OpenCV  3.4.20-dev
Open Source Computer Vision
Classes | Enumerations | Functions


class  cv::AlignExposures
 The base class for algorithms that align images of the same scene with different exposures. More...
class  cv::AlignMTB
 This algorithm converts images to median threshold bitmaps (1 for pixels brighter than median luminance and 0 otherwise) and than aligns the resulting bitmaps using bit operations. More...
class  cv::CalibrateCRF
 The base class for camera response calibration algorithms. More...
class  cv::CalibrateDebevec
 Inverse camera response function is extracted for each brightness value by minimizing an objective function as linear system. Objective function is constructed using pixel values on the same position in all images, extra term is added to make the result smoother. More...
class  cv::CalibrateRobertson
 Inverse camera response function is extracted for each brightness value by minimizing an objective function as linear system. This algorithm uses all image pixels. More...
class  cv::MergeDebevec
 The resulting HDR image is calculated as weighted average of the exposures considering exposure values and camera response. More...
class  cv::MergeExposures
 The base class algorithms that can merge exposure sequence to a single image. More...
class  cv::MergeMertens
 Pixels are weighted using contrast, saturation and well-exposedness measures, than images are combined using laplacian pyramids. More...
class  cv::MergeRobertson
 The resulting HDR image is calculated as weighted average of the exposures considering exposure values and camera response. More...
class  cv::Tonemap
 Base class for tonemapping algorithms - tools that are used to map HDR image to 8-bit range. More...
class  cv::TonemapDrago
 Adaptive logarithmic mapping is a fast global tonemapping algorithm that scales the image in logarithmic domain. More...
class  cv::TonemapMantiuk
 This algorithm transforms image to contrast using gradients on all levels of gaussian pyramid, transforms contrast values to HVS response and scales the response. After this the image is reconstructed from new contrast values. More...
class  cv::TonemapReinhard
 This is a global tonemapping operator that models human visual system. More...


enum  { cv::LDR_SIZE = 256 }


Ptr< AlignMTBcv::createAlignMTB (int max_bits=6, int exclude_range=4, bool cut=true)
 Creates AlignMTB object. More...
Ptr< CalibrateDebeveccv::createCalibrateDebevec (int samples=70, float lambda=10.0f, bool random=false)
 Creates CalibrateDebevec object. More...
Ptr< CalibrateRobertsoncv::createCalibrateRobertson (int max_iter=30, float threshold=0.01f)
 Creates CalibrateRobertson object. More...
Ptr< MergeDebeveccv::createMergeDebevec ()
 Creates MergeDebevec object. More...
Ptr< MergeMertenscv::createMergeMertens (float contrast_weight=1.0f, float saturation_weight=1.0f, float exposure_weight=0.0f)
 Creates MergeMertens object. More...
Ptr< MergeRobertsoncv::createMergeRobertson ()
 Creates MergeRobertson object. More...
Ptr< Tonemapcv::createTonemap (float gamma=1.0f)
 Creates simple linear mapper with gamma correction. More...
Ptr< TonemapDragocv::createTonemapDrago (float gamma=1.0f, float saturation=1.0f, float bias=0.85f)
 Creates TonemapDrago object. More...
Ptr< TonemapMantiukcv::createTonemapMantiuk (float gamma=1.0f, float scale=0.7f, float saturation=1.0f)
 Creates TonemapMantiuk object. More...
Ptr< TonemapReinhardcv::createTonemapReinhard (float gamma=1.0f, float intensity=0.0f, float light_adapt=1.0f, float color_adapt=0.0f)
 Creates TonemapReinhard object. More...

Detailed Description

This section describes high dynamic range imaging algorithms namely tonemapping, exposure alignment, camera calibration with multiple exposures and exposure fusion.

Enumeration Type Documentation

◆ anonymous enum

anonymous enum

#include <opencv2/photo.hpp>

Python: cv.LDR_SIZE

Function Documentation

◆ createAlignMTB()

Ptr<AlignMTB> cv::createAlignMTB ( int  max_bits = 6,
int  exclude_range = 4,
bool  cut = true 
cv.createAlignMTB([, max_bits[, exclude_range[, cut]]]) -> retval

#include <opencv2/photo.hpp>

Creates AlignMTB object.

max_bitslogarithm to the base 2 of maximal shift in each dimension. Values of 5 and 6 are usually good enough (31 and 63 pixels shift respectively).
exclude_rangerange for exclusion bitmap that is constructed to suppress noise around the median value.
cutif true cuts images, otherwise fills the new regions with zeros.

