Line segment detection application

Brief Description

Detect line segments in raster

Tags

Feature Extraction

Long Description

This application detects locally straight contours in a image. It is based on Burns, Hanson, and Riseman method and use an a contrario validation approach (Desolneux, Moisan, and Morel). The algorithm was published by Rafael Gromponevon Gioi, Jérémie Jakubowicz, Jean-Michel Morel and Gregory Randall. The given approach compute gradient and level lines of the image and detects aligned points in line support region. The application allows to export the detected lines in a vector data.

Parameters

• [param] Input Image (-in):

• [param] Output Detected lines (-out): Output detected line segments (vector data).

• [param] Digital Elevation Model directory (-dem):

• [param] No rescaling in [0, 255] (-norescale):

Limitations

None

Authors

OTB-Team

See also

On Line demonstration of the LSD algorithm is available here: http://www.ipol.im/pub/algo/gjmr_line_segment_detector/

Example of use

• Parameters to set value:

• Input Image: QB_Suburb.png

• Output Detected lines: LineSegmentDetection.shp

• Command line to execute:

otbcli_LineSegmentDetection -in QB_Suburb.png -out LineSegmentDetection.shp