Pockmark Bounding Box Detection and Segmentation Labels

This dataset contains 256x256 pixel jpeg images of gridded depth values as well as binary masks for pixels containing pockmarks (these jpegs are merged together with the depth image on the left and the mask on the right, making a 512x256 image). These are contained within the subdirectory 'PockmarkMaskAnnotations'.

Additionally, this dataset contains a csv containing bounding box annotations (label, bounding box coordinates in terms of image pixels, and a unique integer for the label) of pockmarks in each image. These are contained within the subdirectory 'PockmarkBoxAnnotations'.

Together, these annotations can be used to construct either a bounding box object detector, a bounding box and mask object detector, or a semantic segmentation model.

These were the labels used for the experiments described in Lundine et al., 2023. See this reference to find original data sources to the collected bathymetry data.

Lundine, M., Brothers, L., Trembanis, A., Deep learning-based pockmark detection: implications for quantitative seafloor characterization, Geomorphology, 2023, Volume 421, 108524, https://doi.org/10.1016/j.geomorph.2022.108524.