A New Volumetric CNN for 3D Object Classification Based on Joint Multiscale Feature and Subvolume Supervised Learning Approaches

<div>An example of our octree illustration of 3D car object: (a) octree representation according to depths and (b) labelling of nodes to build parent-child (leaf) relationship at <i>d</i><sup>th</sup> depth.</div>

Computational Intelligence and Neuroscience

fig3

Figure 3

Figure 3: A New Volumetric CNN for 3D Object Classification Based on Joint Multiscale Feature and Subvolume Supervised Learning Approaches 