SBIR-STTR Award

The proposed research project will achieve two research objectives, fish tracking and recognition. APPROACH: The focus of this Phase I project is to develop computer vision and pattern recognition algorithms to achieve the objectives. The result of this research will lead to the building of an automated system that is capable of providing real-time fish migration information to the researchers as well as to the public. 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.

Keywords:
computer vision; shape representation; shape analysis; pattern recognition; fish recognition

Fish ecology and environmental research scientists have an urgent need for an automated fish identification system for biological research. Many fish species travel great distances during their life cycle. As they travel past a narrow passage on the rivers or dams that are equipped with a fish ladder, their species, size, total number, and the time can be recorded for migration pattern and population studies. These are very important data for biologists, especially for the research of endangered species and effects of environmental change. Manual monitoring and recognition of fish 24 hours a day or reviewing hours of video tapes recorded at fish passageways during the entire migration season is a very tedious task and, frequently results in unreliable data. At places where monitoring facilities are not available, fish must be captured, measured, and counted manually. This invasive method, although not preferable, may be the only option available. Tests conducted in Phase I show very promising results and prove that such an automated system is feasible. This Phase II project proposes to improve the fish tracking and recognition algorithms, conduct extensive field testing in varying conditions, construct an underwater camera system, and develop and prepare to market a commercial product.