Hierarchical segmentation-based software for cover classification analyses of seabed images (Seascape)

Abstract

An important aspect of marine research is to quantify the areal coverage of benthic communities. It is technically feasible to efficiently obtain images of marine environments at different depths and benthic habitats over large spatial and temporal scales. Currently, there is a large and growing library of digital images to analyze, representing a valuable benthic ecological archive. Benthic coverage is the basis of studies on biodiversity, characterization of communities and evaluation of changes over temporal and spatial scales. However, there is still a lack of automatic or semi-automatic analytical methods for deriving ecologically relevant data from these images. We introduce a software program named Seascape to obtain semi-automatically segmented images (patch outlines) from underwater photographs of benthic communities, where each individual patch (species/categories) is routinely associated to its area cover and perimeter. Seascape is an analog to the classical and better known discipline of landscape ecology approach, which focuses on the concept that communities can be observed as a patch mosaic at any scale. The process starts with a hierarchical segmentation, using a color space criteria adapted to the problem of segmenting complex benthic images. As an endproduct, we obtain a set of images segmented into classified homogenous regions at different resolution levels (hierarchical segmentation). To illustrate the versatility and capacity of Seascape, we analyzed 4 digital images from different habitats and depths: coral reefs (Pacific Ocean), coralligenous communities (NW Mediterranean Sea), deep-water coral reefs (NW Mediterranean Sea) and the Antarctic continental shelf (Weddell Sea). The development of this semi-automatic outline tool and its use for classification constitute an important step forward in the analysis and processing time of underwater seabed images at any scale.

Biological data extraction from imagery – How far can we go? A case study from the Mid-Atlantic Ridge

“…The development of a clearer protocol or the use of automated calculations could help resolving the observed discrepancies. In the mean time, several scientific teams started developing software featuring automated techniques for imagery analysis for different marine habitats (Aguzzi et al, 2011;Teixido et al, 2011), including deep-sea hydrothermal vents (Aron et al, 2011). On the longer term and with the use of systematic approaches, imagery will represent an essential tool to evaluate the impacts of global warming and anthropogenic activity in the deep ocean.…”

Structure and biodiversity of coralligenous assemblages dominated by the precious red coral Corallium rubrum over broad spatial scales

“…Corallium rubrum ), cover was measured as the surface attached to the substrate as our main objective was to estimate the cover of each species in the whole assemblage.to characterize the structural complexity. Finally, for the overall set of perennial species, which are characterized by high longevity and slow population dynamics (see Appendix II), we also quantified the spatial configuration using the number of patches (NP), the mean patch size (MPS: mm 2 ) and the mean shape index (MSI) using the Seascape software55. MSI was calculated applying the following formula56:…”

Comparison of manual and semi-automatic underwater imagery analyses for monitoring of benthic hard-bottom organisms at offshore renewable energy installations

“…However, visual data analysis remains challenging. Most common methods for quantitative benthic cover estimation are manual point-based approaches (Foster, 1991;Meese & Tomich, 1992;Leonard & Clark, 1993;Carleton & Done, 1995) and region-based percentage estimation (Meese & Tomich, 1992;Garrabou et al, 1998Garrabou et al, , 2002Teixidó et al, 2002Teixidó et al, , 2011Pech et al, 2004;Guinda et al, 2013). Various software tools exist to aid those analysis methods (Kohler & Gill, 2006;Teixidó et al, 2011;Trygonis & Sini, 2012, etc.…”