Open AccessFeature point based 3D tracking of multiple fish from multi-view images
Author(s) -
Zhenyu Qian,
Yan Qiu Chen
Publication year - 2017
Publication title -
plos one
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.99
H-Index - 332
ISSN - 1932-6203
DOI - 10.1371/journal.pone.0180254
Subject(s) - computer vision , artificial intelligence , feature (linguistics) , trajectory , tracking (education) , computer science , point (geometry) , matching (statistics) , feature matching , pattern recognition (psychology) , video tracking , representation (politics) , motion (physics) , object (grammar) , feature extraction , mathematics , geometry , physics , psychology , pedagogy , philosophy , linguistics , statistics , astronomy , politics , political science , law
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.