An Improved Deep Residual Network-Based Semantic Simultaneous Localization and Mapping Method for Monocular Vision Robot

<table class="table-group" id="tab3"><tr><td><table class="table"><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr class="thead"><td class="align_left">Algorithms</td><td class="align_center">Matching accuracy (%)</td><td class="align_center">Computation time (s)</td></tr><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr><td class="align_left">SIFT</td><td class="align_center">85.5</td><td class="align_center">5.14</td></tr><tr><td class="align_left">SURF</td><td class="align_center">90.5</td><td class="align_center">0.96</td></tr><tr><td class="align_left">G-ORB</td><td class="align_center">56.6</td><td class="align_center">0.42</td></tr><tr><td class="align_left">I-ORB</td><td class="align_center">99.8</td><td class="align_center">0.68</td></tr><tr class="table-tr"><td colspan="3"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>The valuation of the four methods for image matching experiments.</div>

Computational Intelligence and Neuroscience

tab3

Table 3

Table 3: An Improved Deep Residual Network-Based Semantic Simultaneous Localization and Mapping Method for Monocular Vision Robot 