public class FactoryDetectLineAlgs extends Object
| Constructor and Description |
|---|
FactoryDetectLineAlgs() |
| Modifier and Type | Method and Description |
|---|---|
static <I extends ImageSingleBand,D extends ImageSingleBand> |
houghFoot(int localMaxRadius,
int minCounts,
int minDistanceFromOrigin,
float thresholdEdge,
int maxLines,
Class<I> imageType,
Class<D> derivType)
Detects lines using the foot of norm parametrization, see
DetectLineHoughFoot. |
static <I extends ImageSingleBand,D extends ImageSingleBand> |
houghFootSub(int localMaxRadius,
int minCounts,
int minDistanceFromOrigin,
float thresholdEdge,
int maxLines,
int totalHorizontalDivisions,
int totalVerticalDivisions,
Class<I> imageType,
Class<D> derivType)
Detects lines using a foot of norm parametrization and sub images to reduce degenerate
configurations, see
DetectLineHoughFootSubimage for details. |
static <I extends ImageSingleBand,D extends ImageSingleBand> |
houghPolar(int localMaxRadius,
int minCounts,
double resolutionRange,
double resolutionAngle,
float thresholdEdge,
int maxLines,
Class<I> imageType,
Class<D> derivType)
Creates a Hough line detector based on polar parametrization.
|
static <I extends ImageSingleBand,D extends ImageSingleBand> |
lineRansac(int regionSize,
double thresholdEdge,
double thresholdAngle,
boolean connectLines,
Class<I> imageType,
Class<D> derivType)
Detects line segments inside an image using the
DetectLineSegmentsGridRansac algorithm. |
public static <I extends ImageSingleBand,D extends ImageSingleBand> DetectLineSegmentsGridRansac<I,D> lineRansac(int regionSize, double thresholdEdge, double thresholdAngle, boolean connectLines, Class<I> imageType, Class<D> derivType)
DetectLineSegmentsGridRansac algorithm.regionSize - Size of the region considered. Try 40 and tune.thresholdEdge - Threshold for determining which pixels belong to an edge or not. Try 30 and tune.thresholdAngle - Tolerance in angle for allowing two edgels to be paired up, in radians. Try 2.36connectLines - Should lines be connected and optimized.imageType - Type of single band input image.derivType - Image derivative type.DetectLineSegmentsGridRansacpublic static <I extends ImageSingleBand,D extends ImageSingleBand> DetectLineHoughFoot<I,D> houghFoot(int localMaxRadius, int minCounts, int minDistanceFromOrigin, float thresholdEdge, int maxLines, Class<I> imageType, Class<D> derivType)
DetectLineHoughFoot. The polar
parametrization is more common, but more difficult to tune.I - Input image type.D - Image derivative type.localMaxRadius - Lines in transform space must be a local max in a region with this radius. Try 5;minCounts - Minimum number of counts/votes inside the transformed image. Try 5.minDistanceFromOrigin - Lines which are this close to the origin of the transformed image are ignored. Try 5.thresholdEdge - Threshold for classifying pixels as edge or not. Try 30.maxLines - Maximum number of lines to return. If <= 0 it will return them all.imageType - Type of single band input image.derivType - Image derivative type.DetectLineHoughFootpublic static <I extends ImageSingleBand,D extends ImageSingleBand> DetectLineHoughFootSubimage<I,D> houghFootSub(int localMaxRadius, int minCounts, int minDistanceFromOrigin, float thresholdEdge, int maxLines, int totalHorizontalDivisions, int totalVerticalDivisions, Class<I> imageType, Class<D> derivType)
DetectLineHoughFootSubimage for details.I - Input image type.D - Image derivative type.localMaxRadius - Lines in transform space must be a local max in a region with this radius. Try 5;minCounts - Minimum number of counts/votes inside the transformed image. Try 5.minDistanceFromOrigin - Lines which are this close to the origin of the transformed image are ignored. Try 5.thresholdEdge - Threshold for classifying pixels as edge or not. Try 30.maxLines - Maximum number of lines to return. If <= 0 it will return them all.totalHorizontalDivisions - Number of sub-images in horizontal direction Try 2totalVerticalDivisions - Number of sub images in vertical direction. Try 2imageType - Type of single band input image.derivType - Image derivative type.DetectLineHoughFootSubimagepublic static <I extends ImageSingleBand,D extends ImageSingleBand> DetectLineHoughPolar<I,D> houghPolar(int localMaxRadius, int minCounts, double resolutionRange, double resolutionAngle, float thresholdEdge, int maxLines, Class<I> imageType, Class<D> derivType)
I - Input image type.D - Image derivative type.localMaxRadius - Radius for local maximum suppression. Try 2.minCounts - Minimum number of counts for detected line. Critical tuning parameter and image dependent.resolutionRange - Resolution of line range in pixels. Try 2resolutionAngle - Resolution of line angle in radius. Try PI/180thresholdEdge - Edge detection threshold. Try 50.maxLines - Maximum number of lines to return. If <= 0 it will return them all.imageType - Type of single band input image.derivType - Image derivative type.DetectLineHoughPolarCopyright © 2013. All Rights Reserved.