Physeter catodon localization by sparse coding
This work addresses sperm whale tracking for applications like anti-collision systems and whale watching, representing an incremental improvement by combining existing methods in a new domain.
This paper tackles sperm whale localization by using a bag-of-features approach with machine learning to regress distance and azimuth estimates from acoustic data, which are then refined with a particle filter for precise positioning even with a single hydrophone.
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.