This dataset is a test dataset of image patches created from the 'novel-test' split of the Global Wetlands Luderick-Seagrass dataset. The original images were divided as a grid into 50 image patches. The image patches were manually labeled into 'Background', 'Fish' and 'Seagrass' sets. The images were otherwise unaltered. We contribute this test dataset of underwater image patches to facilitate evaluation of coarse segmentation seagrass methods. Original dataset description: "This dataset comprises of annotated footage of Girella tricuspidata in two estuary systems in South East Queensland, Australia. This data is suitable for a range of classification and object detection research in unconstrained underwater environments." Original dataset citation: Ditria, Ellen M; Connolly, Rod M; Jinks, Eric L; Lopez-Marcano, Sebastian (2021): Annotated video footage for automated identification and counting of fish in unconstrained marine environments. PANGAEA, https://doi.org/10.1594/PANGAEA.926930. The original dataset is available at: https://github.com/globalwetlands/luderick-seagrass https://download.pangaea.de/dataset/926930/files/Fish_automated_identification_and_counting.zip https://globalwetlands.blob.core.windows.net/globalwetlands-public/datasets/luderick-seagrass/luderick-seagrass.zip

{"references": ["Ditria, E. M., Connolly, R. M., Jinks, E. L., & Lopez-Marcano, S. (2021). Annotated video footage for automated identification and counting of fish in unconstrained seagrass habitats. Frontiers in Marine Science, 8, 629485.", "Raine, S., Marchant, R., Kusy, B., Maire, F., & Fischer, T. (2023). Image labels are all you need for coarse seagrass segmentation. arXiv preprint arXiv:2303.00973."]}