OpenCV 4.12.0
開源計算機視覺
載入中...
搜尋中...
無匹配項
cv::xfeatures2d::MSDDetector 類參考abstract

實現 MSD (Maximal Self-Dissimilarity,最大自相異性) 關鍵點檢測器的類,在 [274] 中有描述。更多...

#include <opencv2/xfeatures2d.hpp>

cv::xfeatures2d::MSDDetector 協作圖

公共成員函式

virtual bool getComputeOrientation () const =0
 
String getDefaultName () const CV_OVERRIDE
 
virtual int getKNN () const =0
 
virtual int getNmsRadius () const =0
 
virtual int getNmsScaleRadius () const =0
 
virtual int getNScales () const =0
 
virtual int getPatchRadius () const =0
 
virtual float getScaleFactor () const =0
 
virtual int getSearchAreaRadius () const =0
 
virtual float getThSaliency () const =0
 
virtual void setComputeOrientation (bool compute_orientation)=0
 
virtual void setKNN (int kNN)=0
 
virtual void setNmsRadius (int nms_radius)=0
 
virtual void setNmsScaleRadius (int nms_scale_radius)=0
 
virtual void setNScales (int use_orientation)=0
 
virtual void setPatchRadius (int patch_radius)=0
 
virtual void setScaleFactor (float scale_factor)=0
 
virtual void setSearchAreaRadius (int use_orientation)=0
 
virtual void setThSaliency (float th_saliency)=0
 
- 繼承自 cv::Feature2D 的公共成員函式
virtual ~Feature2D ()
 
virtual void compute (InputArray image, std::vector< KeyPoint > &keypoints, OutputArray descriptors)
 計算影像中檢測到的一組關鍵點(第一種變體)或影像集(第二種變體)的描述符。
 
virtual void compute (InputArrayOfArrays images, std::vector< std::vector< KeyPoint > > &keypoints, OutputArrayOfArrays descriptors)
 
virtual int defaultNorm () const
 
virtual int descriptorSize () const
 
virtual int descriptorType () const
 
virtual void detect (InputArray image, std::vector< KeyPoint > &keypoints, InputArray mask=noArray())
 檢測影像中(第一種變體)或影像集(第二種變體)的關鍵點。
 
virtual void detect (InputArrayOfArrays images, std::vector< std::vector< KeyPoint > > &keypoints, InputArrayOfArrays masks=noArray())
 
virtual void detectAndCompute (InputArray image, InputArray mask, std::vector< KeyPoint > &keypoints, OutputArray descriptors, bool useProvidedKeypoints=false)
 
virtual bool empty () const CV_OVERRIDE
 如果檢測器物件為空,則返回 true。
 
virtual void read (const FileNode &) CV_OVERRIDE
 從檔案儲存中讀取演算法引數。
 
void read (const String &fileName)
 
void write (const Ptr< FileStorage > &fs, const String &name) const
 
void write (const String &fileName) const
 
virtual void write (FileStorage &) const CV_OVERRIDE
 將演算法引數儲存到檔案儲存中。
 
void write (FileStorage &fs, const String &name) const
 
- 繼承自 cv::Algorithm 的公共成員函式
 Algorithm ()
 
virtual ~Algorithm ()
 
virtual void clear ()
 清除演算法狀態。
 
virtual void save (const String &filename) const
 
void write (const Ptr< FileStorage > &fs, const String &name=String()) const
 
void write (FileStorage &fs, const String &name) const
 

靜態公共成員函式

static Ptr< MSDDetectorcreate (int m_patch_radius=3, int m_search_area_radius=5, int m_nms_radius=5, int m_nms_scale_radius=0, float m_th_saliency=250.0f, int m_kNN=4, float m_scale_factor=1.25f, int m_n_scales=-1, bool m_compute_orientation=false)
 
- 繼承自 cv::Algorithm 的靜態公共成員函式
template<typename _Tp >
static Ptr< _Tpload (const String &filename, const String &objname=String())
 從檔案中載入演算法。
 
template<typename _Tp >
static Ptr< _TploadFromString (const String &strModel, const String &objname=String())
 從字串載入演算法。
 
template<typename _Tp >
static Ptr< _Tpread (const FileNode &fn)
 從檔案節點讀取演算法。
 

附加繼承成員

- 繼承自 cv::Algorithm 的保護成員函式
void writeFormat (FileStorage &fs) const
 

詳細描述

實現 MSD (Maximal Self-Dissimilarity,最大自相異性) 關鍵點檢測器的類,在 [274] 中有描述。

該演算法實現了一種新穎的興趣點檢測器,其靈感來源於這樣的直覺:影像塊在其周圍相對較大的範圍內表現出高度的非相似性,這使得它們具有可重複性和獨特性。這種“上下文自相異性”的概念顛覆了近期成功技術(如區域性自相似性描述符和非區域性均值濾波器)的關鍵正規化,這些技術是基於相似而非非相似塊的存在。此外,它將區域性自相異性概念(嵌入在已有的角點類興趣點檢測器中)擴充套件到上下文資訊,從而提高了可重複性、獨特性和定位精度。

