Find boundaries using cubic model
uses the random sample consensus (RANSAC) algorithm to find cubic lane boundary
models that fit a set of boundary points and an approximate width. Each model in
the returned array of boundaries
= findCubicLaneBoundaries(xyBoundaryPoints
,approxBoundaryWidth
)cubicLaneBoundary
objects contains the [A B C
D]
coefficients of its third-degree polynomial equation and the
strength of the boundary estimate.
[
also returns a cell array of inlier boundary points for each boundary model
found, using the previous input arguments.boundaries
,boundaryPoints
]
= findCubicLaneBoundaries(xyBoundaryPoints
,approxBoundaryWidth
)
[___] = findCubicLaneBoundaries(___,
uses options specified by one or more Name,Value
)Name,Value
pair
arguments, with any of the preceding syntaxes.
To fit a single boundary model to a double lane marker, set the
approxBoundaryWidth
argument to be large enough to
include the width spanning both lane markers.
This function uses fitPolynomialRANSAC
(Computer Vision Toolbox) to find cubic
models. Because this algorithm uses random sampling, the output can vary between
runs.
The maxDistance
parameter of fitPolynomialRANSAC
(Computer Vision Toolbox) is set to
half the width specified in the approxBoundaryWidth
argument. Points are considered inliers if they are within the boundary width.
The function obtains the final boundary model using a least-squares fit on the
inlier points.
birdsEyePlot
| birdsEyeView
| cubicLaneBoundary
| monoCamera
| segmentLaneMarkerRidge
| fitPolynomialRANSAC
(Computer Vision Toolbox)