FishSense Lite measures fish length with camera and laser easily
FishSense Lite: A Camera-Based, Single Laser Hardware Framework with Software System for In Situ Fish Length Measurement
Computer Vision and Pattern Recognition
Summary
Measuring fish size underwater usually needs experts or special gear, but FishSense Lite simplifies this with just a camera, a laser pointer, and a printed mount. The laser dot in the photo helps calculate how far the fish is, letting the system figure out its length from the image. The authors tested it with divers and compared it to professional equipment, finding it accurate enough for practical use. They also provide simple steps to get good measurements reliably.
What this means in practice
- •For marine conservation teams: Collect fish length and species data at remote locations using recreational divers with affordable equipment.
- •For animal behavior researchers: Gather size measurements of underwater animals non-invasively during natural observations with minimal gear.
Authors
Christopher L. Crutchfield, Kyle Hu, Nathan Hui, Omair Qazi, Jennifer Loch, Alli Candelmo, Brice X. Semmens, Curt Schurgers, Ryan Kastner
Abstract
Fish stock assessments need fish lengths paired with species from far more places than trained surveyors can reach. Recreational divers already visit many of those places, but measuring a fish underwater has required trained observers or specialist equipment. We present FishSense Lite, which recovers fish length from a single photograph taken with a recreational dive camera, a dive laser pointer, and a 3D-printed mount. The diver aims the laser at a fish and takes a picture; afterward, the dot's position in the image gives the range to the fish, and the range turns the fish's size in the image into a length. A citizen-science program, trained by the system's builders, taught its own divers and collected lengths paired with species for 73 wild fish across seven open-water dives. On seven wild fish also measured by an underwater stereo-imaging system, the two instruments agreed without detectable bias (mean difference +0.8%). On rigid targets of known length, FishSense Lite recovered every target to within 1.3%, and 99% of 1,055 frames fell within a 15% error budget. From the error sources we measure, we derive a field protocol: calibrate against a dive slate on every dive, photograph fish within 15 degrees of perpendicular and beyond 1 m, and take at least ten frames of each.