Abstract
Due to its universality, swarm behavior in nature attracts much attention of scientists from many fields. Fish schools are examples of biological communities that demonstrate swarm behavior. The detection and tracking of fish in a school are of important significance for the quantitative research on swarm behavior. However, different from other biological communities, there are three problems in the detection and tracking of fish school, that is, variable appearances, complex motion and frequent occlusion. To solve these problems, we propose an effective method of fish detection and tracking. In this method, first, the fish head region is positioned through extremum detection and ellipse fitting; second, The Kalman filtering and feature matching are used to track the target in complex motion; finally, according to the feature information obtained by the detection and tracking, the tracking problems caused by frequent occlusion are processed through trajectory linking. We apply this method to track swimming fish school of different densities. The experimental results show that the proposed method is both accurate and reliable.
Highlights
There has been growing research interest in animal collective behavior due to its high scientific values and a wide range of potential applications [1,2,3]
What is the principle behind the movement? How do fish schools benefit from these movements to survive? How could we get revelation of bionic algorithm from schooling? These problems have been intriguing many scientists, especially biologists, physicists and computer scientists
In order to overcome the above mentioned difficulties, we propose an effective method for tracking a large number of fish, which has the following advantages
Summary
There has been growing research interest in animal collective behavior due to its high scientific values and a wide range of potential applications [1,2,3]. (2) Tracking problem: first, the motion of fish swimming is so complex that the existing models cannot fully simulate; second, due to the higher degree of similarity among the fish, the use of a single feature method can hardly distinguish between different targets; the detecting errors caused by fish occlusion will lead to a fragmentation in trajectory, adding more difficulties in tracking.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
