recognition_method Class Reference

Abstract class for a vision-algorithm. More...

#include <recognition_method.hh>

Inheritance diagram for recognition_method:

[legend]Collaboration diagram for recognition_method:

[legend]List of all members.

Public Member Functions
	recognition_method (const calibration_ptr &_calib, vision_type _type, const mimas::mm_xml_reference< XalanElement > &configuration, bool _verbose)
	Constructor.
virtual std::vector< match >	recognise (const mimas::mm_image< unsigned char > &image, double timestamp, mi_scene_ptr scene) const =0
	Virtual recognition method.
mi_pose	convert_pose_to_external (const std::string &type, const mi_pose &pose) const throw (mimas::mm_exception)
	Convert internal pose of recognition method to external pose.
mi_pose	convert_pose_to_internal (const std::string &type, const mi_pose &pose) const throw (mimas::mm_exception)
	Convert external pose to internal pose of recognition method.
vision_type	get_type (void) const
	Get type of vision-method.
Protected Member Functions
void	custom_offset (const std::string &type, const mi_pose &pose)
	Prepend transform for internal customisation.
Protected Attributes
calibration_ptr	calib
	Calibration data.
std::map< std::string, mi_pose >	offset
	Customisation for pose of micro-objects.
vision_type	type
	Type of vision-method.
bool	verbose
	Verbosity-switch.

---

Detailed Description

Abstract class for a vision-algorithm.

All "plugin"-classes for recognition/tracking are deriving from this class.

Author:

Jan Wedekind (j.wedekind@shu.ac.uk)

---

Constructor & Destructor Documentation

recognition_method::recognition_method (  const calibration_ptr &  _calib, vision_type  _type, const mimas::mm_xml_reference< XalanElement > &  configuration, bool  _verbose )

Constructor. The constructor stores a pointer to the calibration-data and it reads the customisation-transformations for the coordinate-systems of the micro-objects. Parameters: _calib  Calibration data. _type  Determines, wether this is a tracking- or recognition-method. configuration  Root-element of xml-document for configuration. _verbose  Set to true, if you want to get verbose information from the vision-algorithms.

---

Member Function Documentation

mi_pose recognition_method::convert_pose_to_external (  const std::string &  type, const mi_pose &  pose )  const throw (mimas::mm_exception)

Convert internal pose of recognition method to external pose. Parameters: type  Type of micro-object. pose  Internal pose of vision-algorithm.

mi_pose recognition_method::convert_pose_to_internal (  const std::string &  type, const mi_pose &  pose )  const throw (mimas::mm_exception)

Convert external pose to internal pose of recognition method. Parameters: type  Type of micro-object. pose  External pose of framework.

virtual std::vector< match > recognition_method::recognise (  const mimas::mm_image< unsigned char > &  image, double  timestamp, mi_scene_ptr  scene )  const [pure virtual]

Virtual recognition method. This method has to be implemented by the deriving class. Parameters: image  Image to recognise objects in. timestamp  Timestamp of image. scene  Scene-object containing vision-jobs and position of tracked objects. Returns: List of hypotheses. See also: match Implemented in geometric_voting_plugin, human_vision_plugin, and maxima_extraction_plugin.

---

The documentation for this class was generated from the following file:

• recognition_method.hh

---