NOAA Fisheries Strategic Initiative on Automated Image Analysis

 

Breaking News

  1. NOAA Fisheries AIASI announces VIAME: An Open Source Framework for Underwater Image Processing

  2. September 20-23: First VIAME Hackathon (NOAA Northwest Fisheries Science Center)

Mission

The mission of the NOAA Fisheries Strategic Initiative on Automated image analysis is to develop guidelines, set priorities, and fund projects to develop broad-scale, standardized, and efficient automated tools for the analysis of optical data for use in stock assessment.

Goal

To create an end-to-end open source software toolkit allowing for the automated analysis of optical data streams to provide fishery-independent abundance estimates for use in stock assessment.

Background

NOAA Fisheries’ stock assessments are key to marine resource management. They provide high-quality science information to managers to answer important questions such as:

  1. What is the current status of a stock relative to established targets?

  2. How much catch is sustainable while maintaining a healthy stock?

  3. If a stock becomes depleted, what steps are required to rebuild it to healthy abundance levels?

Answers to these questions help managers make the best decisions to ensure sustainable fisheries, healthy ecosystems, and productive coastal communities.

The demand to improve stock assessments drives a need for improved data, particularly more precise, accurate, efficient and timely scientific surveys of fish abundance and their associated habitat and ecosystem.  A report from the National Task Force for Improving Fish Stock Assessments found that for more than 40% of the 904 stocks listed in the 1999 Report to Congress on the Status of Fisheries of the United States (NMFS 1999a), there is no index of abundance, which makes it extremely difficult to conduct a meaningful assessment. Increasingly, NOAA Fisheries and other agencies are employing camera-based surveys to estimate size-structured abundance for key stocks. However, the volume of data produced by camera-based survey platforms quickly exceeds the capabilities of human analysis. Automated video analysis solutions are needed to extract species-specific, size-structured abundance measures from optical data streams. To affect this development, the NOAA Fisheries Office of Science and Technology has created the Strategic Initiative on Automated Image Analysis (AIASI).

Optical data provides a variety of advantages, including:

  1. non-extractive sampling

  2. increased precision and accuracy

  3. increased efficiency and spatio-temporal coverage

  4. reduced measurement and calibration errors

  5. reduced inter-observation variation

Challenges

The data streams created by optical survey methods can quickly exceed the capabilities of human analysts.  Many sampling platforms collect hundreds of thousands or millions of high resolution images in a matter of days.  In order to be useful for stock assessment, these optical data streams must be quickly turned into numerical data, such as species, abundance, and size. This is clearly not possible with human analysts and automated tools are needed to improve optical data processing.

The optical data streams under consideration contain a diversity of target types (species and individuals). Many of these targets of interest are morphologically similar and are difficult to distinguish from one another. In many cases targets are imaged against a complex and moving background. Targets may be partially occluded by other targets or by environmental objects. Individuals may leave and then re-enter the viewing frame. In this case, repeat counting of the same individual should be minimized to ensure accurate abundance estimates.

APPROACH

The suggested approach is to convene an international working group composed of agency, academic, and private sector representatives with the following set of tasks:

  1. 1. Identify existing technology and software to meet the stated objectives;

  2. 2. Identify research projects or beta technologies that can be easily developed, modified, or transitioned to meet the stated objectives;

  3. 3. Identify data gaps that impede development of software for automated image analysis;

  4. 4. Identify and rank the principal limitations and deficiencies in the area of automated image analysis as it related to NMFS stocks;

  5. 5. Identify and rank research tracks for the development of automated image analysis solution to meet the stated objectives.  Describe promising new technologies to improve awareness in the assessment and survey programs.

  6. 6. Fund high-ranking research projects to develop technology to meet the stated objectives;

  7. 7. Fund and organize workshops to bring together members of the computer vision, marine science, and stock assessment communities to develop technologies and research tracks to meet the stated objectives.

  8. 8. Consolidate research and development products and develop or catalyze development of an end-to-end open source software toolkit (application) allowing for the automated analysis of optical data streams to provide fishery-independent species-specific, size-structured abundance estimates for use in stock assessment

TIMING

The AIASI panel shall meet at least twice a year for a three to five year term.  At least one of these meeting should be face-to-face.  Panel reports should be sent to OST in late February of each year, and these results can be distributed among the Science Board, stock assessment senior advisor (SASA), and ASTWG in March.

PARTICIPATION

Each regional Science Director shall ensure the participation of an expert in stock assessment, survey, or sampling technologies from their respective Science Center. Additional panel members will come from academia and private industry.  When feasible, the SASA, OST Director and /or national program managers will attend panel meetings to help provide national context.

PRODUCT

The AIASI will strive to develop an end-to-end open source software toolkit allowing for the automated analysis of optical data streams to provide fishery-independent species-specific, size-structured abundance estimates for use in stock assessment.

USAGE

The developed software will be used by:

  1. 1. NOAA Fisheries Regional Science Centers for the routine analysis of optical data streams to produce species-specific, size-structured abundance estimates for key assessment targets.

  2. 2. Regional, State, and Academic Partners the routine analysis of optical data streams to meet regional and local management objectives.  

  3. 3. Academic and private industry partners as they continue to develop and refine automated solutions for analysis of optical data streams.