Terrain Classification Algorithm for Lunar Rover Using a Deep Ensemble Network with High-Resolution Features and Interdependencies between Channels

<table class="table-group" id="tab8"><tr><td><table class="table"><tr><td class="thead-hr" colspan="5"><hr/></td></tr><tr class="thead"><td class="align_left">Class</td><td class="align_center">Soft gravel</td><td class="align_center">Compacted soil</td><td class="align_center">Rocky terrain</td><td class="align_center">Concave land</td></tr><tr><td class="thead-hr" colspan="5"><hr/></td></tr><tr><td class="align_left">Number</td><td class="align_center">2086</td><td class="align_center">2034</td><td class="align_center">2187</td><td class="align_center">2208</td></tr><tr class="table-tr"><td colspan="5"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>The number of images after the transformation.</div>

Wireless Communications and Mobile Computing

tab8

Table 8

Table 8: Terrain Classification Algorithm for Lunar Rover Using a Deep Ensemble Network with High-Resolution Features and Interdependencies between Channels 

Table 8 | Terrain Classification Algorithm for Lunar Rover Using a Deep Ensemble Network with High-Resolution Features and Interdependencies between Channels 