Wyniki wyszukiwania - BazTech

Ograniczanie wyników

2 Oceanologia

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: epibenthos

Sortuj według:

Ogranicz wyniki do:

Coverage estimation of benthic habitat features by semantic segmentation of underwater imagery from South-eastern Baltic reefs using deep learning models

Šiaulys Andrius, Vaičiukynas Evaldas, Medelytė Saulė, Buškus Kazimieras

Oceanologia

2024

Vol. 66 (2)

286--298

Underwater imagery (UI) is an important and sometimes the only tool for mapping hard-bottom habitats. With the development of new camera systems, from hand-held or simple “drop-down” cameras to ROV/AUV-mounted video systems, video data collection has increased considerably. However, the processing and analysing of vast amounts of imagery can become very labour-intensive, thus making it ineffective both time-wise and financially. This task could be simplified if the processes or their intermediate steps could be done automatically. Luckily, the rise of AI applications for automatic image analysis tasks in the last decade has empowered researchers with robust and effective tools. In this study, two ways to make UI analysis more efficient were tested with eight dominant visual features of the Southeastern Baltic reefs: 1) the simplification of video processing and expert annotation efforts by skipping the video mosaicking step and reducing the number of frames analysed; 2) the application of semantic segmentation of UI using deep learning models. The results showed that the annotation of individual frames provides similar results compared to 2D mosaics; moreover, the reduction of frames by 2–3 times resulted in only minor differences from the baseline. Semantic segmentation using the PSPNet model as the deep learning architecture was extensively evaluated, applying three variants of validation. The accuracy of segmentation, as measured by the intersection-over-union, was mediocre; however, estimates of visual coverage percentages were fair: the difference between the expert annotations and model-predicted segmentation was less than 6–8%, which could be considered an encouraging result.

Epibenthic diversity and productivity on a heavily trawled Barents Sea bank (Tromsøflaket)

Kędra M., Renaud P. E., Andrade H.

Oceanologia

2017

No. 59 (2)

93--101

Shallow Arctic banks have been observed to harbour rich communities of epifaunal organisms, but have not been well-studied with respect to composition or function due to sampling challenges. In order to determine how these banks function in the Barents Sea ecosystem, we used a combination of video and trawl/dredge sampling at several locations on a heavily trawled bank, Tromsøflaket – located at the southwestern entrance to the Barents Sea. We describe components of the benthic community, and calculate secondary production of dominant epifaunal organisms. Forty-six epibenthic taxa were identified, and sponges were a significant part of the surveyed benthic communities. There were differences in diversity and production among areas, mainly related to the intensity of trawling activities. Gamma was the most diverse and productive area, with highest species abundance and biomass. Trawled areas had considerably lower species numbers, and significant differences in epifaunal abundance and biomass were found between all trawled and untrawled areas. Trawling seems to have an impact on the sponge communities: mean individual poriferan biomass was higher in untrawled areas, and, although poriferans were observed in areas subjected to more intensive trawling, they were at least five times less frequent than in untrawled areas.