CVLGMar 9, 2021

DeepSeagrass Dataset

arXiv:2103.05226v1Has Code
Originality Synthesis-oriented
AI Analysis

This work provides a new dataset and tools for researchers in marine biology and computer vision to study seagrass species, but it is incremental as it applies existing methods to new data.

The authors introduced the DeepSeagrass dataset, consisting of seagrass images collected in Moreton Bay, Australia, and provided pre-trained models and code for detection and classification of seagrass species at the patch level.

We introduce a dataset of seagrass images collected by a biologist snorkelling in Moreton Bay, Queensland, Australia, as described in our publication: arXiv:2009.09924. The images are labelled at the image-level by collecting images of the same morphotype in a folder hierarchy. We also release pre-trained models and training codes for detection and classification of seagrass species at the patch level at https://github.com/csiro-robotics/deepseagrass.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes