dcv.multiview.stereo.matching

Members

Aliases

CostType

alias CostType = float

Undocumented in source.

CostVolume

alias CostVolume = Slice!(SliceKind.contiguous, [3], CostType*)

Undocumented in source.

DisparityMap

alias DisparityMap = Slice!(SliceKind.contiguous, [2], DisparityType*)

Undocumented in source.

DisparityMethod

alias DisparityMethod = void delegate(const ref StereoPipelineProperties props, CostVolume costVol, DisparityMap disp)

Undocumented in source.

DisparityRefiner

alias DisparityRefiner = void delegate(const ref StereoPipelineProperties props, DisparityMap disp)

Undocumented in source.

DisparityType

alias DisparityType = uint

Undocumented in source.

StereoCostAggregator

alias StereoCostAggregator = void delegate(const ref StereoPipelineProperties props, CostVolume costVol)

Undocumented in source.

StereoCostFunction

alias StereoCostFunction = void delegate(const ref StereoPipelineProperties properties, inout Image left, inout Image right, CostVolume cost)

Undocumented in source.

Classes

StereoMatcher

class StereoMatcher

Handles boilerplate code common to all stereo matching methods.

StereoPipeline

class StereoPipeline

This class provides a framework for constructing stereo matching pipelines that conform to the taxonomy laid out in Scharstein and Szeliski (2002).

Functions

absoluteDifference

StereoCostFunction absoluteDifference()

Creates a StereoCostFunction that computes the pixelwise absolute difference between intensities in the left and right images

bilateralDisparityFilter

DisparityRefiner bilateralDisparityFilter(uint windowSize, float sigmaCol, float sigmaSpace)

Applies a bilateral filter to the disparity map in order to correct outliers.

emptyDisparityMap

DisparityMap emptyDisparityMap()

Creates an empty disparity map

medianDisparityFilter

DisparityRefiner medianDisparityFilter(size_t windowSize)

Applies a median filter to the disparity map in order to correct outliers.

normalisedCrossCorrelation

StereoCostFunction normalisedCrossCorrelation(uint windowSize)

Computes the normalised cross correlation, also known as the cosine similarity, between image patches.

semiGlobalAggregator

StereoCostAggregator semiGlobalAggregator(size_t numPaths, CostType p1, CostType p2)

Implements the cost aggregation method described by Hirschmuller (2007), commonly known as Semi-Global Matching.

semiGlobalMatchingPipeline

StereoPipeline semiGlobalMatchingPipeline(StereoPipelineProperties props, size_t numPaths, CostType p1, CostType p2)

Creates a StereoPipeline that performs semi-global matching.

squaredDifference

StereoCostFunction squaredDifference()

Creates a StereoCostFunction that computes the pixelwise squared difference between intensities in the left and right images

sumAbsoluteDifferences

StereoCostFunction sumAbsoluteDifferences(uint windowSize)

Computes the sum of absolute differences between two image patches in order to compute the matching cost.

winnerTakesAll

DisparityMethod winnerTakesAll()

Implements the naive winner takes all algorithm for computing a diparity map from a cost volume.

Structs

StereoPipelineProperties

struct StereoPipelineProperties

Contains the properties required to build a StereoPipeline

• matching