Improving 3-D Zebrafish Tracking With Multiview Data Fusion and Global Association

Authors:
Publisher website
Google Scholar
Abstract
Zebrafish behavioral patterns reveal valuable insights for biomedical research. To accurately identify these patterns, visual tracking systems need to reconstruct 3D trajectories from multi-view video sequences. However, 3D zebrafish tracking faces challenges such as the dynamics in movements, the similarity in appearances, and the distortion caused by different viewpoints. In this paper, we propose a new method for robust 3D zebrafish trajectory reconstruction based on multi-view data fusion and global association. Our method generates reliable segments of 2D/3D trajectories, called tracklets , where we considering short-term cues of appearance similarity and motion consistency and proposing corresponding scoring metrics. Moreover, we use a lazy-reconstruction strategy to enhance the overall accuracy of 3D trajectories by taking into account the global context. Extensive experiments on the public 3D-ZeF20 dataset demonstrate the effectiveness of the proposed method, achieving 67.9% MOTA, 64.3% IDF1, and 55.0 MTBFm.
Funding Information
  • National Key Research and Development Program of China (2022YFB3306500)
  • National Natural Science Foundation of China (61872025)
  • Department of Faculty of Applied Sciences, Macao Polytechnic University, Macau, China (RP/ESCA-03/2020)
  • HAWKEYE Group

This publication has 57 references indexed in Scilit: