Paper Info
Title
Particle Filter-Based Predictive Tracking for Robust Fish Counting
Abstract
In this paper we study the use of computer vision techniques for for underwater visual tracking and counting of fishes in vivo. The methodology is based on the application of a Bayesian filtering technique that enables tracking of objects whose number may vary over time. Unlike existing fish-counting methods, this approach provides adequate means for the acquisition of relevant information about characteristics of different fish species such as swimming ability, time of migration and peak flow rates. The system is also able to estimate fish trajectories over time, which can be further used to study their behaviors when swimming in regions of interest. Our experiments demonstrate that the proposed method can operate reliably under severe environmental changes (e.g. variations in water turbidity) and handle problems such as occlusions or large inter-frame motions. The proposed approach was successfully validated with real-world video streams, achieving overall accuracy as high as 81%.
Year
DOI
Venue
2005
10.1109/SIBGRAPI.2005.36
SIBGRAPI
Keywords
Field
DocType
robust fish,particle filter-based predictive tracking,overall accuracy,fish-counting method,adequate mean,underwater visual tracking,computer vision technique,fish trajectory,different fish species,large inter-frame motion,visual tracking,computer vision,application software,particle filter,filtering,robustness,in vivo,flow rate,region of interest,bayesian methods
Computer vision,Computer science,Particle filter,Filter (signal processing),Robustness (computer science),Eye tracking,Artificial intelligence,Application software,Bayesian filtering,Bayesian probability,Underwater
Conference
ISBN
Citations 
PageRank 
0-7695-2389-7
17
1.70
References 
Authors
4
4
Name
Order
Citations
PageRank
Erikson F. Morais1171.70
Mario F. M. Campos2797.01
Flávio L. C. Pádua310210.88
Rodrigo L. Carceroni418218.67