1/1
5 files

Data underlying the publication: Automatic discard registration in cluttered environments using deep learning and object tracking: class imbalance, occlusion, and a comparison to human review

dataset
posted on 26.10.2021, 11:40 by Rick Essen, vanRick Essen, van, Arjan Vroegop, A. (Angelo) Mencarelli, Aloysius van Helmond, Linh Nyugen, Jurgen Batsleer, J.J. (Jan Jaap) Poos, Gert Kootstra
Data for training and evaluation of a method for detection and counting demersal fish species in complex, cluttered and occluded environments that can be installed on the
conveyor belts of fishing vessels. The data mainly exists of images of fish on a conveyer belt with the corresponding annotations. This was used to train a neural network (YOLOv3) to detect and classify fish species. Because each fish is visible in multiple images, the fishes were tracked over consecutive images and the total number of fish per specie was counted. These counts were compared to human review.

History

Publisher

4TU.ResearchData

Time coverage

October 2019

Geolocation

North Sea

Format

json pt

Organizations

Farm Technology Group, Wageningen University and Research; Greenhouse Horticulture Unit, Wageningen University and Research; Wageningen Marine Research, Wageningen University and Research; Aquaculture and Fisheries, Wageningen University and Research