ORB Feature descriptor. More...

Functions

AFAPI void orb (features &feat, array &desc, const array &image, const float fast_thr=20.f, const unsigned max_feat=400, const float scl_fctr=1.5f, const unsigned levels=4, const bool blur_img=false)
 C++ Interface for ORB feature descriptor. More...
 
AFAPI af_err af_orb (af_features *feat, af_array *desc, const af_array in, const float fast_thr, const unsigned max_feat, const float scl_fctr, const unsigned levels, const bool blur_img)
 C Interface for ORB feature descriptor. More...
 

Detailed Description

ORB Feature descriptor.

Extract ORB descriptors from FAST features that hold higher Harris responses. FAST does not compute orientation, thus, orientation of features is calculated using the intensity centroid. As FAST is also not multi-scale enabled, a multi-scale pyramid is calculated by downsampling the input image multiple times followed by FAST feature detection on each scale.


Function Documentation

AFAPI af_err af_orb ( af_features feat,
af_array desc,
const af_array  in,
const float  fast_thr,
const unsigned  max_feat,
const float  scl_fctr,
const unsigned  levels,
const bool  blur_img 
)

C Interface for ORB feature descriptor.

Parameters
[out]feataf_features struct composed of arrays for x and y coordinates, score, orientation and size of selected features
[out]descNx8 array containing extracted descriptors, where N is the number of selected features
[in]inarray containing a grayscale image (color images are not supported)
[in]fast_thrFAST threshold for which a pixel of the circle around the central pixel is considered to be brighter or darker
[in]max_featmaximum number of features to hold (will only keep the max_feat features with higher Harris responses)
[in]scl_fctrfactor to downsample the input image, meaning that each level will hold prior level dimensions divided by scl_fctr
[in]levelsnumber of levels to be computed for the image pyramid
[in]blur_imgblur image with a Gaussian filter with sigma=2 before computing descriptors to increase robustness against noise if true
AFAPI void af::orb ( features feat,
array desc,
const array image,
const float  fast_thr = 20.f,
const unsigned  max_feat = 400,
const float  scl_fctr = 1.5f,
const unsigned  levels = 4,
const bool  blur_img = false 
)

C++ Interface for ORB feature descriptor.

Parameters
[out]featfeatures object composed of arrays for x and y coordinates, score, orientation and size of selected features
[out]descNx8 array containing extracted descriptors, where N is the number of selected features
[in]imagearray containing a grayscale image (color images are not supported)
[in]fast_thrFAST threshold for which a pixel of the circle around the central pixel is considered to be brighter or darker
[in]max_featmaximum number of features to hold (will only keep the max_feat features with higher Harris responses)
[in]scl_fctrfactor to downsample the input image, meaning that each level will hold prior level dimensions divided by scl_fctr
[in]levelsnumber of levels to be computed for the image pyramid
[in]blur_imgblur image with a Gaussian filter with sigma=2 before computing descriptors to increase robustness against noise if true