Main MRPT website > C++ reference
MRPT logo
Public Member Functions | Public Attributes

mrpt::slam::TDataAssociationResults Struct Reference


Detailed Description

The results from mrpt::slam::data_association.

Definition at line 66 of file data_association.h.

#include <mrpt/slam/data_association.h>

List of all members.

Public Member Functions

 TDataAssociationResults ()
void clear ()

Public Attributes

std::map< observation_index_t,
prediction_index_t
associations
 For each observation (with row index IDX_obs in the input "Z_observations"), its association in the predictions, as the row index in the "Y_predictions_mean" input (or it's mapping to a custom ID, if it was provided).
double distance
 The Joint Mahalanobis distance or matching likelihood of the best associations found.
mrpt::math::CMatrixDouble indiv_distances
 Individual mahalanobis distances (or matching likelihood, depending on the selected metric) between predictions (row indices) & observations (column indices).
mrpt::math::CMatrixBool indiv_compatibility
 The result of a chi2 test for compatibility using mahalanobis distance - Indices are like in "indiv_distances".
vector_uint indiv_compatibility_counts
 The sum of each column of indiv_compatibility, that is, the number of compatible pairings for each observation.
size_t nNodesExploredInJCBB
 Only for the JCBB method,the number of recursive calls expent in the algorithm.

Constructor & Destructor Documentation

mrpt::slam::TDataAssociationResults::TDataAssociationResults (  ) [inline]

Definition at line 68 of file data_association.h.


Member Function Documentation

void mrpt::slam::TDataAssociationResults::clear ( void   ) [inline]

Definition at line 77 of file data_association.h.

References mrpt::math::distance().


Member Data Documentation

For each observation (with row index IDX_obs in the input "Z_observations"), its association in the predictions, as the row index in the "Y_predictions_mean" input (or it's mapping to a custom ID, if it was provided).

Note that not all observations may have an associated prediction. An observation with index "IDX_obs" corresponds to the prediction number "associations[IDX_obs]", or it may not correspond to anyone if it's not present in the std::map (Tip: Use associations.find(IDX_obs)!=associations.end() )

Note:
The types observation_index_t and prediction_index_t are just used for clarity, use normal size_t's.

Definition at line 93 of file data_association.h.

The Joint Mahalanobis distance or matching likelihood of the best associations found.

Definition at line 94 of file data_association.h.

The result of a chi2 test for compatibility using mahalanobis distance - Indices are like in "indiv_distances".

Definition at line 100 of file data_association.h.

The sum of each column of indiv_compatibility, that is, the number of compatible pairings for each observation.

Definition at line 101 of file data_association.h.

Individual mahalanobis distances (or matching likelihood, depending on the selected metric) between predictions (row indices) & observations (column indices).

Indices are for the appearing order in the arguments "Y_predictions_mean" & "Z_observations", they are NOT landmark IDs.

Definition at line 99 of file data_association.h.

Only for the JCBB method,the number of recursive calls expent in the algorithm.

Definition at line 103 of file data_association.h.




Page generated by Doxygen 1.7.2 for MRPT 0.9.4 SVN: at Mon Jan 10 22:30:30 UTC 2011