Investigate UWA data set #6
Description
The paper does not refer to this dataset, but the code refers to "UWA" videos. I believe the data set may be described by another paper:
Siddiqui, S. A., Salman, A., Malik, M. I., Shafait, F., Mian, A., Shortis, M. R., and Harvey, E. S. 2017. Automatic fish species classification in underwater videos: exploiting pre-trained deep neural network models to compensate for limited labelled data. – ICES Journal of Marine Science, 75: 374–389.
Videos were collected from several baited remote underwater video sampling programs that occurred between Cape Naturaliste and the Houtman Abrolhos islands in the temperate and subtropical coastal waters of Western Australia during 2011–2013. Videos were collected from kelp, seagrass, sand and coral reef habitats between 5 and 50 m of water depth. The sampling location of fish spread across the coast of Western Australia and does not represent the actual frequency distribution of target fish species in that location. The data used in this study are extracted from the videos in a way to achieve the minimum number of samples required to train the classifiers hence, covers only a fraction of actual recorded data.