VisionWorks Toolkit Reference

September 29, 2015 | 1.0 Release

 All Data Structures Namespaces Files Functions Variables Typedefs Enumerations Enumerator Macros Groups Pages
Hough Transform Demo App

Hough Transform Demo user guide.

Introduction

nvx_demo_hough_transform demonstrates lines and circles detection via Hough Transform.

The demo uses the following pipeline:

                               (frame)
                                  |
                            [ColorConvert]
                                  |
                           [ChannelExtract]
                                  |
                         [ScaleImage (down)]
                                  |
                             [Median3x3]
                                  |
                            [EqualizeHist]
                                  |
           +----------------------+----------------------+
           |                                             |
   [CannyEdgeDetector]                                   |
           |                                             |
       +---+---------------------+----+              [Sobel3x3]
       |                         |    |                  |
       |                         |    +------------------+
       |                         |                       |
[ScaleImage (up)]         [HoughSegments]         [HoughCircles]
       |                         |                       |
    (edges)                 (segments)               (circles)

The input frame is converted to grayscale, downscaled, blurred with Median filter, and equalized. The equalized frame is then processed by Canny Edge Detector and Sobel operator, and the resulting edges image and derivatives are passed to the Hough Circle node to get the final array with detected circles. The edges image is also passed to the Hough Segments node to get the final array with detected lines.

The result from Canny Edge Detector is upscaled into a real image to use for rendering; all other intermediate results are kept in virtual images for graph optimization.

nvx_demo_hough_transform is installed in the following directory:

/usr/share/visionworks/sources/demos/hough_transform

For the steps to build sample applications, see the Samples and Demos section for your OS.

Executing the Hough Transform Demo

./nvx_demo_hough_transform [options]

Command Line Options

This topic provides a list of supported options and the values they consume.

-s, --source

Note
On Vibrante V3Le, V4L platforms hardware accelerated video playback is supported for H.264 elementary streams only.
The V4L platform has a permissions issue. If input data are an H.264 elementary stream, hardware decoder is used and sample must be executed with super user permissions, i.e., with sudo.

-c, --config

-h, --help

Operational Keys