◆ createCalibrateDebevec()

Ptr<CalibrateDebevec> cv::createCalibrateDebevec ( int  samples = 70,
float  lambda = 10.0f,
bool  random = false 
cv.createCalibrateDebevec([, samples[, lambda_[, random]]]) -> retval

#include <opencv2/photo.hpp>

Creates CalibrateDebevec object.

samplesnumber of pixel locations to use
lambdasmoothness term weight. Greater values produce smoother results, but can alter the response.
randomif true sample pixel locations are chosen at random, otherwise they form a rectangular grid.

◆ createCalibrateRobertson()

Ptr<CalibrateRobertson> cv::createCalibrateRobertson ( int  max_iter = 30,
float  threshold = 0.01f 
cv.createCalibrateRobertson([, max_iter[, threshold]]) -> retval

#include <opencv2/photo.hpp>

Creates CalibrateRobertson object.

max_itermaximal number of Gauss-Seidel solver iterations.
thresholdtarget difference between results of two successive steps of the minimization.

◆ createMergeDebevec()

Ptr<MergeDebevec> cv::createMergeDebevec ( )
cv.createMergeDebevec() -> retval

#include <opencv2/photo.hpp>

Creates MergeDebevec object.

◆ createMergeMertens()

Ptr<MergeMertens> cv::createMergeMertens ( float  contrast_weight = 1.0f,
float  saturation_weight = 1.0f,
float  exposure_weight = 0.0f 
cv.createMergeMertens([, contrast_weight[, saturation_weight[, exposure_weight]]]) -> retval

#include <opencv2/photo.hpp>

Creates MergeMertens object.

contrast_weightcontrast measure weight. See MergeMertens.
saturation_weightsaturation measure weight
exposure_weightwell-exposedness measure weight

◆ createMergeRobertson()

Ptr<MergeRobertson> cv::createMergeRobertson ( )
cv.createMergeRobertson() -> retval

#include <opencv2/photo.hpp>

Creates MergeRobertson object.

◆ createTonemap()

Ptr<Tonemap> cv::createTonemap ( float  gamma = 1.0f)
cv.createTonemap([, gamma]) -> retval

#include <opencv2/photo.hpp>

Creates simple linear mapper with gamma correction.

gammapositive value for gamma correction. Gamma value of 1.0 implies no correction, gamma equal to 2.2f is suitable for most displays. Generally gamma > 1 brightens the image and gamma < 1 darkens it.

◆ createTonemapDrago()

Ptr<TonemapDrago> cv::createTonemapDrago ( float  gamma = 1.0f,
float  saturation = 1.0f,
float  bias = 0.85f 
cv.createTonemapDrago([, gamma[, saturation[, bias]]]) -> retval

#include <opencv2/photo.hpp>

Creates TonemapDrago object.

gammagamma value for gamma correction. See createTonemap
saturationpositive saturation enhancement value. 1.0 preserves saturation, values greater than 1 increase saturation and values less than 1 decrease it.
biasvalue for bias function in [0, 1] range. Values from 0.7 to 0.9 usually give best results, default value is 0.85.

◆ createTonemapMantiuk()

Ptr<TonemapMantiuk> cv::createTonemapMantiuk ( float  gamma = 1.0f,
float  scale = 0.7f,
float  saturation = 1.0f 
cv.createTonemapMantiuk([, gamma[, scale[, saturation]]]) -> retval

#include <opencv2/photo.hpp>

Creates TonemapMantiuk object.

gammagamma value for gamma correction. See createTonemap
scalecontrast scale factor. HVS response is multiplied by this parameter, thus compressing dynamic range. Values from 0.6 to 0.9 produce best results.
saturationsaturation enhancement value. See createTonemapDrago

◆ createTonemapReinhard()

Ptr<TonemapReinhard> cv::createTonemapReinhard ( float  gamma = 1.0f,
float  intensity = 0.0f,
float  light_adapt = 1.0f,
float  color_adapt = 0.0f 
cv.createTonemapReinhard([, gamma[, intensity[, light_adapt[, color_adapt]]]]) -> retval

#include <opencv2/photo.hpp>

Creates TonemapReinhard object.

gammagamma value for gamma correction. See createTonemap
intensityresult intensity in [-8, 8] range. Greater intensity produces brighter results.
light_adaptlight adaptation in [0, 1] range. If 1 adaptation is based only on pixel value, if 0 it's global, otherwise it's a weighted mean of this two cases.
color_adaptchromatic adaptation in [0, 1] range. If 1 channels are treated independently, if 0 adaptation level is the same for each channel.