基于深度学习的有刺鱼类检测和分类框架。

IF 2.3 2区 物理与天体物理 Q2 ACOUSTICS
Ziqi Huang, Dominik Ochs, M Clara P Amorim, Paulo J Fonseca, Mayank Goel, Nuno Jardim Nunes, Manuel Vieira, Manuel Lopes
{"title":"基于深度学习的有刺鱼类检测和分类框架。","authors":"Ziqi Huang, Dominik Ochs, M Clara P Amorim, Paulo J Fonseca, Mayank Goel, Nuno Jardim Nunes, Manuel Vieira, Manuel Lopes","doi":"10.1121/10.0038800","DOIUrl":null,"url":null,"abstract":"<p><p>Passive acoustic monitoring (PAM) is emerging as a valuable tool for assessing fish populations in natural habitats. This study compares two deep learning-based frameworks: (1) a multi-label segmentation-based classification system (SegClas) combining convolutional neural networks and long short term memory networks and, (2) an object detection approach (ObjDet) using a You Only Look Once based model to detect, classify, and count sounds produced by soniferous fish in the Tagus Estuary, Portugal. The target species-Lusitanian toadfish (Halobatrachus didactylus), meagre (Argyrosomus regius), and weakfish (Cynoscion regalis)-exhibit overlapping vocalization patterns, posing classification challenges. Results show both methods achieve high accuracy (over 96%) and F1 scores above 87% for species-level sound identification, demonstrating their effectiveness under varied noise conditions. ObjDet generally offers slightly higher classification performance (F1 up to 92%) and can annotate each vocalization for more precise counting. However, it requires bounding-box annotations and higher computational costs (inference time of ca. 1.95 s/h of recording). In contrast, SegClas relies on segment-level labels and provides faster inference (ca. 1.46 s/h). This study also compares both counting strategies, each offering distinct advantages for different ecological and operational needs. Our results highlight the potential of deep learning-based PAM for fish population assessment.</p>","PeriodicalId":17168,"journal":{"name":"Journal of the Acoustical Society of America","volume":"158 2","pages":"1060-1071"},"PeriodicalIF":2.3000,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Deep learning-based frameworks for the detection and classification of soniferous fish.\",\"authors\":\"Ziqi Huang, Dominik Ochs, M Clara P Amorim, Paulo J Fonseca, Mayank Goel, Nuno Jardim Nunes, Manuel Vieira, Manuel Lopes\",\"doi\":\"10.1121/10.0038800\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Passive acoustic monitoring (PAM) is emerging as a valuable tool for assessing fish populations in natural habitats. This study compares two deep learning-based frameworks: (1) a multi-label segmentation-based classification system (SegClas) combining convolutional neural networks and long short term memory networks and, (2) an object detection approach (ObjDet) using a You Only Look Once based model to detect, classify, and count sounds produced by soniferous fish in the Tagus Estuary, Portugal. The target species-Lusitanian toadfish (Halobatrachus didactylus), meagre (Argyrosomus regius), and weakfish (Cynoscion regalis)-exhibit overlapping vocalization patterns, posing classification challenges. Results show both methods achieve high accuracy (over 96%) and F1 scores above 87% for species-level sound identification, demonstrating their effectiveness under varied noise conditions. ObjDet generally offers slightly higher classification performance (F1 up to 92%) and can annotate each vocalization for more precise counting. However, it requires bounding-box annotations and higher computational costs (inference time of ca. 1.95 s/h of recording). In contrast, SegClas relies on segment-level labels and provides faster inference (ca. 1.46 s/h). This study also compares both counting strategies, each offering distinct advantages for different ecological and operational needs. Our results highlight the potential of deep learning-based PAM for fish population assessment.</p>\",\"PeriodicalId\":17168,\"journal\":{\"name\":\"Journal of the Acoustical Society of America\",\"volume\":\"158 2\",\"pages\":\"1060-1071\"},\"PeriodicalIF\":2.3000,\"publicationDate\":\"2025-08-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of the Acoustical Society of America\",\"FirstCategoryId\":\"101\",\"ListUrlMain\":\"https://doi.org/10.1121/10.0038800\",\"RegionNum\":2,\"RegionCategory\":\"物理与天体物理\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ACOUSTICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of the Acoustical Society of America","FirstCategoryId":"101","ListUrlMain":"https://doi.org/10.1121/10.0038800","RegionNum":2,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ACOUSTICS","Score":null,"Total":0}
引用次数: 0

摘要

被动声监测(PAM)正在成为评估自然栖息地鱼类种群的一种有价值的工具。本研究比较了两种基于深度学习的框架:(1)结合卷积神经网络和长短期记忆网络的基于多标签分割的分类系统(SegClas);(2)使用You Only Look Once模型的对象检测方法(ObjDet),用于检测、分类和计数葡萄牙塔霍斯河口(Tagus Estuary)有音鱼类产生的声音。目标物种-卢西塔尼亚蟾蜍鱼(Halobatrachus didactylus),贫鱼(Argyrosomus regius)和弱鱼(Cynoscion regalis)-表现出重叠的发声模式,提出了分类挑战。结果表明,两种方法对物种级声音识别的准确率均在96%以上,F1分数均在87%以上,证明了两种方法在不同噪声条件下的有效性。ObjDet通常提供稍高的分类性能(F1高达92%),并且可以注释每个发声以进行更精确的计数。然而,它需要边界盒注释和更高的计算成本(大约1.95秒/小时的记录推理时间)。相比之下,segclass依赖于段级标签,并提供更快的推理(约1.46秒/小时)。本研究还比较了两种计数策略,每种策略都为不同的生态和运营需求提供了独特的优势。我们的研究结果突出了基于深度学习的PAM在鱼类种群评估中的潜力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Deep learning-based frameworks for the detection and classification of soniferous fish.

Passive acoustic monitoring (PAM) is emerging as a valuable tool for assessing fish populations in natural habitats. This study compares two deep learning-based frameworks: (1) a multi-label segmentation-based classification system (SegClas) combining convolutional neural networks and long short term memory networks and, (2) an object detection approach (ObjDet) using a You Only Look Once based model to detect, classify, and count sounds produced by soniferous fish in the Tagus Estuary, Portugal. The target species-Lusitanian toadfish (Halobatrachus didactylus), meagre (Argyrosomus regius), and weakfish (Cynoscion regalis)-exhibit overlapping vocalization patterns, posing classification challenges. Results show both methods achieve high accuracy (over 96%) and F1 scores above 87% for species-level sound identification, demonstrating their effectiveness under varied noise conditions. ObjDet generally offers slightly higher classification performance (F1 up to 92%) and can annotate each vocalization for more precise counting. However, it requires bounding-box annotations and higher computational costs (inference time of ca. 1.95 s/h of recording). In contrast, SegClas relies on segment-level labels and provides faster inference (ca. 1.46 s/h). This study also compares both counting strategies, each offering distinct advantages for different ecological and operational needs. Our results highlight the potential of deep learning-based PAM for fish population assessment.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
4.60
自引率
16.70%
发文量
1433
审稿时长
4.7 months
期刊介绍: Since 1929 The Journal of the Acoustical Society of America has been the leading source of theoretical and experimental research results in the broad interdisciplinary study of sound. Subject coverage includes: linear and nonlinear acoustics; aeroacoustics, underwater sound and acoustical oceanography; ultrasonics and quantum acoustics; architectural and structural acoustics and vibration; speech, music and noise; psychology and physiology of hearing; engineering acoustics, transduction; bioacoustics, animal bioacoustics.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信