OpenCV
3.3.1
Open Source Computer Vision
|
Object detector using the LINE template matching algorithm with any set of modalities. More...
#include "linemod.hpp"
Public Member Functions | |
Detector () | |
Empty constructor, initialize with read(). More... | |
Detector (const std::vector< Ptr< Modality > > &modalities, const std::vector< int > &T_pyramid) | |
Constructor. More... | |
int | addSyntheticTemplate (const std::vector< Template > &templates, const String &class_id) |
Add a new object template computed by external means. More... | |
int | addTemplate (const std::vector< Mat > &sources, const String &class_id, const Mat &object_mask, Rect *bounding_box=NULL) |
Add new object template. More... | |
std::vector< String > | classIds () const |
const std::vector< Ptr< Modality > > & | getModalities () const |
Get the modalities used by this detector. More... | |
int | getT (int pyramid_level) const |
Get sampling step T at pyramid_level. More... | |
const std::vector< Template > & | getTemplates (const String &class_id, int template_id) const |
Get the template pyramid identified by template_id. More... | |
void | match (const std::vector< Mat > &sources, float threshold, std::vector< Match > &matches, const std::vector< String > &class_ids=std::vector< String >(), OutputArrayOfArrays quantized_images=noArray(), const std::vector< Mat > &masks=std::vector< Mat >()) const |
Detect objects by template matching. More... | |
int | numClasses () const |
int | numTemplates () const |
int | numTemplates (const String &class_id) const |
int | pyramidLevels () const |
Get number of pyramid levels used by this detector. More... | |
void | read (const FileNode &fn) |
String | readClass (const FileNode &fn, const String &class_id_override="") |
void | readClasses (const std::vector< String > &class_ids, const String &format="templates_%s.yml.gz") |
void | write (FileStorage &fs) const |
void | writeClass (const String &class_id, FileStorage &fs) const |
void | writeClasses (const String &format="templates_%s.yml.gz") const |
Protected Types | |
typedef std::vector< Mat > | LinearMemories |
typedef std::vector< std::vector< LinearMemories > > | LinearMemoryPyramid |
typedef std::vector< Template > | TemplatePyramid |
typedef std::map< String, std::vector< TemplatePyramid > > | TemplatesMap |
Protected Member Functions | |
void | matchClass (const LinearMemoryPyramid &lm_pyramid, const std::vector< Size > &sizes, float threshold, std::vector< Match > &matches, const String &class_id, const std::vector< TemplatePyramid > &template_pyramids) const |
Protected Attributes | |
TemplatesMap | class_templates |
std::vector< Ptr< Modality > > | modalities |
int | pyramid_levels |
std::vector< int > | T_at_level |
Object detector using the LINE template matching algorithm with any set of modalities.
|
protected |
|
protected |
|
protected |
|
protected |
cv::linemod::Detector::Detector | ( | ) |
Empty constructor, initialize with read().
cv::linemod::Detector::Detector | ( | const std::vector< Ptr< Modality > > & | modalities, |
const std::vector< int > & | T_pyramid | ||
) |
Constructor.
modalities | Modalities to use (color gradients, depth normals, ...). |
T_pyramid | Value of the sampling step T at each pyramid level. The number of pyramid levels is T_pyramid.size(). |
int cv::linemod::Detector::addSyntheticTemplate | ( | const std::vector< Template > & | templates, |
const String & | class_id | ||
) |
Add a new object template computed by external means.
int cv::linemod::Detector::addTemplate | ( | const std::vector< Mat > & | sources, |
const String & | class_id, | ||
const Mat & | object_mask, | ||
Rect * | bounding_box = NULL |
||
) |
Add new object template.
sources | Source images, one for each modality. | |
class_id | Object class ID. | |
object_mask | Mask separating object from background. | |
[out] | bounding_box | Optionally return bounding box of the extracted features. |
std::vector<String> cv::linemod::Detector::classIds | ( | ) | const |
Get the modalities used by this detector.
You are not permitted to add/remove modalities, but you may dynamic_cast them to tweak parameters.
|
inline |
Get sampling step T at pyramid_level.
const std::vector<Template>& cv::linemod::Detector::getTemplates | ( | const String & | class_id, |
int | template_id | ||
) | const |
Get the template pyramid identified by template_id.
For example, with 2 modalities (Gradient, Normal) and two pyramid levels (L0, L1), the order is (GradientL0, NormalL0, GradientL1, NormalL1).
void cv::linemod::Detector::match | ( | const std::vector< Mat > & | sources, |
float | threshold, | ||
std::vector< Match > & | matches, | ||
const std::vector< String > & | class_ids = std::vector< String >() , |
||
OutputArrayOfArrays | quantized_images = noArray() , |
||
const std::vector< Mat > & | masks = std::vector< Mat >() |
||
) | const |
Detect objects by template matching.
Matches globally at the lowest pyramid level, then refines locally stepping up the pyramid.
sources | Source images, one for each modality. | |
threshold | Similarity threshold, a percentage between 0 and 100. | |
[out] | matches | Template matches, sorted by similarity score. |
class_ids | If non-empty, only search for the desired object classes. | |
[out] | quantized_images | Optionally return vector<Mat> of quantized images. |
masks | The masks for consideration during matching. The masks should be CV_8UC1 where 255 represents a valid pixel. If non-empty, the vector must be the same size as sources. Each element must be empty or the same size as its corresponding source. |
|
protected |
|
inline |
int cv::linemod::Detector::numTemplates | ( | ) | const |
int cv::linemod::Detector::numTemplates | ( | const String & | class_id | ) | const |
|
inline |
Get number of pyramid levels used by this detector.
void cv::linemod::Detector::read | ( | const FileNode & | fn | ) |
String cv::linemod::Detector::readClass | ( | const FileNode & | fn, |
const String & | class_id_override = "" |
||
) |
void cv::linemod::Detector::readClasses | ( | const std::vector< String > & | class_ids, |
const String & | format = "templates_%s.yml.gz" |
||
) |
void cv::linemod::Detector::write | ( | FileStorage & | fs | ) | const |
void cv::linemod::Detector::writeClass | ( | const String & | class_id, |
FileStorage & | fs | ||
) | const |
void cv::linemod::Detector::writeClasses | ( | const String & | format = "templates_%s.yml.gz" | ) | const |
|
protected |
|
protected |
|
protected |