Class cv::linemod::QuantizedPyramid#

Represents a modality operating over an image pyramid.

#include <opencv2/rgbd/linemod.hpp>

Collaboration diagram for cv::linemod::QuantizedPyramid:

cv::linemod::QuantizedPyramid Node1 cv::linemod::QuantizedPyramid   + ~QuantizedPyramid() + extractTemplate() + pyrDown() + quantize() # selectScatteredFeatures()

cv::linemod::QuantizedPyramid Node1 cv::linemod::QuantizedPyramid   + ~QuantizedPyramid() + extractTemplate() + pyrDown() + quantize() # selectScatteredFeatures()

Detailed Description#

Represents a modality operating over an image pyramid.

Constructor & Destructor Documentation#

~QuantizedPyramid()#

cv::linemod::QuantizedPyramid::~QuantizedPyramid()

Member Function Documentation#

extractTemplate()#

bool cv::linemod::QuantizedPyramid::extractTemplate(Template & templ)

Extract most discriminant features at current pyramid level to form a new template.

Parameters

  • templ — The new template.

pyrDown()#

void cv::linemod::QuantizedPyramid::pyrDown()

Go to the next pyramid level.

Todo

Allow pyramid scale factor other than 2

quantize()#

void cv::linemod::QuantizedPyramid::quantize(Mat & dst)

Compute quantized image at current pyramid level for online detection.

Parameters

  • dst — The destination 8-bit image. For each pixel at most one bit is set, representing its classification.

selectScatteredFeatures()#

static void cv::linemod::QuantizedPyramid::selectScatteredFeatures(
const std::vector< Candidate > & candidates,
std::vector< Feature > & features,
size_t num_features,
float distance )

Choose candidate features so that they are not bunched together.

Parameters

  • candidates — Candidate features sorted by score.

  • features — Destination vector of selected features.

  • num_features — Number of candidates to select.

  • distance — Hint for desired distance between features.

Source file#

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