AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
PDF (1.1 MB)
Collect
Submit Manuscript AI Chat Paper
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Research Article | Open Access | Just Accepted

AUV target perception in forward-looking sonar images: A low-pixel dataset and multi-frame segmentation network

Jingfeng Yu1,2( ), Chen Liang3, Kailai Sun4,5( ), Jiugen Lin1, Zhongju Sun1, Ruiming Wang3, Qianchuan Zhao2

1 Ganjiang Innovation Academy, Chinese Academy of Sciences, Ganzhou 341119, China

2 Department of Automation, Tsinghua University, Beijing 100084, China

3 Department of Automation, University of Science and Technology of China, Hefei 230026, China

4 Singapore-MIT Alliance for Research and Technology Centre (SMART), Singapore 138602, Singapore

5 Urban Mobility Lab, Massachusetts Institute of Technology, Cambridge MA 02139, USA

Show Author Information

Abstract

This study investigates low-pixel segmentation of a moving autonomous underwater vehicle (AUV) observed by a fixed forward-looking sonar (FLS) and formulates the task as a pixel-level segmentation problem under low-pixel and noise-interference conditions. We release the Underwater Sonar Moving Target (USMT) dataset, which contains 21 temporally ordered sequences and 7,136 annotated FLS frames collected using a fixed FLS while observing a single AUV in a controlled lake environment. To exploit motion cues across consecutive frames, we propose LSNet, a multi-frame segmentation network adapted to the characteristics of sonar imagery. LSNet incorporates three improvements: (1) a spatio-temporal scale fusion block that combines multi-scale spatial features with variance-based temporal motion cues; (2) a decoupled 3D spatio-temporal attention module that separates local perception from temporal verification; and (3) a Muon-Adam hybrid optimizer with a joint loss function. Technical validation shows that the rectangular B-scan representation is more suitable for segmentation than the sector-shaped representation. On the USMT dataset, LSNet achieves an IoU of 68.21%, outperforming the retrained LVNet reference by 19.57 percentage points and the strongest additional comparator, LMAFormer, by 5.45 percentage points, while maintaining an inference speed of 91.23 FPS. These results demonstrate the effectiveness of multi-frame modeling for low-pixel AUV target segmentation in external FLS-based monitoring. 

References

【1】
【1】
 
 
Journal of Intelligent and Connected Vehicles

{{item.num}}

Comments on this article

Go to comment

< Back to all reports

Review Status: {{reviewData.commendedNum}} Commended , {{reviewData.revisionRequiredNum}} Revision Required , {{reviewData.notCommendedNum}} Not Commended Under Peer Review

Review Comment

Close
Close
Cite this article:
Yu J, Liang C, Sun K, et al. AUV target perception in forward-looking sonar images: A low-pixel dataset and multi-frame segmentation network. Journal of Intelligent and Connected Vehicles, 2026, https://doi.org/10.26599/JICV.2026.9210108

117

Views

12

Downloads

0

Crossref

0

Web of Science

0

Scopus

Received: 10 August 2026
Revised: 01 September 2026
Accepted: 15 October 2026
Available online: 12 November 2026

© The Author(s) 2026.

This is an open access article under the terms of the Creative Commons Attribution 4.0 International License (CC BY 4.0, http://creativecommons.org/licenses/by/4.0/)