Abstract

Zebrafish are widely used for drug development and behavioral pattern studies. The currently employed zebrafish re-identification methods rely solely on top-view and grayscale images which require a significant amount of annotated data in order to perform well. In this paper, for the first time, we perform zebrafish re-identification using RGB images recorded from a side-view perspective, while keeping the amount of data annotation to a minimum. Inspired by the person re-identification field, two feature descriptors are tested, each encoding both color and texture information, and five metric and subspace learning methods. The contribution of the color and texture components of the feature descriptors were also investigated. We present and evaluate on a novel publicly available dataset of six zebrafish, recorded in a laboratory setup. The results show that a mean average precision of 99% can be achieved by using just 15 annotated samples per fish. This approach shows a clear potential for incorporating the side-view in-formation in the field of zebrafish tracking, as well as a clear argument for utilizing the color information of the zebrafish.
Original languageEnglish
Title of host publicationProceedings - 2020 IEEE Winter Conference on Applications of Computer Vision Workshops, WACVW 2020
Number of pages11
PublisherIEEE
Publication dateMar 2020
Pages1-11
Article number9096922
ISBN (Print)978-1-7281-7163-0
ISBN (Electronic)978-1-7281-7162-3
DOIs
Publication statusPublished - Mar 2020
Event2020 IEEE Winter Conference on Applications of Computer Vision Workshops (WACVW) - Aspen, United States
Duration: 1 Mar 20205 Mar 2020

Conference

Conference2020 IEEE Winter Conference on Applications of Computer Vision Workshops (WACVW)
CountryUnited States
CityAspen
Period01/03/202005/03/2020

Keywords

  • Computer Vision
  • Re-identification
  • Zebrafish

Fingerprint Dive into the research topics of 'Re-Identification of Zebrafish using Metric Learning'. Together they form a unique fingerprint.

  • Projects

    Marine Analytics using Computer Vision

    Pedersen, M.

    01/01/202001/01/2023

    Project: Research

    Datasets

    Cite this

    Haurum, J. B., Karpova, A., Pedersen, M., Bengtson, S. H., & Moeslund, T. B. (2020). Re-Identification of Zebrafish using Metric Learning. In Proceedings - 2020 IEEE Winter Conference on Applications of Computer Vision Workshops, WACVW 2020 (pp. 1-11). [9096922] IEEE. https://doi.org/10.1109/WACVW50321.2020.9096922