Automated Analysis of Fisheries Information from Digital Stills

Toyon proposes development of a system which performs automated analysis of images for fish population monitoring and fishing regulation enforcement application. The proposed system is capable of processing images collected from autonomous underwater vehicles (AUVs) and remotely operated vehicles (ROVs), as well as images collected using electronic monitoring (EM) cameras used to observe fish catches landed on the decks of vessels. The proposed software prototype will include functions for assisting humans in rapidly and consistently analyzing stereo images, including automation of 3D length measurement of fish, and assisting humans in fish counting and classification applications by cueing to fish locations in video image/data streams. The proposed system is based on advanced algorithms developed in Phase I, which will be optimized and implemented in real-time software with a convenient user interface in Phase II. The software prototype will be optimized for assisting NOAA scientists in AUV imagery analysis, and Toyon will support software integration and testing in collaboration with NOAA scientists in Phase II. The utility of the algorithms for EM applications will also be tested and demonstrated, and commercialization opportunities in the commercial fishing industry will be pursued in conjunction with deployment of EM systems.