{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T01:48:58Z","timestamp":1769046538260,"version":"3.49.0"},"reference-count":36,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T00:00:00Z","timestamp":1756080000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Journal of Field Robotics"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Complex physicochemical environmental effects result in highly intricate and diverse backgrounds in underwater object images, posing significant challenges for detecting structural defects. Besides, current methods overlook the tradeoff between the detection accuracy and computational cost. To effectively address the aforementioned issues, we present a lightweight multiscale feature fusion network (LMFFNet) for underwater structural defect detection. Aiming to enhance the feature representability, spatial attention, and bidirectional pyramid modules are jointly employed for fusing multiscale features. A parameter\u2010sharing header module is designed to reduce the model parameters. The dynamic nonmonotonic focusing mechanism is introduced in the loss function, which can improve the defect detection performance on degraded underwater images. Comprehensive experiments on a real\u2010world underwater data set demonstrate the superiority of the LMFFNet over existing state\u2010of\u2010the\u2010art methods.<\/jats:p>","DOI":"10.1002\/rob.70041","type":"journal-article","created":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T10:17:28Z","timestamp":1756117048000},"page":"376-386","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["LMFFNet: Lightweight Multiscale Feature Fusion Network for Underwater Structural Defect Detection"],"prefix":"10.1002","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2772-1575","authenticated-orcid":false,"given":"Chunyan","family":"Ma","sequence":"first","affiliation":[{"name":"The College of Artificial Intelligence and Automation Hohai University Changzhou China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huibin","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer and Software Engineering Hohai University Nanjing China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Zhang","sequence":"additional","affiliation":[{"name":"Dam Safety Management Department Nanjing Hydraulic Research Institute Nanjing China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangze","family":"Shen","sequence":"additional","affiliation":[{"name":"Dam Safety Management Department Nanjing Hydraulic Research Institute Nanjing China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhe","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering Hohai University Changzhou China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2025,8,25]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engstruct.2022.115291"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2020.103371"},{"key":"e_1_2_8_4_1","first-page":"52","article-title":"Research on Crack Detection Method of Dam Surface Based on Full Convolutional Neural Network","volume":"39","author":"Chen B.","year":"2020","journal-title":"Journal of Hydroelectric Power"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2875889"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00066"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01352"},{"key":"e_1_2_8_8_1","volume-title":"YOLO by Ultralytics","author":"Jocher G.","year":"2023"},{"key":"e_1_2_8_9_1","volume-title":"Ultralytics\/Yolov5: v7.0\u2014YOLOv5 SOTA Real\u2010Time Instance Segmentation","author":"Jocher G.","year":"2022"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.7848\/ksgpc.2018.36.6.629"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1155\/2017\/8231314"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.3390\/APP11062750"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2016.08.008"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.3390\/app10124230"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2018.01.001"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11036-017-0863-4"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.1111\/mice.12561"},{"key":"e_1_2_8_18_1","doi-asserted-by":"publisher","DOI":"10.3390\/buildings12020156"},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"e_1_2_8_20_1","volume-title":"Bridge Inspection Practices: A Synthesis of Highway Practice","author":"Rens K. L.","year":"2005"},{"key":"e_1_2_8_21_1","first-page":"88","article-title":"Deep Learning\u2010Based Reinforced Concrete Bridge Lost Block Exposed Rib Disease Identification","volume":"48","author":"Ruan X. L.","year":"2020","journal-title":"World Bridge"},{"key":"e_1_2_8_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"e_1_2_8_23_1","first-page":"343","volume-title":"Chinese Conference on Pattern Recognition and Computer Vision (PRCV)","author":"Tang F. L.","year":"2023"},{"key":"e_1_2_8_24_1","volume-title":"Wise\u2010IoU: Bounding Box Regression Loss With Dynamic Focusing Mechanism","author":"Tong Z. J.","year":"2023"},{"key":"e_1_2_8_25_1","first-page":"4","volume-title":"LabelImg","author":"Tzutalin D.","year":"2015"},{"key":"e_1_2_8_26_1","first-page":"7464","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Wang C. Y.","year":"2023"},{"key":"e_1_2_8_27_1","first-page":"1","volume-title":"European Conference on Computer Vision","author":"Wang C. Y.","year":"2024"},{"key":"e_1_2_8_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2019.06.096"},{"key":"e_1_2_8_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2024.115922"},{"key":"e_1_2_8_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2020.107756"},{"key":"e_1_2_8_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2024.102553"},{"key":"e_1_2_8_32_1","first-page":"75","article-title":"Research on Bridge Crack Identification Method Based on Deep Learning","volume":"1","author":"Ying J. J.","year":"2021","journal-title":"Water Resources Planning and Design"},{"key":"e_1_2_8_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124932"},{"key":"e_1_2_8_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3299314"},{"key":"e_1_2_8_35_1","volume-title":"Objects as Points","author":"Zhou X.","year":"2019"},{"key":"e_1_2_8_36_1","doi-asserted-by":"publisher","DOI":"10.1111\/mice.12836"},{"key":"e_1_2_8_37_1","doi-asserted-by":"publisher","DOI":"10.1080\/15732479.2019.1680709"}],"container-title":["Journal of Field Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/rob.70041","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T09:12:21Z","timestamp":1766049141000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/rob.70041"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,25]]},"references-count":36,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1002\/rob.70041"],"URL":"https:\/\/doi.org\/10.1002\/rob.70041","archive":["Portico"],"relation":{},"ISSN":["1556-4959","1556-4967"],"issn-type":[{"value":"1556-4959","type":"print"},{"value":"1556-4967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,25]]},"assertion":[{"value":"2024-10-21","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-15","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}