The server is under maintenance between 08:00 to 12:00 (GMT+08:00), and please visit later.
We apologize for any inconvenience caused
Login  | Sign Up  |  Oriprobe Inc. Feed
China/Asia On Demand
Journal Articles
Bookmark and Share
Research on Feature Matching Algorithm of Visual-Guidance-Information for ARV Underwater Docking
Pages: 9-15
Year: Issue:  5
Journal: Journal of Ocean Technology

Keyword:  autonomous and remotely-operated vehicle(arv)underwater dockingguidance-informationfeature point matching;
Abstract: The docking of underwater robots and underwater stations is of great significance. In order to solve the problem of close range guidance and positioning in the underwater docking process, a visual SLAM(simultaneous localization and mapping) method based on features of multi-layer guidance-information is proposed to achieve high-precision visual positioning and improve the success rate of underwater docking. The rapid extraction and precise matching of feature points of guidance-information is the key to achieving high-precision visual positioning. This thesis aims at fast and accurate matching of feature points in image in the applications of terminal guidance of ARV(Autonomous &Remotely Operated Vehicle) underwater docking, and proposes a feature matching algorithm for image features combined with guide-light information. The information of relative location is added based on the traditional ORB(Oriented FAST and Rotated BRIEF) algorithm which uses key points and descriptors to characterize feature points. In the stage of feature points extraction, the key points,BRIEF descriptors and relative position information are extracted, and the degree of match between descriptors and relative position information is considered simultaneously in the matching stage, which improves the accuracy and robustness of feature points matching. At the same time, we use guide-light to calculate the scale of the image in the stage of feature points extraction, making the extraction of feature points more accurate and faster.Through experiments, the effectiveness of the algorithm is verified. It is proved that the algorithm proposed in this paper can effectively improve the accuracy of the matching of feature points in the image, and shorten the operation time of the algorithm. It helps to ensure the real-time nature of the positioning algorithm, thereby improving the success rate of underwater docking.
Related Articles
No related articles found