A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf
.
Development of Fast-RCNN based Dynamic Object Detection Using an Object Motion Tracking Device in Marine Environments
2020
Asia-pacific Journal of Convergent Research Interchange
In this paper, we propose an obstacle identification system and a corresponding algorithm for object motion tracking. The object motion tracking device detects only ships rather than all objects so it can be applied to unmanned surface vehicles' operation in marine environments. When an obstacle is detected, the object motion tracking device identifies and tracks it in real-time according to its movement. Objects are recognized using the Fast-RCNN algorithm, and their positions are measured
doi:10.21742/apjcri.2020.03.05
fatcat:axovvgxydndttcxwokjhj3kmay