Abstract
The intelligentization of unmanned surface vehicles (USVs) has recently attracted intensive interest. Visual perception of the water scenes is critical for the autonomous navigation of USVs. In this paper, an adaptive semantic segmentation method is proposed to recognize the water scenes. A semantic segmentation network model is designed to classify each pixel of an image into water, land or sky. The segmentation result is refined by the conditional random field (CRF) method. It is further improved accordingly by referring to the superpixel map. A weight map is generated based on the prediction confidence. The network trains itself with the refined pseudo label and the weight map. A set of experiments were designed to evaluate the proposed method. The experimental results show that the proposed method exhibits excellent performance with few-shot learning and is quite adaptable to a new environment, very efficient for limited manual labeled data utilization.
Highlights
Research in the field and marine robotics has brought about the rapid development of unmanned surface vehicles (USVs)
In response to the questions mentioned above, we propose an adaptive semantic segmentation algorithm for the USV
In order to to clearly clearly show show the the improvement improvement of the network network prediction prediction during the pseudo generating, the segmentation network is added added pseudo label label generating, the segmentation network is is pre-trained pre-trained with with bad bad training training data data that that is with noise
Summary
Research in the field and marine robotics has brought about the rapid development of unmanned surface vehicles (USVs). The unmanned intelligent vessels are small-sized and can navigate either programmatically or manually for specific tasks. They are portable and ready to deploy in different environments. Compared with the larger counterparts, they have the ability to navigate at narrow rivers and relatively shallow waters. This broadens the USV application areas, such as marine environmental monitoring, water rescue and geophysical exploration. In order to more intelligently complete various tasks and save labor costs, the USVs should have the ability of autonomous navigation with little manual intervention.
Sign-in/Register to view highlights & summary 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.
