What is it about?
Line following is a basic behavior which is often used as basis to build more complex behaviors. Also in the International Micro Aerial Vehicle competitions it one of the expected capabilities of a drone. Yet, following a line on the ground is not the same as following a line through the sky. In this study a combination of edge detection and disparity estimation is used, which makes use that objects closeby require more attention (and can be detected because the seem to move faster than objects in the background).
Featured Image
Photo by Max Böttinger on Unsplash
Why is it important?
Following lines with a drone is also an essential capability for real-life applications. Think of aligning your trajectory to fly parallel with a highway, inspecting dikes and railways. In 3D one can think of inspection of power lines (horizontal) and windmills & chimneys (vertical). This is important both for autonomous flight, but also for semi-autonomous flight to aid the operator (so that only have to stear in one direction, relative to the object to follow).
Perspectives
What I like from this study is that my co-author used this experience to start a company, which actually is inspecting windmills and automatically is analysing the camera images for defects.
Dr. Arnoud Visser
Universiteit van Amsterdam
Read the Original
This page is a summary of: Integrating disparity and edge detection algorithms to autonomously follow linear-shaped structures at low altitude, April 2013, Institute of Electrical & Electronics Engineers (IEEE),
DOI: 10.1109/rios.2013.6595319.
You can read the full text:
Contributors
The following have contributed to this page
