Efficient and accurate feature-aided active tracking for underwater small targets in highly cluttered harbor environments using a full motion acoustic flow field solution

• DOI: 10.1121/10.0035564
• Publication Date: 2025-02-03T13:13:07Z
• Authors: Zhuoqun Wei; Yina Han; Qingyu Liu; Shuang Zhao; Jun Song
• Keywords: Tracking (education); Feature (linguistics); Match moving

To address the issue of tracking highly maneuverable small underwater intruders in dynamic and heavily interfered environment harbors, a local sparse motion acoustic flow (LSMAF) computation method constrained by robust high-order flux tensor (RHO-FT) feature has been proposed, along with LSMAF feature-aided active method. First, potential targets are localized from dense clutter background sonar echographs using RHO-FT maps. Subsequently, on basis calculation method, consistency criterion is introduced to target area, establishing for calculating LSMAF, which updates precise vectors real time. Finally, all measurements obtained map iteratively filtered together their corresponding maintain kinematic target's trajectory. Experiments conducted series cooperative real-world harbor environments show that LSMAF-aided outperforms latest developments terms both efficiency trajectory accuracy.