{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T18:05:20Z","timestamp":1790100320718,"version":"4.0.1"},"reference-count":23,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T00:00:00Z","timestamp":1790035200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006407","name":"Natural Science Foundation of Henan Province","doi-asserted-by":"publisher","award":["252300423440"],"award-info":[{"award-number":["252300423440"]}],"id":[{"id":"10.13039\/501100006407","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Automated bridge crack detection is challenging because cracks often exhibit weak contrast, irregular morphology, slender structures, and strong interference from complex surface textures. To address these issues, this study proposes a YOLOv8-CA-EYHL framework that combines filtering-equalization preprocessing with coordinate attention (CA) and enhanced high- and low-frequency feature learning modules. The filtering-equalization strategy improves crack-background contrast while suppressing background interference. CA enhances spatially directional feature representation, while the YHL module strengthens local and high-frequency crack features. The EYHL module further establishes multi-scale feature interaction and spatial recalibration to improve the representation of irregular and slender cracks. Ablation experiments demonstrate that the performance improvement results from the complementary contributions of preprocessing and the proposed architectural components. The proposed model achieves an mAP50 of 93.1% and an mAP50-95 of 63.5%, compared with 64.4% and 42.8%, respectively, for YOLOv8s. It requires 32.6 B FLOPs and 13.7 M parameters while maintaining an inference speed of approximately 76 FPS. Repeated experiments with different random seeds and evaluation on an independent external dataset provide further evidence of the stability and generalisation potential of the proposed framework.<\/jats:p>","DOI":"10.1371\/journal.pone.0358872","type":"journal-article","created":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T17:26:20Z","timestamp":1790097980000},"page":"e0358872","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Yolov8-CA-EYHL: A bridge crack detection algorithm based on improved YOLOv8"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-6895-7376","authenticated-orcid":true,"given":"Xianwei","family":"Zhu","sequence":"first","affiliation":[{"name":"School of Mechanical and Electrical Engineering, Zhengzhou University of Industrial Technology","place":["Zhengzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"He","family":"Chao","sequence":"additional","affiliation":[{"name":"School of Intelligent Manufacturing and Electrical Engineering, Nanyang Normal University","place":["Henan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yahui","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Intelligent Manufacturing, Nanyang Institute of Technology","place":["Henan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,9,22]]},"reference":[{"issue":"3","key":"pone.0358872.ref001","doi-asserted-by":"crossref","DOI":"10.2316\/Journal.206.2015.3.206-4247","article-title":"A multi-agent architecture with hierarchical fuzzy controller for a mobile robot","volume":"30","author":"M Boujelben","year":"2015","journal-title":"Int J Robotics and Automation"},{"issue":"1","key":"pone.0358872.ref002","doi-asserted-by":"crossref","DOI":"10.2316\/J.2019.206-4986","article-title":"Position\u2013posture trajectory tracking of a six-legged walking robot","volume":"34","author":"G Chen","year":"2019","journal-title":"Int J Robotics and Automation"},{"key":"pone.0358872.ref003","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1504\/IJMA.2015.075960","article-title":"Levenberg-Marquardt optimised neural networks for trajectory tracking of autonomous ground vehicles","volume":"5","author":"AA Mayyahi","year":"2015","journal-title":"IJMA"},{"issue":"1","key":"pone.0358872.ref004","doi-asserted-by":"crossref","DOI":"10.2316\/J.2026.206-1201","article-title":"Research on cooperative control method of multi-agent formation for engineering vehicles. 54-63","volume":"41","author":"L Wang","year":"2026","journal-title":"Int J Robotics and Automation"},{"issue":"1","key":"pone.0358872.ref005","doi-asserted-by":"crossref","first-page":"15704","DOI":"10.1038\/s41598-025-00468-7","article-title":"Lightweight concrete crack recognition model based on improved MobileNetV3","volume":"15","author":"R Wang","year":"2025","journal-title":"Sci Rep"},{"issue":"12","key":"pone.0358872.ref006","doi-asserted-by":"crossref","first-page":"5209","DOI":"10.1111\/ffe.70091","article-title":"Crack evolution and damage mechanisms of double\u2010flawed sandstone monitored under DIC and AE: the influence of rock bridge angle","volume":"48","author":"X Xie","year":"2025","journal-title":"Fatigue Fract Eng Mat Struct"},{"issue":"1","key":"pone.0358872.ref007","doi-asserted-by":"crossref","first-page":"10698","DOI":"10.1038\/s41598-025-94992-1","article-title":"Evolution of strain field and crack prediction in cemented paste backfill specimens based on digital image correlation and computer vision recognition model","volume":"15","author":"H Zhang","year":"2025","journal-title":"Sci Rep"},{"issue":"18","key":"pone.0358872.ref008","doi-asserted-by":"crossref","first-page":"3266","DOI":"10.3390\/buildings15183266","article-title":"Research on optimization of intelligent recognition