Turn an underwater image into seagrass data

This model is a patch-based coarse image segmentation framework designed for seagrass morphological identification and marine habitat mapping across eight distinct classes: seven seagrass morphology classes and one background class. Compared with the Australian model, it excludes the ferny morphology class because this type, specifically Halophila spinulosa, is rare or absent in the target Indo-Pacific regions. The framework processes high-resolution benthic imagery by dividing each image into fixed-size patches (e.g., 280×280 pixels), and classifying each patch into a foreground seagrass morphology class, such as strappy or stemmy, or into a single background category, labelled as others. By aggregating patch-level predictions, the model estimates morphology-level seagrass coverage as a percentage of the total image area, providing a scalable and automated tool for seagrass distribution and density assessment.

This model is a patch-based coarse image segmentation framework designed for seagrass morphological identification and marine habitat mapping across 9 distinct classes (8 seagrass morphology classes and one background class). Compared to the Indo model, it introduces an additional morphological class for the ferny type, specifically Halophila spinulosa. The framework processes high-resolution imagery by dividing it into fixed-size patches (e.g., 280x280 pixels) and classifying each patch into a specific foreground seagrass morphological class (e.g., strappy, stemmy, or ferny) or a single background category (i.e., others). By aggregating these patch-level predictions, the model quantifies morphological seagrass coverage as a percentage of the total area, providing a scalable, automated tool for precise distribution and density assessments.

A computer vision model designed to classify seagrass coverage from subtidal images into 3 cover categories : low seagrass cover (≥3 <10%), medium seagrass cover
(≥10 <30%), and high seagrass cover (≥30%). The percent coverage used as reference is from Seagrass-Watch percent cover standards on a 50x50cm quadrat. Please only use the model on images with at least 3% seagrass cover.

A computer vision model designed to identify the presence of specific seagrass species morphologies from subtidal images. The morphologies identified are : oval, strappy, ferny and cylindrical. Please only use the model on images with at least 3% seagrass cover.

A computer vision model designed identify the presence of seagrass from subtidal images. The percent coverage used as reference is from Seagrass-Watch percent cover standards on a 50x50cm quadrat. Please only use the model on images with at least 3% seagrass cover.