* @brief Convert vectorized calib mat to matrix form * * @param matrix_data vectorized 1*12 calib matrix * @param calib_mat 4*4 calib matrix * @r

* @brief the Dynamic Curved-Voxle Clustering algoithm for fast and precise * point cloud segmentaiton * @param label_info, output the catego

* Remove default constructor */

finds position of least significant unset bit */

Constructor: takes a const ref to the matrix object with the data points

Deleted copy constructor*/

* KDTree constructor * * Refer to docs in README.md or online in * https://github.com/jlblancoc/nanoflann * * The KD-Tree point dimensi

* KDTree constructor * * Refer to docs in README.md or online in * https://github.com/jlblancoc/nanoflann * * The KD-Tree point dimensi

New methods Public methods: 1. calculateCorrespondences input: source point cloud, target point cloud output: correspondences

* @brief Default constructor for PointCloud */

* @brief Default constructor for PointCloud */

Default constructor. Initializes a new pool. */

Note: The first argument (checks_IGNORED_) is ignored, but kept for * compatibility with the FLANN interface */

* Called during search to add an element matching the criteria. * @return true if the search should be continued, false if the results are * suf

Add points to the set, Inserts all points from [start, end] */

* Add a vertex with no edges. * @param [in] id the id of vertex to be added */

* Builds the index */

Get the best candidate frame by geometry check