Orientation invariant 3D object classification using hough transform based methods
Proceedings of the ACM workshop on 3D object retrieval, 2010•dl.acm.org
In comparison to the 2D case, object class recognition in 3D is a much less researched area.
However, with the advent of affordable 3D acquisition technology and the growing popularity
of 3D content, its relevance is steadily increasing. Just as in the 2D case, 3D data is often
partial, noisy and without prior segmentation. Moreover, the object is rarely observed in a
canonical frame of reference with respect to orientation (or scale). We propose a method,
using Hough-voting for local 3D features, which is orientation (and scale) invariant.
However, with the advent of affordable 3D acquisition technology and the growing popularity
of 3D content, its relevance is steadily increasing. Just as in the 2D case, 3D data is often
partial, noisy and without prior segmentation. Moreover, the object is rarely observed in a
canonical frame of reference with respect to orientation (or scale). We propose a method,
using Hough-voting for local 3D features, which is orientation (and scale) invariant.
In comparison to the 2D case, object class recognition in 3D is a much less researched area. However, with the advent of affordable 3D acquisition technology and the growing popularity of 3D content, its relevance is steadily increasing. Just as in the 2D case, 3D data is often partial, noisy and without prior segmentation. Moreover, the object is rarely observed in a canonical frame of reference with respect to orientation (or scale). We propose a method, using Hough-voting for local 3D features, which is orientation (and scale) invariant.
ACM Digital Library以上显示的是最相近的搜索结果。 查看全部搜索结果