Waterline and obstacle detection in images from low-cost autonomous boats for environmental monitoring
Anno:
2020
Tipologia prodotto:
Articolo in Rivista
Tipologia ANVUR:
Articolo su rivista
Lingua:
Inglese
Referee:
No
Nome rivista:
Robotics and Autonomous Systems
ISSN Rivista:
0921-8890
N° Volume:
124
Intervallo pagine:
103346-103356
Parole chiave:
Water detection, Autonomous surface vessels, Robotic boats, Robot vision, Water quality monitoring
Breve descrizione dei contenuti:
Waterline detection from images taken by cameras mounted on low-cost autonomous surface vehicles(ASVs) is a key process for obtaining a fast obstacle detection. Achieving an accurate waterlineprediction is difficult due to the instability of the ASV on which the camera is mounted and thepresence of reflections, illumination changes, and waves. In this work, we present a method forwaterline and obstacle detection designed for low-cost ASVs employed in environmental monitoring.The proposed approach is made of two steps: (1) a pixel-wise segmentation of the current image isused to generate a binary mask separating water and non-water regions, (2) the mask is analyzedto infer the position of the waterline, which in turn is used for detecting obstacles. Experimentswere carried out on two publicly available datasets containing floating obstacles such as buoys, sailingand motor boats, and swans moving near the ASV. Quantitative results show the effectiveness of theproposed approach with 98.8% pixel-wise segmentation accuracy running at 10 frames per second onan embedded GPU board