{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T00:02:14Z","timestamp":1773014534084,"version":"3.50.1"},"reference-count":47,"publisher":"Institution of Engineering and Technology (IET)","issue":"1","license":[{"start":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T00:00:00Z","timestamp":1771804800000},"content-version":"vor","delay-in-days":53,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62571179"],"award-info":[{"award-number":["62571179"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U2441254"],"award-info":[{"award-number":["U2441254"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["IET Image Processing"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>To address the problems of high computational complexity and limited deploy ability in underwater sonar image detection, we propose SSGA\u2010YOLO, a lightweight and efficient object detection algorithm optimised for sonar imagery and successfully deployed on the Ascend AI embedded platform. SSGA\u2010YOLO focuses on three key aspects to achieve a favourable balance between accuracy and efficiency. The S\u2010Net backbone employs depthwise separable convolutions and a lightweight attention mechanism to enhance the extraction of weak echo and shadow features in sonar images while reducing redundancy for efficient deployment. The Efficient Group Shuffle Convolution (EGSConv) enhances cross\u2010channel feature interaction to improve the detection of small, low\u2010contrast sonar targets and the Lightweight Shuffle\u2010Aware Group Attention (LSGA) refines key acoustic and spatial cues in the presence of strong noise. Furthermore, SSGA\u2010YOLO significantly reduces model parameters and computational complexity: compared to YOLOv8n, it achieves reductions of 79.82% and 74.07% in parameter count and GFLOPs, respectively. To evaluate model performance across diverse environments, embedded deployment experiments were conducted on three datasets representing distinct scenarios: MDFD for controlled artificial tanks, UATD for complex natural waters and MOTfish for dynamic video sequences. SSGA\u2010YOLO consistently achieves high detection accuracy, with an mAP50 exceeding 0.930 on all datasets and peaking at 0.983 on MDFD. In terms of inference efficiency, the model demonstrates exceptional real\u2010time capability, reaching a frame rate of 65.77 FPS on MOTfish. These results outperform other lightweight detectors, confirming the model's effectiveness for practical underwater applications.<\/jats:p>","DOI":"10.1049\/ipr2.70313","type":"journal-article","created":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T22:51:00Z","timestamp":1773010260000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SSGA\u2010YOLO: A Lightweight Sonar Image Object Detection Network With Efficient Convolution and Acoustic\u2010Aware Attention for Embedded Systems"],"prefix":"10.1049","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9887-2795","authenticated-orcid":false,"given":"Yan","family":"Liu","sequence":"first","affiliation":[{"name":"College of Information Science and Engineering Hohai University  Changzhou China"}]},{"given":"Gan","family":"Yan","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering Hohai University  Changzhou China"}]},{"given":"Tong","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering Hohai University  Changzhou China"}]},{"given":"Guanying","family":"Huo","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering Hohai University  Changzhou China"}]}],"member":"265","published-online":{"date-parts":[[2026,2,23]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2930148"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3112010"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.1049\/ipr2.12707"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3224815"},{"key":"e_1_2_10_6_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2023.3256373","article-title":"Building a Bridge of Bounding Box Regression Between Oriented and Horizontal Object Detection in Remote Sensing Images","volume":"61","author":"Qian X.","year":"2023","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"e_1_2_10_7_1","article-title":"Self\u2010Trained Target Detection of Radar and Sonar Images Using Automatic Deep Learning","volume":"60","author":"Zhang P.","year":"2022","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"e_1_2_10_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2021.3131645"},{"key":"e_1_2_10_9_1","article-title":"IPS\u2010YOLO: Iterative Pseudo\u2010Fully Supervised Training of YOLO for Weakly Supervised Object Detection in Remote Sensing Images","volume":"62","author":"Qian X.","year":"2025","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"e_1_2_10_11_1","doi-asserted-by":"crossref","unstructured":"W.Liu D.Anguelov andD.Erhan \u201cSSD: Single Shot Multibox Detector \u201d inThe European Conference on Computer Vision ECCV (Springer 2016) 21\u201337.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"e_1_2_10_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_2_10_13_1","unstructured":"A.Vaswani N.Shazeer andN.Parmar \u201cAttention is All You Need \u201d inConference and Workshop on Neural Information Processing Systems (Curran Associates Inc.2017) 5998\u20136008."},{"key":"e_1_2_10_14_1","doi-asserted-by":"crossref","unstructured":"N.Carion F.Massa G.Synnaeve N.Usunier A.Kirillov andS.Zagoruyko \u201cEnd\u2010to\u2010End Object Detection With Transformers \u201d inThe European Conference on Computer Vision (Springer 2020) 213\u2013229.