Loading...
Searching...
No Matches
cv::cuda::StereoSGM Class Referenceabstract
The class implements the modified H. Hirschmuller algorithm [HH08]. Limitation and difference are as follows: More...
#include <opencv2/cudastereo.hpp>
Inheritance diagram for cv::cuda::StereoSGM:

Public Member Functions | |
virtual void | compute (InputArray left, InputArray right, OutputArray disparity) CV_OVERRIDE=0 |
Computes disparity map for the specified stereo pair. | |
virtual void | compute (InputArray left, InputArray right, OutputArray disparity, Stream &stream)=0 |
Computes disparity map with specified CUDA Stream. | |
![]() | |
virtual int | getMode () const =0 |
virtual int | getP1 () const =0 |
virtual int | getP2 () const =0 |
virtual int | getPreFilterCap () const =0 |
virtual int | getUniquenessRatio () const =0 |
virtual void | setMode (int mode)=0 |
virtual void | setP1 (int P1)=0 |
virtual void | setP2 (int P2)=0 |
virtual void | setPreFilterCap (int preFilterCap)=0 |
virtual void | setUniquenessRatio (int uniquenessRatio)=0 |
![]() | |
virtual void | compute (InputArray left, InputArray right, OutputArray disparity)=0 |
Computes disparity map for the specified stereo pair. | |
virtual int | getBlockSize () const =0 |
virtual int | getDisp12MaxDiff () const =0 |
virtual int | getMinDisparity () const =0 |
virtual int | getNumDisparities () const =0 |
virtual int | getSpeckleRange () const =0 |
virtual int | getSpeckleWindowSize () const =0 |
virtual void | setBlockSize (int blockSize)=0 |
virtual void | setDisp12MaxDiff (int disp12MaxDiff)=0 |
virtual void | setMinDisparity (int minDisparity)=0 |
virtual void | setNumDisparities (int numDisparities)=0 |
virtual void | setSpeckleRange (int speckleRange)=0 |
virtual void | setSpeckleWindowSize (int speckleWindowSize)=0 |
![]() | |
Algorithm () | |
virtual | ~Algorithm () |
virtual void | clear () |
Clears the algorithm state. | |
virtual bool | empty () const |
Returns true if the Algorithm is empty (e.g. in the very beginning or after unsuccessful read. | |
virtual String | getDefaultName () const |
virtual void | read (const FileNode &fn) |
Reads algorithm parameters from a file storage. | |
virtual void | save (const String &filename) const |
void | write (const Ptr< FileStorage > &fs, const String &name=String()) const |
virtual void | write (FileStorage &fs) const |
Stores algorithm parameters in a file storage. | |
void | write (FileStorage &fs, const String &name) const |
Additional Inherited Members | |
![]() | |
enum | { MODE_SGBM = 0 , MODE_HH = 1 , MODE_SGBM_3WAY = 2 , MODE_HH4 = 3 } |
![]() | |
enum | { DISP_SHIFT = 4 , DISP_SCALE = (1 << DISP_SHIFT) } |
![]() | |
static Ptr< StereoSGBM > | create (int minDisparity=0, int numDisparities=16, int blockSize=3, int P1=0, int P2=0, int disp12MaxDiff=0, int preFilterCap=0, int uniquenessRatio=0, int speckleWindowSize=0, int speckleRange=0, int mode=StereoSGBM::MODE_SGBM) |
Creates StereoSGBM object. | |
![]() | |
template<typename _Tp > | |
static Ptr< _Tp > | load (const String &filename, const String &objname=String()) |
Loads algorithm from the file. | |
template<typename _Tp > | |
static Ptr< _Tp > | loadFromString (const String &strModel, const String &objname=String()) |
Loads algorithm from a String. | |
template<typename _Tp > | |
static Ptr< _Tp > | read (const FileNode &fn) |
Reads algorithm from the file node. | |
![]() | |
void | writeFormat (FileStorage &fs) const |
Detailed Description
The class implements the modified H. Hirschmuller algorithm [HH08]. Limitation and difference are as follows:
- By default, the algorithm uses only 4 directions which are horizontal and vertical path instead of 8. Set mode=StereoSGM::MODE_HH in createStereoSGM to run the full variant of the algorithm.
- Mutual Information cost function is not implemented. Instead, Center-Symmetric Census Transform with \(9 \times 7\) window size from [Spangenberg2013] is used for robustness.
- See also
- cv::StereoSGBM
Member Function Documentation
◆ compute() [1/2]
|
pure virtual |
Computes disparity map for the specified stereo pair.
- Parameters
-
left Left 8-bit or 16-bit unsigned single-channel image. right Right image of the same size and the same type as the left one. disparity Output disparity map. It has the same size as the input images. StereoSGM computes 16-bit fixed-point disparity map (where each disparity value has 4 fractional bits).
Implements cv::StereoMatcher.
◆ compute() [2/2]
|
pure virtual |
The documentation for this class was generated from the following file:
- opencv2/cudastereo.hpp