fig-caption"><td align="center"><table><tr><td><b>(a) </b>The 95th frame</td></tr></table></td></tr><tr class="fig-image" id="b"><td><img alt="828907.fig.005b" src="https://static.hindawi.com/articles/jam/volume-2014/828907/figures/828907.fig.005b.jpg"/></td></tr><tr class="fig-caption"><td align="center"><table><tr><td><b>(b) </b>The 96th frame</td></tr></table></td></tr></table>

<table>Tracking results in ThreePostShop2cor with Weight-Selection strategy (green: result of SR, yellow: result of PF, blue: the sampled particles, and red: the final tracking result).</table>

Journal of Applied Mathematics

fig5

Figure 5

Figure 5: Visual Tracking Using Max-Average Pooling and Weight-Selection Strategy 