Have a UROP opening you would like to submit?
Please fill out the form.
Image recognition under water - enhance fisheries management and/or water quality assessments
2: Mechanical Engineering
Theresa Werth: firstname.lastname@example.org
Marine fisheries populations have a large impact on the U.S. economy – from commercial fishing to coastal communities. Overfishing, barriers to migration, and other forms of human activity may impact spawning patterns of these species. Therefore, it is necessary to monitor these populations to maintain sustainable resources, healthy oceans, and marine life. Federal and state agencies deploy camera equipment to monitor fisheries populations. Employees then manually count the number of specimens in the gathered videos and images. Not only is this an inefficient use of resources and employee time, but it can also lead to inaccurate results due to human error. A closely related problem, of interest to some of the industry mentors, is optical bacteria recognition, tracking, and counting. Through the application of deep learning-based image recognition, identification of target species in video and image data can be automated. Current state-of-the-art image recognition relies on Convolutional Neural Networks (CNNs) to achieve learning and recognition. CNNs loosely represent biological neural networks: each neuron, or layer, accomplishes a specific task, such as edge detection. Impact: This project is of interest to fisheries and other animal monitoring applications and water monitoring applications. Such algorithms can be adopted to enhance the capabilities of Fisheries Management in monitoring fisheries populations or adopted to aid in water quality measurement. This is an ongoing project students would join a current team.
Experience and/or interest in Machine learning and data analytics, image visualization, process modelling.