| Title |
HDBSCAN-based Clutter Removal of An Active Sonar under Multipath Environment |
| Authors |
정명준(Myoung Jun Cheong) ; 조현덕(Hyeon-Deok Cho) ; 김원기(Won-Ki Kim) ; 박도현(Do-Hyun Park) ; 김형남(Hyoung-Nam Kim) |
| DOI |
https://doi.org/10.5573/ieie.2024.61.8.47 |
| Keywords |
Active sonar; Clutter rejection; Clustering; One class classification; Multipath; HDBSCAN |
| Abstract |
In this paper, we propose a novel clutter reduction algorithm, which rejects heavy clutters with multipath detection environments, based on a hierarchical clustering method. The proposed algorithm involves clustering active sonar detection measurements using hierarchical clustering method and employing the target/clutter discrimination algorithm, based on one class classification incorporating underwater target characteristics and active sonar detection environment. On the other hand, measurements which are not in any cluster, are classified by noise and removed. We evaluate the performance of the proposed algorithm on sea-trial data. The results demonstrate that the proposed algorithm provides better performances in reducing clutter than the conventional algorithm. |