Abstract
Aiming at the complicated problems of the detection task of marine ship targets such as complex environment, changing light, and deformation of ship targets, this paper designs a ROS-based visual perception method for autonomous maritime navigation. This method uses the YOLOV3 algorithm integrated with the Densenet network to obtain target category and location information from multiple targets at sea. The method is based on the Robot Operating System (ROS) to develop an overall solution for system development and engineering application verification. A visual perception system based on ROS in autonomous navigation is formed through the multi-level selection of software algorithms and system frameworks. The experimental results show that the visual perception method based on ROS designed in this paper can realize rapid detection and positioning of objects in autonomous navigation of ships. Compared with the traditional image processing method, it has better robustness to the target shape and environmental diversity.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
