The Ciona17 Dataset for Semantic Segmentation of Invasive Species in a Marine Aquaculture Environment
It addresses the problem of semantic segmentation for invasive species in marine aquaculture, providing a new dataset and tool for the computer vision community, but is incremental as it focuses on data creation.
The paper introduces the Ciona17 dataset, the first with pixel-level annotations for invasive species in a marine environment, and reports baseline results using a variant of Fully Convolutional Networks with a mean intersection over union (mIoU) metric.
An original dataset for semantic segmentation, Ciona17, is introduced, which to the best of the authors' knowledge, is the first dataset of its kind with pixel-level annotations pertaining to invasive species in a marine environment. Diverse outdoor illumination, a range of object shapes, colour, and severe occlusion provide a significant real world challenge for the computer vision community. An accompanying ground-truthing tool for superpixel labeling, Truth and Crop, is also introduced. Finally, we provide a baseline using a variant of Fully Convolutional Networks, and report results in terms of the standard mean intersection over union (mIoU) metric.