PCL learning: key points -Keypoint class

The key point is also called point of interest, it is the stability point set, distinguishing the 2D image or a 3D point cloud model or a curved surface, can be obtained by defining testing standards, technically speaking, the number of key points with reducing the amount of data than the original image or point cloud many sub combined together to form a critical point descriptors used to form the original data representation, and yet descriptive representation and the local feature descriptor, which speeds up the subsequent identifying, tracing the data processing speed, therefore, become the key technology in 2D and 3D critical information processing technologies.

pcl::Keypoint< PointInT, PointOutT > 

Class keypoint detector is the base class for all key points related class defines the base interface;

virtual void	setSearchSurface (const PointCloudInConstPtr &cloud)
	When searching a search set by the point cloud, cloud point referenced as point cloud object pointer.
void	setSearchMethod (const KdTreePtr &tree)
	Setting the search target internal algorithm used, tree or to point kdtree octree corresponding pointer reference.
void	setKSearch (int k)
	K k-nearest neighbor set search parameters used.
void	setRadiusSearch (double radius)
	Radius radius search radius parameter setting used.
int	searchForNeighbors (int index, double parameter, std::vector< int > &indices, std::vector< float > &distances) const
	Using setSearchMethod set search target, and a search point cloud setSearchSurface set for neighbor search returns the neighbor index disk indices to the point cloud, and the distance corresponding to the disc distanee, wherein the index is a query point index, parameter search parameters used when the radius or radius k.