Physeter catodon localization by sparse coding

TL;DR

This paper introduces a novel sperm whale localization system combining bag-of-features and machine learning to estimate position accurately from acoustic data, useful for anti-collision and whale watching.

Contribution

It proposes a new approach integrating BoF and supervised regression for whale localization, enabling precise positioning with minimal sensors.

Findings

Effective localization in mono-hydrophone setup

Accurate distance and azimuth estimation

Potential applications in anti-collision systems

Abstract

This paper presents a spermwhale' localization architecture using jointly a bag-of-features (BoF) approach and machine learning framework. BoF methods are known, especially in computer vision, to produce from a collection of local features a global representation invariant to principal signal transformations. Our idea is to regress supervisely from these local features two rough estimates of the distance and azimuth thanks to some datasets where both acoustic events and ground-truth position are now available. Furthermore, these estimates can feed a particle filter system in order to obtain a precise spermwhale' position even in mono-hydrophone configuration. Anti-collision system and whale watching are considered applications of this work.