More information about the project
According to webpage at https://www.zooniverse.org/projects/benjamin-dot-richards/oceaneyes/about/research:
"What is the Stock Assessment Program and What is its Role?
The Stock Assessment Program of the NOAA Pacific Islands Fisheries Science Center is responsible for monitoring fish stocks to help guide management in commercial and recreational fishing. The program is responsible for assessing seven species of bottomfish known as the "Deep 7," which consists of six species of snapper and one species of grouper that are economically and culturally important in the Hawaiian Islands. The program checks and assesses this group by gathering three main data types: Abundance (the amount of fish in the ocean), Biology (mainly observed through life history), and Catch. These three types of data make up what is known as the “A, B, Cs of stock assessment.”
Bottomfish stock assessments currently use “fishery-dependent” data to check abundance. Fishery-dependent data relies on data reported by the commercial fishing industry: fishermen and fish dealers. This type of data is prone to be biased because the amount of fish reported by fishermen and dealers may be affected by a fish’s price on the market or the target fish preference of fishermen. Thus, fishery-dependent data alone may not accurately represent the abundance of fish in the ocean. A series of stock assessment workshops throughout 2001–2005 evaluating existing bottomfish assessment methodologies in the Pacific Islands region stated that the biggest factor preventing accurate, precise, and credible stock assessments was the lack of adequate data.
To help improve the accuracy of stock assessments, a “fishery-independent” survey was conducted by the Science Center in 2016. “Fishery-independent” relies solely on data collected systematically by the researchers, which helps to eliminate the potential biases of fishery-dependent surveys.
Underwater Cameras: Botcam and MOUSS
One way that “fishery-independent” surveys collect data is through the use of stereo-video camera systems. Marine scientists are using stereo-video camera platforms to produce high-resolution, species-specific, size-structured abundance estimates without actually taking any fish out of the ocean. Systems like the BotCam and Modular Optical Underwater Survey System (MOUSS) (seen in the image below) are fully autonomous stationary stereo-video camera systems that have been effectively used to collect fishery-independent species-specific size-structured abundance data on bottomfish in the main Hawaiian Islands. The system consists of two low-light video cameras with an 80° diagonal field of view that can image targets in natural lighting to a depth of 300 meters in Hawaiian waters.
The Botcam camera system (left image) and the MOUSS camera system (right image)
The system is moored to the bottom using an anchor weight attached to an acoustic release or shear pin and anchor line. The cameras are designed to float approximately 10 feet (3 meters) above the seafloor and to record video by pointing at a downward angle of 15 degrees. We chose this configuration because the “Deep 7” species are known to school in the water column at least several meters above the bottom, and are known to favor steep and rocky slopes.
What is Produced = So Many Images!
The fishery-independent survey stereo-video camera systems collect video and camera footage to produce millions of underwater images of fish. To assess abundance, we need to annotate these images. But given so many images, it is difficult for a small team of researchers to annotate them all. Machine-learning algorithms could deal with this issue by annotating all of the images with little to no interference. But the machine-learning algorithms require training data in order to learn how to recognize and identify fish. Humans must analyze and annotate these images to create these training data.
The way that we currently analyze and annotate this footage is through a method called “MaxN,” which is when an analyst scans through the video or images to find the video frame or image with the highest number of each species of interest. We only count or measure the fish within that frame or image, which means that all of the other fish that may have been seen throughout the video are not taken into account. This has been accepted as a standard method only because it is impossible for a small team of people to count fish in every single image.
With your help, it may now become possible to analyze and annotate all of these images to produce training data for computer vision algorithms and to provide a more accurate representation of fish abundance in Hawaiʻi!"