Fish behavior analysis

In this chapter, we address fish behavior analysis in unconstrained underwater videos. Assessing this is based on unusual fish trajectory detection which tries to detect rare fish behaviors, which can help marine biologists to detect new behaviors and to detect environmental changes observed from the unusual trajectories of fish. Fish trajectories are classified as normal and unusual which are the common behaviors of fish and the behaviors that are rare respectively. We investigated three different classification methods to detect unusual fish trajectories. The first method is a filtering method to eliminate normal trajectories, the second method is based on labeled and clustered data and the third method constructs a hierarchy using clustered and labeled data based on data similarity. The first two methods can be seen as preliminary works while the results of them are significant considering the challenges of underwater environments and highly imbalanced trajectory data that we used. In this chapter, we briefly summarize these two methods and mainly focus on the third method (hierarchial decomposition) which presented improved results and performed better than the state of art methods.