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_2_10_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3150339"},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.3390\/jmse11112155"},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.apor.2023.103630"},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.3390\/rs13183555"},{"key":"e_1_2_10_19_1","doi-asserted-by":"publisher","DOI":"10.1117\/1.JEI.34.2.023019"},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3156907"},{"key":"e_1_2_10_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2019.112870"},{"key":"e_1_2_10_22_1","article-title":"Lightweight YOLOv5 Sonar Image Object Detection Algorithm and Implementation Based on ZYNQ","volume":"51","author":"Zhao D. D.","year":"2024","journal-title":"Opto\u2010Electronic Engineering"},{"key":"e_1_2_10_23_1","doi-asserted-by":"crossref","unstructured":"N.Ma X.Zhang H.Zheng andJ.Sun \u201cShufflenet v2: Practical Guidelines for Efficient CNN Architecture Design \u201d inThe European Conference on Computer Vision (Springer 2018) 116\u2013131.","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"e_1_2_10_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"e_1_2_10_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00165"},{"key":"e_1_2_10_26_1","doi-asserted-by":"crossref","unstructured":"D.Qin A.Leonardis andE.Ricci \u201cMobileNetV4: Universal Models for the Mobile Ecosystem \u201d inThe European Conference on Computer Vision (Springer 2024) 15098.","DOI":"10.1007\/978-3-031-73661-2_5"},{"key":"e_1_2_10_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.isci.2024.111618"},{"key":"e_1_2_10_28_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0334216"},{"key":"e_1_2_10_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11554-024-01436-6"},{"key":"e_1_2_10_30_1","doi-asserted-by":"crossref","unstructured":"Y.Chen H.Fan andB.Xu \u201cDrop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks With Octave Convolution \u201d inIEEE\/CVF International Conference on Computer Vision (IEEE 2019) 3435\u20133444.","DOI":"10.1109\/ICCV.2019.00353"},{"key":"e_1_2_10_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00596"},{"key":"e_1_2_10_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3175432"},{"key":"e_1_2_10_33_1","doi-asserted-by":"crossref","unstructured":"J.Dai H.Qi andY.Xiong \u201cDeformable Convolutional Networks \u201d inIEEE\/CVF International Conference on Computer Vision (IEEE 2017) 764\u2013773.","DOI":"10.1109\/ICCV.2017.89"},{"key":"e_1_2_10_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"e_1_2_10_35_1","doi-asserted-by":"crossref","unstructured":"S.Woo J.Park J.Lee andI. S.Kweon \u201cCBAM: Convolutional Block Attention Module \u201d inThe European Conference on Computer Vision (Springer 2018) 3\u201319.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"e_1_2_10_36_1","doi-asserted-by":"crossref","unstructured":"Q.ZhangandY.Yang \u201cSA\u2010Net: Shuffle Attention for Deep Convolutional Neural Networks \u201d inIEEE International Conference on Acoustics Speech and Signal Processing (IEEE 2021) 2235\u20132239.","DOI":"10.1109\/ICASSP39728.2021.9414568"},{"issue":"24","key":"e_1_2_10_37_1","first-page":"07","article-title":"DNP\u2010PTQ: A Model Quantization Method for YOLO Embedded Deployment","volume":"62","author":"Pan N. P.","year":"2025","journal-title":"Laser & Optoelectronics Progress"},{"key":"e_1_2_10_38_1","unstructured":"M.Lei S.Li Y.Wu et\u00a0al. \u201cYOLOv13: Real\u2010Time Object Detection With Hypergraph\u2010Enhanced Adaptive Visual Perception \u201d preprint arXiv September 5 2025 https:\/\/doi.org\/10.48550\/arXiv.2506.17733."},{"key":"e_1_2_10_39_1","doi-asserted-by":"publisher","DOI":"10.1049\/iet-ipr.2018.5675"},{"key":"e_1_2_10_40_1","doi-asserted-by":"publisher","DOI":"10.1049\/ipr2.13241"},{"key":"e_1_2_10_41_1","article-title":"Automatic Detection of Underwater Small Targets Using Forward\u2010Looking Sonar Images","volume":"60","author":"Zhou T.","year":"2022","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"e_1_2_10_42_1","doi-asserted-by":"crossref","unstructured":"D.SinghandM.Valdenegro\u2010Toro \u201cThe Marine Debris Dataset for Forward\u2010Looking Sonar Semantic Segmentation \u201d inIEEE\/CVF International Conference on Computer Vision (IEEE 2021) 3741\u20133749.","DOI":"10.1109\/ICCVW54120.2021.00417"},{"key":"e_1_2_10_43_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01854-w"},{"key":"e_1_2_10_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01157"},{"key":"e_1_2_10_45_1","first-page":"11534","volume-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Wang Q.","year":"2020"},{"key":"e_1_2_10_46_1","doi-asserted-by":"crossref","unstructured":"X.Qin N.Li C.Weng D.Su andM.Li \u201cSimple Attention Module Based Speaker Verification With Iterative Noisy Label Detection \u201d inIEEE International Conference on Acoustics Speech and Signal Processing (IEEE 2022) 6722\u20136726.","DOI":"10.1109\/ICASSP43922.2022.9746294"},{"key":"e_1_2_10_47_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2019.11.023"},{"key":"e_1_2_10_48_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2025.3580937","article-title":"Incorporating Multiscale Context and Task\u2010Consistent Focal Loss into Oriented Object Detection","volume":"63","author":"Qian X.","year":"2025","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"}],"container-title":["IET Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/ipr2.70313","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/full-xml\/10.1049\/ipr2.70313","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/ipr2.70313","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T22:51:06Z","timestamp":1773010266000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/ipr2.70313"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":47,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1049\/ipr2.70313"],"URL":"https:\/\/doi.org\/10.1049\/ipr2.70313","archive":["Portico"],"relation":{},"ISSN":["1751-9659","1751-9667"],"issn-type":[{"value":"1751-9659","type":"print"},{"value":"1751-9667","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"2025-09-28","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-12","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70313"}}