English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Monocular absolute 3D fish pose estimation allows for efficient fish lengthmeasurement in the longline fisheries, where fishes are under severedeformation during the catching process. This task is challenging since itrequires locating absolute 3D fish keypoints based on a short monocular videoclip. Unlike related works, which either require expensive 3D ground-truth dataand/or multiple-view images to provide depth information, or are limited torigid objects, we propose a novel frame-based method to estimate the absolute3D fish pose and fish length from a single-view 2D segmentation mask. We firstintroduce a relative 3D fish template. By minimizing an objective function, ourmethod systematically estimates the relative 3D pose of the target fish andfish 2D keypoints in the image. Finally, with a closed-form solution, therelative 3D fish pose can help locate absolute 3D keypoints, resulting in theframe-based absolute fish length measurement, which is further refined based onthe statistical temporal inference for the optimal fish length measurement fromthe video clip. Our experiments show that this method can accurately estimatethe absolute 3D fish pose and further measure the absolute length, evenoutperforming the state-of-the-art multi-view method.

Absolute 3D Pose Estimation and Length Measurement of Severely Deformed Fish from Monocular Videos in Longline Fishing