成員函式文件

◆ create()

static Ptr< MSDDetector > cv::xfeatures2d::MSDDetector::create ( int m_patch_radius = 3,
int m_search_area_radius = 5,
int m_nms_radius = 5,
int m_nms_scale_radius = 0,
float m_th_saliency = 250.0f,
int m_kNN = 4,
float m_scale_factor = 1.25f,
int m_n_scales = -1,
bool m_compute_orientation = false )
static
Python
cv.xfeatures2d.MSDDetector.create([, m_patch_radius[, m_search_area_radius[, m_nms_radius[, m_nms_scale_radius[, m_th_saliency[, m_kNN[, m_scale_factor[, m_n_scales[, m_compute_orientation]]]]]]]]]) -> retval
cv.xfeatures2d.MSDDetector_create([, m_patch_radius[, m_search_area_radius[, m_nms_radius[, m_nms_scale_radius[, m_th_saliency[, m_kNN[, m_scale_factor[, m_n_scales[, m_compute_orientation]]]]]]]]]) -> retval

◆ getComputeOrientation()

virtual bool cv::xfeatures2d::MSDDetector::getComputeOrientation ( ) const
純虛擬函式
Python
cv.xfeatures2d.MSDDetector.getComputeOrientation() -> retval

◆ getDefaultName()

String cv::xfeatures2d::MSDDetector::getDefaultName ( ) const
virtual
Python
cv.xfeatures2d.MSDDetector.getDefaultName() -> retval

返回演算法的字串識別符號。當物件儲存到檔案或字串時,此字串用作頂層 xml/yml 節點標籤。

重寫自 cv::Feature2D

◆ getKNN()

virtual int cv::xfeatures2d::MSDDetector::getKNN ( ) const
純虛擬函式
Python
cv.xfeatures2d.MSDDetector.getKNN() -> retval

◆ getNmsRadius()

virtual int cv::xfeatures2d::MSDDetector::getNmsRadius ( ) const
純虛擬函式
Python
cv.xfeatures2d.MSDDetector.getNmsRadius() -> retval

◆ getNmsScaleRadius()

virtual int cv::xfeatures2d::MSDDetector::getNmsScaleRadius ( ) const
純虛擬函式
Python
cv.xfeatures2d.MSDDetector.getNmsScaleRadius() -> retval

◆ getNScales()

virtual int cv::xfeatures2d::MSDDetector::getNScales ( ) const
純虛擬函式
Python
cv.xfeatures2d.MSDDetector.getNScales() -> retval

◆ getPatchRadius()

virtual int cv::xfeatures2d::MSDDetector::getPatchRadius ( ) const
純虛擬函式
Python
cv.xfeatures2d.MSDDetector.getPatchRadius() -> retval

◆ getScaleFactor()

virtual float cv::xfeatures2d::MSDDetector::getScaleFactor ( ) const
純虛擬函式
Python
cv.xfeatures2d.MSDDetector.getScaleFactor() -> retval

◆ getSearchAreaRadius()

virtual int cv::xfeatures2d::MSDDetector::getSearchAreaRadius ( ) const
純虛擬函式
Python
cv.xfeatures2d.MSDDetector.getSearchAreaRadius() -> retval

◆ getThSaliency()

virtual float cv::xfeatures2d::MSDDetector::getThSaliency ( ) const
純虛擬函式
Python
cv.xfeatures2d.MSDDetector.getThSaliency() -> retval

◆ setComputeOrientation()

virtual void cv::xfeatures2d::MSDDetector::setComputeOrientation ( bool compute_orientation)
純虛擬函式
Python
cv.xfeatures2d.MSDDetector.setComputeOrientation(compute_orientation) ->

◆ setKNN()

virtual void cv::xfeatures2d::MSDDetector::setKNN ( int kNN)
純虛擬函式
Python
cv.xfeatures2d.MSDDetector.setKNN(kNN) ->

◆ setNmsRadius()

virtual void cv::xfeatures2d::MSDDetector::setNmsRadius ( int nms_radius)
純虛擬函式
Python
cv.xfeatures2d.MSDDetector.setNmsRadius(nms_radius) ->

◆ setNmsScaleRadius()

virtual void cv::xfeatures2d::MSDDetector::setNmsScaleRadius ( int nms_scale_radius)
純虛擬函式
Python
cv.xfeatures2d.MSDDetector.setNmsScaleRadius(nms_scale_radius) ->

◆ setNScales()

virtual void cv::xfeatures2d::MSDDetector::setNScales ( int use_orientation)
純虛擬函式
Python
cv.xfeatures2d.MSDDetector.setNScales(use_orientation) ->

◆ setPatchRadius()

virtual void cv::xfeatures2d::MSDDetector::setPatchRadius ( int patch_radius)
純虛擬函式
Python
cv.xfeatures2d.MSDDetector.setPatchRadius(patch_radius) ->

◆ setScaleFactor()

virtual void cv::xfeatures2d::MSDDetector::setScaleFactor ( float scale_factor)
純虛擬函式
Python
cv.xfeatures2d.MSDDetector.setScaleFactor(scale_factor) ->

◆ setSearchAreaRadius()

virtual void cv::xfeatures2d::MSDDetector::setSearchAreaRadius ( int use_orientation)
純虛擬函式
Python
cv.xfeatures2d.MSDDetector.setSearchAreaRadius(use_orientation) ->

◆ setThSaliency()

virtual void cv::xfeatures2d::MSDDetector::setThSaliency ( float th_saliency)
純虛擬函式
Python
cv.xfeatures2d.MSDDetector.setThSaliency(th_saliency) ->

此類的文件是從以下檔案生成的