Object Recognition from Local Scale-Invariant Features
ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Distinctive Image Features from Scale-Invariant Keypoints
International Journal of Computer Vision
Journal of Intelligent and Robotic Systems
Vision-Based Odometry and SLAM for Medium and High Altitude Flying UAVs
Journal of Intelligent and Robotic Systems
Automatic Battery Replacement System for UAVs: Analysis and Design
Journal of Intelligent and Robotic Systems
Hi-index | 0.00 |
This paper presents a simple and efficient solution to vision guided autonomous landing of a light-weight (ISLANDS--Intelligent Self-Leveling and Nodal Docking System. The advantage of ISLANDS is that it may allow the helicopter upon docking to recharge its batteries or refuel, thus, indirectly increasing endurance and flight range. In order for the helicopter to dock with ISLANDS, an on-board `vision module' coupled with the helicopter attitude controller is developed. This `vision module' detects the location and orientation of ISLANDS and feeds back information to the helicopter attitude controller, which commands the helicopter to descent onto the landing platform at a desired orientation and speed. The Scale Invariant Feature Transform (SIFT) is used for automatic detection of the landing platform based on images captured by a single camera mounted on the helicopter. The detected SIFT features are used to estimate the 3-D orientation of the platform relative to the helicopter using Homography and RANSAC techniques. The focus of this paper is on the vision-guided landing technique in a predefined orientation and not on controller details, which may be found in Shim et al. (1998).