2011: Robust Horizon Finding Algorithm for Real Time Autonomous Navigation based on Monocular Vision

http://sites.google.com/site/arthurdemirandaneto/

This work was supported in part by French National Research Agency / ANR PERCOIVE.

Navigation of an Autonomous Vehicle is based on its interaction with the environment, through information acquired by sensors. The perception of the environment is a major issue in autonomous and (semi)-autonomous systems. This work presents the embedded real-time visual perception problem applied to experimental platform. We propose a robust horizon finding algorithm that finds the horizon line and apply it to generate the navigable area (region of interest). It permits to investigate dynamically only a small portion of the image (road) ahead of the vehicle. From a dynamic threshold search method based on Otsu segmentation and Hough transform, our system is robust to illumination changes and does not need any contrast adjustments. It can also be used with infrared camera.

It is a simple solution that solves the problem related to the visual perception of the environment during the navigation of intelligent vehicles and robots. From an image captured by a single camera, the purpose of it was to present a real-time algorithm capable of identifying the horizon area and apply it to generate the navigable area (region of interest). It is important to notice that our algorithm is not based on previous knowledge of the environment neither camera calibration.

www.kingdombr.com

Category:

Science & Technology

Tags:

• autonomous
• vehicle;
• embedded;
• real-time;
• computer
• vision