Vision-based Automatic Obstacle Avoidance for Unmanned Aerial Vehicles

This study proposes a stable flight control and obstacle avoidance algorithm based on vision detection. The stable flight is achieved bases on skyline detection in an image captured by a camera mounted on an unmanned aerial vehicle (UAV), which is combined with obstacle detection to avoid obstacles...

Full description

Saved in:
Bibliographic Details
Published inInternational Information Institute (Tokyo). Information Vol. 17; no. 2; p. 797
Main Authors Chiu, Chung-Cheng, Teng, Yao-Jen, Huang, Kuo-Lung, Lai, Cheng-Chyuan
Format Journal Article
LanguageEnglish
Published Koganei International Information Institute 01.02.2014
Subjects
Aircraft
Algorithms
Cameras
Controllers
Discriminant analysis
Flight control
Image detection
Obstacle avoidance
Obstacles
Receivers & amplifiers
Remote control
Software
Statistical analysis
Transmitters
Unmanned aerial vehicles
Online AccessGet full text

Cover

More Information
Summary:This study proposes a stable flight control and obstacle avoidance algorithm based on vision detection. The stable flight is achieved bases on skyline detection in an image captured by a camera mounted on an unmanned aerial vehicle (UAV), which is combined with obstacle detection to avoid obstacles in the flight path. The voltages of the remote controller are calculated, based on the information related to the skyline and obstacles using a ground computer, which facilitates stable, horizontal flight with obstacle avoidance. The flight control system completes the obstacle avoidance algorithm, and the authors have developed a program interface, which integrate the hardware interface of a digital-to-analog converter, a video capture card, the UAV remote controller, and other components. The experimental results in a virtual environment demonstrate the practical utility of the vision-based flight control method for obstacle avoidance.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:1343-4500
1344-8994