Feature Point Based 3D Tracking of Multiple Fish from Multi-view Images
Overview
Authors
Affiliations
A feature point based method is proposed for tracking multiple fish in 3D space. First, a simplified representation of the object is realized through construction of two feature point models based on its appearance characteristics. After feature points are classified into occluded and non-occluded types, matching and association are performed, respectively. Finally, the object's motion trajectory in 3D space is obtained through integrating multi-view tracking results. Experimental results show that the proposed method can simultaneously track 3D motion trajectories for up to 10 fish accurately and robustly.
Exploring the use of deep learning models for accurate tracking of 3D zebrafish trajectories.
Fan Y, Hsu C, Hsu F, Liao L Front Bioeng Biotechnol. 2024; 12:1461264.
PMID: 39386044 PMC: 11463218. DOI: 10.3389/fbioe.2024.1461264.
Fan Y, Hsu F, Wang Y, Liao L Med Biol Eng Comput. 2023; 61(11):2797-2814.
PMID: 37558927 DOI: 10.1007/s11517-023-02903-1.
Li H, Wang J, Zhang X, Hu Y, Liu Y, Ma Z Fish Physiol Biochem. 2022; 48(5):1333-1347.
PMID: 36103021 DOI: 10.1007/s10695-022-01123-y.
Zhang X, Li P, Li Y J Healthc Eng. 2021; 2021:4959727.
PMID: 34394892 PMC: 8357506. DOI: 10.1155/2021/4959727.
The zebrafish subcortical social brain as a model for studying social behavior disorders.
Geng Y, Peterson R Dis Model Mech. 2019; 12(8).
PMID: 31413047 PMC: 6737945. DOI: 10.1242/dmm.039446.