|
1. Project Description
1.1. Background
Electronic monitoring (EM) and electronic reporting (ER) technologies offer a way to obtain independent fishery data onboard vessels where space is limited and/or safety is a concern for human observers. The cost of post-processing EM video data is a substantial portion of the costs for implementing EM. To address this issue, AFSC is currently implementing a multi-year project to develop an automated image processing application for electronic monitoring in Alaska fisheries. Previous FIS/NOP funding is supporting application development and creation of an image library. This library will store images that are easily accessible and necessary to train automatic image processing software development. Capturing high quality images at sea is costly and logistically challenging during fishing operations, and the number of images captured from less frequently occurring species will not meet the number of images or image quality necessary to adequately train a software application. This project aims to collect multiple high definition images of each species of catch that would be encountered at sea in various fisheries operating in the North Pacific. These images will populate the image library and be accessible for development of automated species identification and automated measuring applications.
1.2. History
The Alaska Fisheries Science Center has developed and tested camera chute systems to consistently capture high quality images of fish. To date, initial testing has been completed in the lab and in processing plants. However, these systems have limited deployment due to a lack of industry interest in field testing. To address this lack of data gathering ability, we proposed to collect images from trawl survey catch thus keeping the automatic image processing software application development on track for 2015 and 2016.
1.3. Overview
This project will provide HD images and size data to support applications development needs for the currently funded FIS project “Automated Image Processing for Fisheries Applications”. The image data set will be compared to at-sea sampler information to test the accuracy of EM sizing and automated species identification. We plan to collect a wider range of images during the 2015 Gulf of Alaska Bottom Trawl Survey conducted by the AFSC’s RACE Division. The trawl survey vessel allows for interception of many species that would be difficult to collect from the fishery due to the wide coverage area of the survey and difficulty of collecting multiple images of less frequently occurring species in the fishery. GUI application development for human processing images and video will proceed late in 2014 based on standard images collected from volunteer vessels and a single chartered vessel. High definition images from this project will support automation of species identification beginning July, 2015 as images are recovered from the first leg of the trawl survey.
Principal investigators are currently working with other NMFS, PSMFC and IPHC staff to coordinate installation of camera system(s) on survey vessels operating in the Gulf of Alaska in 2015. These systems could potentially be installed on vessels conducting the GOA IPHC, sablefish and trawl surveys in 2014. A simpler camera system was successfully installed and tested on the sablefish survey in 2013. Advantage of conducting this study on survey vessels, prior to installing on volunteer commercial vessels, is that we will have dedicated personnel onboard to ensure the camera system is operating as it should, and collecting specific catch data required to evaluate the reliability of EM systems to capture catch events and measure length composition.
1.4. Objectives
This EM project addresses the Electronic Monitoring Technology Development area of interest specified by the FIS Request for Proposals (RFP) and the FIS Project Management Team (PMT) for FY 2014 “Develop and promote tools to facilitate timely reporting of fisheries information” by automating and expediting video imagery review and analysis. The project also addresses NMFS’ policy directive on Electronic Technologies and Fishery-Dependent Data Collection; Objective 5. “NOAA Fisheries encourages the use of electronic technologies that utilize open source code or standards that facilitate data integration and offer long-term cost savings rather than becoming dependent on proprietary software.”
This work will provide data to enhance and complement the ongoing research for EM/ER development across the country and in numerous fisheries. In addition, the data and products/deliverables will be developed in open source software code that can be shared with all other NMFS FMC’s, FIN’s, and any other NMFS partners. Also the deliverables will be used by the staff of the North Pacific Fisheries Management Council in assisting with the development of EM monitoring programs.
A camera chute system will be installed on three 25-day legs of the 2015 Gulf of Alaska Bottom Trawl Survey onboard the F/T Alaska Provider. The survey will commence late May and include a dedicated at-sea sampler to collect a minimum of 500 images for each species encountered. Survey catches will be processed with normal AFSC protocols (e.g. von Szalay et al. 2010) and identification standards (Orr et al. 2014). After processing, identified catches will be shunted from the sorting table to the conveyer and camera chute system. A measuring board will be integrated with the camera chute system to allow sampler to enter species for each fish or group of fish being processed. Fish will be sub-sampled for length to allow comparison to EM length to evaluate size accuracy by species.
The at-sea sampler(s) duties will include making sure project protocols for data collection are followed and equipment is operating as designed. Responsibilities will include; 1) managing and maintaining the EM system, 2) recording all invertebrates and fishes caught and randomly sampling length 3) processing sampled catch through the camera chute 4) aid in collection of all other sample data for the cruise.
|
