SRBA: Sparser Relative Bundle Adjustment
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends
Public Member Functions | Public Attributes
srba::RbaEngine< KF2KF_POSE_TYPE, LM_TYPE, OBS_TYPE, RBA_OPTIONS >::TOptimizeExtraOutputInfo Struct Reference

Detailed Description

template<class KF2KF_POSE_TYPE, class LM_TYPE, class OBS_TYPE, class RBA_OPTIONS = RBA_OPTIONS_DEFAULT>
struct srba::RbaEngine< KF2KF_POSE_TYPE, LM_TYPE, OBS_TYPE, RBA_OPTIONS >::TOptimizeExtraOutputInfo

All the information returned by the local area optimizer

See also:
define_new_keyframe()

Definition at line 125 of file RbaEngine.h.

#include <RbaEngine.h>

List of all members.

Public Member Functions

void clear ()

Public Attributes

size_t num_observations
 Number of individual feature observations taken into account in the optimization.
size_t num_jacobians
 Number of Jacobian blocks which had been to be evaluated for each relinearization step.
size_t num_kf2kf_edges_optimized
 Number of solved unknowns of type "kf-to-kf edge".
size_t num_kf2lm_edges_optimized
 Number of solved unknowns of type "kf-to-landmark".
size_t num_total_scalar_optimized
 The total number of dimensions (scalar values) in all the optimized unknowns.
size_t num_kf_optimized
 Number of individual keyframes taken into account in the optimization.
size_t num_lm_optimized
 Number of individual landmarks taken into account in the optimization.
size_t num_span_tree_numeric_updates
 Number of poses updated in the spanning tree numeric-update stage.
double obs_rmse
 RMSE for each observation after optimization.
double total_sqr_error_init
double total_sqr_error_final
 Initial and final total squared error for all the observations.
double HAp_condition_number
 To be computed only if enabled in parameters.compute_condition_number.
size_t sparsity_dh_dAp_nnz
size_t sparsity_dh_dAp_max_size
size_t sparsity_dh_df_nnz
size_t sparsity_dh_df_max_size
size_t sparsity_HAp_nnz
size_t sparsity_HAp_max_size
size_t sparsity_Hf_nnz
size_t sparsity_Hf_max_size
size_t sparsity_HApf_nnz
size_t sparsity_HApf_max_size
std::vector< size_t > optimized_k2k_edge_indices
 The 0-based indices of all kf-to-kf edges which were considered in the optimization.
std::vector< size_t > optimized_landmark_indices
 The 0-based indices of all landmarks whose relative positions were considered as unknowns in the optimization.
RBA_OPTIONS::solver_t::extra_results_t extra_results

Member Data Documentation

template<class KF2KF_POSE_TYPE , class LM_TYPE , class OBS_TYPE , class RBA_OPTIONS = RBA_OPTIONS_DEFAULT>
RBA_OPTIONS::solver_t::extra_results_t srba::RbaEngine< KF2KF_POSE_TYPE, LM_TYPE, OBS_TYPE, RBA_OPTIONS >::TOptimizeExtraOutputInfo::extra_results

Other solver-specific output information

Definition at line 154 of file RbaEngine.h.

template<class KF2KF_POSE_TYPE , class LM_TYPE , class OBS_TYPE , class RBA_OPTIONS = RBA_OPTIONS_DEFAULT>
size_t srba::RbaEngine< KF2KF_POSE_TYPE, LM_TYPE, OBS_TYPE, RBA_OPTIONS >::TOptimizeExtraOutputInfo::sparsity_dh_dAp_nnz

Sparsity stats of (the active part of) the Jacobian matrix and hessian matrices: total number of blocks and how many of them are non-zero To be computed only if enabled in parameters.compute_sparsity_stats

Definition at line 147 of file RbaEngine.h.


The documentation for this struct was generated from the following file:
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends