OpenPose  1.0.0rc2
OpenPose: A Real-Time Multi-Person Key-Point Detection And Multi-Threading C++ Library
 All Classes Namespaces Files Functions Variables Enumerations Enumerator Macros
op::WrapperStructFace Struct Reference

#include <wrapperStructFace.hpp>

Public Member Functions

 WrapperStructFace (const bool enable=false, const Point< int > &netInputSize=Point< int >{368, 368}, const RenderMode renderMode=RenderMode::None, const float alphaKeypoint=FACE_DEFAULT_ALPHA_KEYPOINT, const float alphaHeatMap=FACE_DEFAULT_ALPHA_HEAT_MAP, const float renderThreshold=0.4f)
 

Public Attributes

bool enable
 
Point< int > netInputSize
 
RenderMode renderMode
 
float alphaKeypoint
 
float alphaHeatMap
 
float renderThreshold
 

Detailed Description

WrapperStructFace: Face estimation and rendering configuration struct. WrapperStructFace allows the user to set up the face estimation and rendering parameters that will be used for the OpenPose Wrapper class.

Constructor & Destructor Documentation

op::WrapperStructFace::WrapperStructFace ( const bool  enable = false,
const Point< int > &  netInputSize = Point< int >{368, 368},
const RenderMode  renderMode = RenderMode::None,
const float  alphaKeypoint = FACE_DEFAULT_ALPHA_KEYPOINT,
const float  alphaHeatMap = FACE_DEFAULT_ALPHA_HEAT_MAP,
const float  renderThreshold = 0.4f 
)

Constructor of the struct. It has the recommended and default values we recommend for each element of the struct. Since all the elements of the struct are public, they can also be manually filled.

Member Data Documentation

float op::WrapperStructFace::alphaHeatMap

Rendering blending alpha value of the heat maps (face part, background or PAF) with respect to the background image. Value in the range [0, 1]. 0 will only render the background, 1 will only render the heat map.

float op::WrapperStructFace::alphaKeypoint

Rendering blending alpha value of the pose point locations with respect to the background image. Value in the range [0, 1]. 0 will only render the background, 1 will fully render the pose.

bool op::WrapperStructFace::enable

Whether to extract face.

Point<int> op::WrapperStructFace::netInputSize

CCN (Conv Net) input size. The greater, the slower and more memory it will be needed, but it will potentially increase accuracy. Both width and height must be divisible by 16.

RenderMode op::WrapperStructFace::renderMode

Whether to render the output (pose locations, body, background or PAF heat maps) with CPU or GPU. Select None for no rendering, Cpu or Gpu por CPU and GPU rendering respectively.

float op::WrapperStructFace::renderThreshold

Rendering threshold. Only estimated keypoints whose score confidences are higher than this value will be rendered. Generally, a high threshold (> 0.5) will only render very clear body parts; while small thresholds (~0.1) will also output guessed and occluded keypoints, but also more false positives (i.e. wrong detections).


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