An Automated Fish Migration Pattern Monitoring System Using Shape Descriptors for Pattern Recognition

NON-TECHNICAL SUMMARY: Fish ecology and environmental research scientists have an urgent need for an automated fish recognition system for monitoring fish migration patterns. Many fish species are known to travel for great distances during their life cycle. As they travel past dams equipped with a fish passage, their species, size, total number, and the time are recorded for migration pattern studies. These are very important data for biologists, especially for the research of endangered species and effects of environmental change. This data collection process is currently performed manually at these dam passageways. Manual monitoring and recognition of fish 24 hours a day or reviewing hours of recorded video taps during the entire migration season is a very tedious task and, most of the time, results in unreliable data. Additionally, report generation and access to data are inconvenient. The result of this proposed research project will have great impacts on fish behavior and migration pattern studies, especially for endangered species, as well as the studies of the environmental effects due to man-made changes. Compared to the current process, a fully automated fish recognition system will provide more reliable data with greatly reduced efforts for researchers. This research will lead to an affordable vision system for environmental studies and commercial fishery.