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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

With the growth of sensing, control and robotic technologies, autonomousunderwater vehicles (AUVs) have become useful assistants to human divers forperforming various underwater operations. In the current practice, the diversare required to carry expensive, bulky, and waterproof keyboards orjoystick-based controllers for supervision and control of AUVs. Therefore,diver action-based supervision is becoming increasingly popular because it isconvenient, easier to use, faster, and cost effective. However, the variousenvironmental, diver and sensing uncertainties present underwater makes itchallenging to train a robust and reliable diver action recognition system. Inthis regard, this paper presents DARE, a diver action recognition system, thatis trained based on Cognitive Autonomous Driving Buddy (CADDY) dataset, whichis a rich set of data containing images of different diver gestures and posesin several different and realistic underwater environments. DARE is based onfusion of stereo-pairs of camera images using a multi-channel convolutionalneural network supported with a systematically trained tree-topological deepneural network classifier to enhance the classification performance. DARE isfast and requires only a few milliseconds to classify one stereo-pair, thusmaking it suitable for real-time underwater implementation. DARE iscomparatively evaluated against several existing classifier architectures andthe results show that DARE supersedes the performance of all classifiers fordiver action recognition in terms of overall as well as individual classaccuracies and F1-scores.

DARE: AI-based Diver Action Recognition System using Multi-Channel CNNs for AUV Supervision