Struct StereoDepthConfig::CostMatching

Nested Relationships

This struct is a nested type of Class StereoDepthConfig.

Nested Types

Struct Documentation

struct CostMatching

The matching cost is way of measuring the similarity of image locations in stereo correspondence algorithm. Based on the configuration parameters and based on the descriptor type, a linear equation is applied to computing the cost for each candidate disparity at each pixel.

Public Types

enum class DisparityWidth : std::uint32_t

Disparity search range: 64 or 96 pixels are supported by the HW.

Values:

enumerator DISPARITY_64
enumerator DISPARITY_96

Public Functions

DEPTHAI_SERIALIZE(CostMatching, disparityWidth, enableCompanding, invalidDisparityValue, confidenceThreshold, enableSwConfidenceThresholding, linearEquationParameters)

Public Members

DisparityWidth disparityWidth = DisparityWidth::DISPARITY_96

Disparity search range, default 96 pixels.

bool enableCompanding = false

Disparity companding using sparse matching. Matching pixel by pixel for N disparities. Matching every 2nd pixel for M disparitites. Matching every 4th pixel for T disparities. In case of 96 disparities: N=48, M=32, T=16. This way the search range is extended to 176 disparities, by sparse matching. Note: when enabling this flag only depth map will be affected, disparity map is not.

uint8_t invalidDisparityValue = 0

Used only for debug purposes, SW postprocessing handled only invalid value of 0 properly.

uint8_t confidenceThreshold = 55

Disparities with confidence value over this threshold are accepted.

bool enableSwConfidenceThresholding = false

Enable software confidence thresholding. Applicable to RVC4 only.

LinearEquationParameters linearEquationParameters

Cost calculation linear equation parameters.

struct LinearEquationParameters

The linear equation applied for computing the cost is: COMB_COST = α*AD + β*(CTC<<3). CLAMP(COMB_COST >> 5, threshold). Where AD is the Absolute Difference between 2 pixels values. CTC is the Census Transform Cost between 2 pixels, based on Hamming distance (xor). The α and β parameters are subject to fine tuning by the user.

Public Functions

DEPTHAI_SERIALIZE(LinearEquationParameters, alpha, beta, threshold)

Public Members

uint8_t alpha = 0
uint8_t beta = 2
uint8_t threshold = 127