2020/06/27 by Riza Rae Pineda, Pineda, Riza Rae, Kristofer delas Peñas +3
Computer Science · Environmental Science · #Advanced Image and Video Retrieval Techniques #Computer Vision and Pattern Recognition (cs.CV) #Coral and Marine Ecosystems Studies #FOS: Computer and information sciences #Water Quality Monitoring Technologies
paper · pdf · doi:10.48550/arxiv.2006.15478
openalex publication_date 2020/06/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Behavior analysis of animals involves the observation of intraspecific and\ninterspecific interactions among various organisms in the environment.\nCollective behavior such as herding in farm animals, flocking of birds, and\nshoaling and schooling of fish provide information on its benefits on\ncollective survival, fitness, reproductive patterns, group decision-making, and\neffects in animal epidemiology. In marine ethology, the investigation of\nbehavioral patterns in schooling species can provide supplemental information\nin the planning and management of marine resources. Currently, damselfish\nspecies, although prevalent in tropical waters, have no adequate established\nbase behavior information. This limits reef managers in efficiently planning\nfor stress and disaster responses in protecting the reef. Visual marine data\ncaptured in the wild are scarce and prone to multiple scene variations,\nprimarily caused by motion and changes in the natural environment. The gathered\nvideos of damselfish by this research exhibit several scene distortions caused\nby erratic camera motions during acquisition. To effectively analyze shoaling\nbehavior given the issues posed by capturing data in the wild, we propose a\npre-processing system that utilizes color correction and image stitching\ntechniques and extracts behavior features for manual analysis.\n