face_video_segment  0.8
Adaptation of The Video Segmentation Project for face segmentation.
fvs::Keyframer Class Reference

Divides a sequence of frames containing faces into keyframes. More...

#include <keyframer.h>

Classes

struct  FaceData
 
struct  Keyframe
 

Public Member Functions

 Keyframer (int start_frame=10, int stability_range=5)
 Constructor. More...
 
void addFrame (const sfl::Frame &sfl_frame, Frame &fvs_frame)
 Add a new frame. More...
 

Detailed Description

Divides a sequence of frames containing faces into keyframes.

Each keyframe is associated with it's corresponding face orientation. A new frame will only become a keyframe if the euclidean distance between it's face orientation (in euler angles) to the orientation of any other keyframe is large enough.

Constructor & Destructor Documentation

fvs::Keyframer::Keyframer ( int  start_frame = 10,
int  stability_range = 5 
)

Constructor.

Parameters
[in]start_frameThe frame index to start adding keyframes from.
[in]stability_rangeSpecify how many frames in a row must have landmarks before a new keyframe can be added.

Member Function Documentation

void fvs::Keyframer::addFrame ( const sfl::Frame &  sfl_frame,
Frame &  fvs_frame 
)

Add a new frame.

Parameters
[in]sfl_frameLandmarks frame.
[in,out]fvs_frameRegions frame.

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