model for bridge cracks based on dual-parameter error evaluation indexes","volume":"15","author":"K Peng","year":"2025","journal-title":"Buildings"},{"issue":"3","key":"pone.0358872.ref009","doi-asserted-by":"crossref","DOI":"10.2316\/J.2023.206-0831","article-title":"Lightweight mesh crack detection algorithm based on efficient attention mechanism, 170-179","volume":"38","author":"D Hang","year":"2023","journal-title":"Int J Robotics and Automation"},{"issue":"5","key":"pone.0358872.ref010","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0324512","article-title":"Enhanced YOLOv8-based pavement crack detection: A high-precision approach","volume":"20","author":"Z Zhang","year":"2025","journal-title":"PLoS One"},{"issue":"2","key":"pone.0358872.ref011","first-page":"379","article-title":"Root zone fertilization robot based on YOLOv5 stalk identification","volume":"61","author":"X Li","year":"2024","journal-title":"Pakistan J Agricultural Sci"},{"issue":"4","key":"pone.0358872.ref012","doi-asserted-by":"crossref","first-page":"042033","DOI":"10.1088\/1757-899X\/782\/4\/042033","article-title":"Road crack detection using deep neural network with receptive field block","volume":"782","author":"J Yang","year":"2020","journal-title":"IOP Conf Ser: Mater Sci Eng"},{"key":"pone.0358872.ref013","doi-asserted-by":"crossref","first-page":"104436","DOI":"10.1016\/j.autcon.2022.104436","article-title":"Multi-scale feature fusion network for pixel-level pavement distress detection","volume":"141","author":"J Zhong","year":"2022","journal-title":"Automation in Construction"},{"key":"pone.0358872.ref014","doi-asserted-by":"crossref","first-page":"135025","DOI":"10.1016\/j.conbuildmat.2024.135025","article-title":"A novel YOLOv8-GAM-Wise-IoU model for automated detection of bridge surface cracks","volume":"414","author":"C Xiong","year":"2024","journal-title":"Construction and Building Materials"},{"issue":"3","key":"pone.0358872.ref015","doi-asserted-by":"crossref","first-page":"359","DOI":"10.3390\/coatings16030359","article-title":"Intelligent detection of asphalt pavement cracks based on improved YOLOv8s","volume":"16","author":"J Su","year":"2026","journal-title":"Coatings"},{"key":"pone.0358872.ref016","doi-asserted-by":"crossref","first-page":"112831","DOI":"10.1016\/j.asoc.2025.112831","article-title":"Bridge crack detection algorithm designed based on YOLOv8","volume":"171","author":"H Xia","year":"2025","journal-title":"Appl Soft Comput"},{"issue":"1","key":"pone.0358872.ref017","doi-asserted-by":"crossref","first-page":"13074","DOI":"10.1038\/s41598-025-97842-2","article-title":"Improved YOLOv8n-based bridge crack detection algorithm under complex background conditions","volume":"15","author":"W Xu","year":"2025","journal-title":"Sci Rep"},{"issue":"13","key":"pone.0358872.ref018","doi-asserted-by":"crossref","first-page":"5497","DOI":"10.3390\/app14135497","article-title":"Superficial defect detection for concrete bridges using YOLOv8 with attention mechanism and deformation convolution","volume":"14","author":"T Li","year":"2024","journal-title":"Appl Sci"},{"issue":"4","key":"pone.0358872.ref019","doi-asserted-by":"crossref","first-page":"1313","DOI":"10.3390\/s26041313","article-title":"FEGW-YOLO: a feature-complexity-guided lightweight framework for real-time multi-crop detection with advanced sensing integration on edge devices","volume":"26","author":"Y Liu","year":"2026","journal-title":"Sensors (Basel)"},{"key":"pone.0358872.ref020","doi-asserted-by":"crossref","first-page":"129554","DOI":"10.1016\/j.eswa.2025.129554","article-title":"A novel object detection system for computer night vision images using residual 3D transformer-based YoloV8 with adaptive GRU in edge and cloud sector","volume":"298","author":"VC Prabu","year":"2026","journal-title":"Expert Systems with Applications"},{"issue":"7","key":"pone.0358872.ref021","doi-asserted-by":"crossref","first-page":"2016","DOI":"10.3390\/s26072016","article-title":"AL-YOLOv8: a small object detection algorithm for remote sensing images based on an improved YOLOv8s","volume":"26","author":"F Zhang","year":"2026","journal-title":"Sensors (Basel)"},{"issue":"16","key":"pone.0358872.ref022","doi-asserted-by":"crossref","first-page":"7190","DOI":"10.3390\/s23167190","article-title":"UAV-YOLOv8: A small-object-detection model based on improved YOLOv8 for UAV aerial photography scenarios","volume":"23","author":"G Wang","year":"2023","journal-title":"Sensors (Basel)"},{"key":"pone.0358872.ref023","doi-asserted-by":"crossref","first-page":"1734","DOI":"10.1109\/JSTARS.2023.3339235","article-title":"Small Object Detection Algorithm Based on Improved YOLOv8 for Remote Sensing","volume":"17","author":"H Yi","year":"2024","journal-title":"IEEE J Sel Top Appl Earth Observations Remote Sensing"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0358872","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T17:26:28Z","timestamp":1790097988000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0358872"}},"subtitle":[],"editor":[{"given":"Muhammad Amjad","family":"Ali","sequence":"first","affiliation":[{"name":"University of Agriculture Faisalabad","place":["PAKISTAN"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,9,22]]},"references-count":23,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9,22]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0358872","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,22]]}}}