Affiliation:
1. National Taipei University of Technology
Abstract
An embedded vision recognition system is developed for a regular UAH to provide guidance information during hovering and landing. An innovative landing mark has been designed to facilitate the image processing while provide relative heading, height, and coordinate for navigation. The system can provide 30 Hz updating rate to the UAH avionic system. Simulation and real-world tests have shown promising performance and results for future applications.
Publisher
Trans Tech Publications, Ltd.
Reference11 articles.
1. ADSP-BF561 Blackfin® Processor Hardware Reference, Revision 1. 0, (2005).
2. ADSP-BF561 EZ-KIT Lite® Evaluation System Manual, Revision 3. 0, (2006).
3. Wen-Hsiang Tsai and Zhi-Fang Yang, Using parallel line information for vision-based landmark location estimation and an application to automatic helicopter landing1, Robotics and Computer Integrated Manufacturing 14, pp.297-306 , (1998).
4. Andrea Cesetti, Emanuele Frontoni, Adriano Mancini, Primo Zingaretti and Sauro Longhi, Vision-based Autonomous Navigation and Landing of an Unmanned Aerial Vehicle using Natural Landmarks, 17th Mediterranean Conference on Control & Automation, (2009).
5. Srikanth Saripalli, James F. Montgomery, and Gaurav S. Sukhatme, Visually Guided Landing of an Unmanned Aerial Vehicle, IEEE Transactions on Robotics and Automation, Vol. 19, No. 3, (2003).