Vision-based horizon detection and target tracking for UAVs

Authors:
Yingju Chen;Ahmad Abushakra;Jeongkyu Lee
Affiliations:
Department of Computer Science and Engineering, University of Bridgeport, Bridgeport, CT;Department of Computer Science and Engineering, University of Bridgeport, Bridgeport, CT;Department of Computer Science and Engineering, University of Bridgeport, Bridgeport, CT
Venue:
ISVC'11 Proceedings of the 7th international conference on Advances in visual computing - Volume Part II
Year:
2011

Citing 2
Cited 0

The Design and Analysis of the Unmanned Aerial Vehicle Navigation and Altimeter

ICCSIT '08 Proceedings of the 2008 International Conference on Computer Science and Information Technology
An iterative image registration technique with an application to stereo vision

IJCAI'81 Proceedings of the 7th international joint conference on Artificial intelligence - Volume 2

Quantified Score

Hi-index	0.00

Visualization

Abstract

Unmanned Aerial Vehicle (UAV) has been deployed in a variety of applications like remote traffic surveillance, dangerous area observation, and mine removal, since it is able to overcome the limitations of ground vehicles. It can also be used for traffic controlling, border patrolling, accident and natural disaster monitoring for search and rescue purpose. There are two important tasks in the UAV system, automatic stabilization and target tracking. Automatic stabilization makes a UAV fully autonomous, while target tracking alleviates the overhead of a manual system. In order to address these, we present computer vision based horizon detection and target tracking for the videos captured by UAV camera. The proposed horizon detection algorithm is an enhancement of the Cornall's Theorem and our target tracking employs optical flow. The results of both real and simulated videos show that the proposed algorithms are promising.