Boulders provide ecologically important hard grounds in shelf seas, and form protected habitats under the European Habitats Directive. Boulders on the seafloor can usually be recognized in backscatter mosaics due to a characteristic pattern of high backscatter intensity followed by an acoustic shadow. The manual identification of boulders on mosaics is tedious and subjective, and thus could benefit from automation. In this study, we train an object detection framework, RetinaNet, based on a neural network backbone, ResNet, to detect boulders in backscatter mosaics derived from a sidescan-sonar operating at 384 kHz. A training dataset comprising 4617 boulders and 2005 negative examples similar to boulders was used to train RetinaNet. The trained model was applied to a test area located in the Kriegers Flak area (Baltic Sea), and the results compared to mosaic interpretation by expert analysis. Some misclassification of water column noise and boundaries of artificial plough marks occurs, but the results of the trained model are comparable to the human interpretation. While the trained model correctly identified a higher number of boulders, the human interpreter had an advantage at recognizing smaller objects comprising a bounding box of less than 7 × 7 pixels. Almost identical performance between the best model and expert analysis was found when classifying boulder density into three classes (0, 1–5, more than 5) over 10,000 m2 areas, with the best performing model reaching an agreement with the human interpretation of 90%.
Subtidal hard substrate habitats are unique habitats in the marine environment. They provide crucial ecosystem services that are socially relevant, such as water clearance or as nursery space for fishes. With increasing marine usage and changing environmental conditions, pressure on reefs is increasing. All relevant directives and conventions around Europe include sublittoral hard substrate habitats in any manner. However, detailed specifications and specific advices about acquisition or delineation of these habitats are internationally rare although the demand for single object detection for e.g., ensuring safe navigation or to understand ecosystem functioning is increasing. To figure out the needs for area wide hard substrate mapping supported by automatic detection routines this paper reviews existing delineation rules and definitions relevant for hard substrate mapping. We focus on progress reached in German approval process resulting in first hydroacoustic mapping advices. In detail, we summarize present knowledge of hard substrate occurrence in the German North Sea and Baltic Sea, describes the development of hard substrate investigations and state of the art mapping techniques as well as automated analysis routines.
1 July 2018 in Estuarine, Coastal and Shelf Science