Edgelet 2D Tracking using C++

The sample metavision_edgelet_2d_tracking.cpp demonstrates how to use the Metavision SDK CV3D module to detect and track 2D edgelets in a time surface.

By edgelets, we mean short segments of edges that are locally straight or slightly curved (at max 30°). Edgelets are detected on a grid, by default 16x16 pixels in the sample.

Expected Output

The sample visualizes events and detected and/or tracked edgelets using the following color-code:

  • edgelets that are tracked are shown in green

  • edgelets that are not tracked are shown in red

  • newly detected edgelets are shown in blue

How to start

First, compile the sample as described in this tutorial.

To start the sample based on the live stream from your camera, run:

Linux

./metavision_edgelet_2d_tracking

Windows

metavision_edgelet_2d_tracking.exe

To start the sample, you need to provide recorded data with the full path to a RAW file (here, we use a file from our Sample Recordings):

Linux

./metavision_edgelet_2d_tracking -i marker.raw

Windows

metavision_edgelet_2d_tracking.exe -i marker.raw

To check for additional options:

Linux

./metavision_edgelet_2d_tracking -h

Windows

metavision_edgelet_2d_tracking.exe -h