LTI-Lib latest version v1.9 - last update 10 Apr 2010

lti::temporalTemplate Class Reference

This functor implements temporal templates, as described by James Davis and Aaron Bobick in "The Representation and Recognition of Action Using Temporal Templates", MIT Media Lab, Tech. More...

#include <ltiTemporalTemplate.h>

Inheritance diagram for lti::temporalTemplate:
Inheritance graph
[legend]
Collaboration diagram for lti::temporalTemplate:
Collaboration graph
[legend]

List of all members.

Classes

class  parameters
 the parameters for the class temporalTemplate More...

Public Member Functions

 temporalTemplate ()
 temporalTemplate (const temporalTemplate &other)
virtual ~temporalTemplate ()
virtual const char * getTypeName () const
void reset ()
bool apply (channel &srcdest)
bool apply (const image &src, channel &dest)
bool apply (const channel &src, channel &dest)
bool apply (const channel8 &src, channel &dest)
temporalTemplatecopy (const temporalTemplate &other)
virtual functorclone () const
const parametersgetParameters () const

Protected Member Functions

float difference (channel &newChannel, channel &diff)
float difference (channel8 &newChannel, channel &diff)
float difference (image &newImage, channel &diff)
void accumulate (channel &diff, const float &threshold)

Protected Attributes

channel lastChannel
channel8 lastChannel8
image lastImage
channel mhi

Detailed Description

This functor implements temporal templates, as described by James Davis and Aaron Bobick in "The Representation and Recognition of Action Using Temporal Templates", MIT Media Lab, Tech.

Report 402, IEEE Conference on Computer Vision and Pattern Recognition (CVPR'97) The apply()-methods return the calculated Motion-History-Image coded in a channel, where the value 1.0 means there was motion between the last two images.


Constructor & Destructor Documentation

lti::temporalTemplate::temporalTemplate (  ) 

default constructor

lti::temporalTemplate::temporalTemplate ( const temporalTemplate other  ) 

copy constructor

Parameters:
other the object to be copied
virtual lti::temporalTemplate::~temporalTemplate (  )  [virtual]

destructor


Member Function Documentation

void lti::temporalTemplate::accumulate ( channel diff,
const float &  threshold 
) [protected]

accumulate the given difference image in the MHI.

Diff will contain the same value as mhi after calling this member.

bool lti::temporalTemplate::apply ( const channel8 src,
channel dest 
)

operates on a copy of the given parameters.

Parameters:
src channel8 with the source data.
dest channel8 where the result will be left.
Returns:
true if successful, false otherwise Please note that all considered images MUST have the same size, otherwise your previous information will be lost. The first images will determine the used image size. You can restart with another size using reset().
bool lti::temporalTemplate::apply ( const channel src,
channel dest 
)

operates on a copy of the given parameters.

Parameters:
src channel with the source data.
dest channel where the result will be left.
Returns:
true if successful, false otherwise Please note that all considered images MUST have the same size, otherwise your previous information will be lost. The first images will determine the used image size. You can restart with another size using reset().
bool lti::temporalTemplate::apply ( const image src,
channel dest 
)

operates on a copy of the given parameters.

Parameters:
src image with the source data.
dest image where the result will be left.
Returns:
true if successful, false otherwise Please note that all considered images MUST have the same size, otherwise your previous information will be lost. The first images will determine the used image size. You can restart with another size using reset().
bool lti::temporalTemplate::apply ( channel srcdest  ) 

operates on the given parameter.

Parameters:
srcdest channel with the source data. The result will be left here too.
Returns:
true if successful, false otherwise Please note that all considered images MUST have the same size, otherwise your previous information will be lost. The first image will determine the used image size. You can restart with another size using reset().
virtual functor* lti::temporalTemplate::clone (  )  const [virtual]

returns a pointer to a clone of this functor.

Implements lti::functor.

temporalTemplate& lti::temporalTemplate::copy ( const temporalTemplate other  ) 

copy data of "other" functor.

Parameters:
other the functor to be copied
Returns:
a reference to this functor object

Reimplemented from lti::functor.

float lti::temporalTemplate::difference ( image newImage,
channel diff 
) [protected]

calculates the difference image.

The given image will substitute the lastChannel, and at the end will be empty() returns the threshold to be used.

float lti::temporalTemplate::difference ( channel8 newChannel,
channel diff 
) [protected]

calculates the difference image.

The given image will substitute the lastChannel, and at the end will be empty() returns the threshold to be used.

float lti::temporalTemplate::difference ( channel newChannel,
channel diff 
) [protected]

calculates the difference image.

The given image will substitute the lastChannel, and at the end will be empty() returns the threshold to be used.

const parameters& lti::temporalTemplate::getParameters (  )  const

returns used parameters

Reimplemented from lti::transform.

virtual const char* lti::temporalTemplate::getTypeName (  )  const [virtual]

returns the name of this type ( "temporalTemplate" )

Reimplemented from lti::transform.

void lti::temporalTemplate::reset (  ) 

reset the internal accumulators, so that the next apply will be considered as the first image to detect motion


Member Data Documentation

the last channel, required to calculate D(x,y,t)

the last channel8, required to calculate D(x,y,t)

the last image, required to calculate D(x,y,t)

The Motion History Image.


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

Generated on Sat Apr 10 15:27:56 2010 for LTI-Lib by Doxygen 1.6.1