{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T09:08:03Z","timestamp":1779959283486,"version":"3.53.1"},"reference-count":47,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T00:00:00Z","timestamp":1779926400000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>The proliferation of clean energy infrastructure has accelerated the global deployment of wind farms, necessitating enhanced mitigation strategies for bird conservation. This study presents a computationally efficient detection algorithm designed to minimize the ecological impact of wind turbines on bird populations. Our primary contributions include three technical innovations: (1) A Dilated Channel Shuffle Squeeze-and-Excitation (DCSSE) attention module that achieves parameter efficiency while preserving detection accuracy; (2) An Adaptive Scale Efficient Intersection over Union (AS-EIoU) loss function optimized for small-target detection; and (3) Integration of PP-LCNet\u2019s lightweight architecture for feature extraction. The proposed FB-YOLO framework demonstrates superior performance compared to the YOLOv8 benchmark across all evaluation metrics. Quantitative analysis reveals significant improvements: precision (+13.57%), recall (+18.86%), mean Average Precision (mAP)50 (+15.48%), and mAP50-95 (+7.89%), accompanied by a model weight reduction of 3.3\u00a0MB. Comparative evaluations with alternative detection models confirm FB-YOLO\u2019s dual advantage in achieving higher accuracy with reduced computational complexity. To support this research, we introduce an annotated bird dataset comprising 6,038 high-resolution images. Experimental results on this dataset demonstrate FB-YOLO\u2019s robust performance (95.6% precision, 94.9% recall, 96.4% mAP50, and 43.4% mAP50-95). The optimized architecture demonstrates significant potential for practical implementation in wind farm monitoring systems, offering an effective technological solution for bird collision prevention through real-time detection capabilities.<\/jats:p>","DOI":"10.7717\/peerj-cs.3901","type":"journal-article","created":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T08:52:47Z","timestamp":1779958367000},"page":"e3901","source":"Crossref","is-referenced-by-count":0,"title":["FB-YOLO (flying bird YOLO): a YOLO-based detector for flying birds in wind farms"],"prefix":"10.7717","volume":"12","author":[{"given":"Jun","family":"Li","sequence":"first","affiliation":[{"name":"School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Wang","sequence":"additional","affiliation":[{"name":"PLA Naval Medical Center, Naval Medical University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingliang","family":"Ge","sequence":"additional","affiliation":[{"name":"School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yixing","family":"Li","sequence":"additional","affiliation":[{"name":"School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mincong","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"4443","published-online":{"date-parts":[[2026,5,28]]},"reference":[{"key":"10.7717\/peerj-cs.3901\/ref-1","doi-asserted-by":"publisher","first-page":"1279","DOI":"10.1109\/ITAIC58329.2023.10408937","article-title":"Design of simulation experimental platform for airport bird control linkage system based on improved YOLOv5","author":"Chen","year":"2023"},{"issue":"10","key":"10.7717\/peerj-cs.3901\/ref-2","doi-asserted-by":"publisher","first-page":"2076","DOI":"10.3390\/ani13101713","article-title":"An efficient method for monitoring birds based on object detection and multi-object tracking networks","volume":"13","author":"Chen","year":"2023","journal-title":"Animals"},{"key":"10.7717\/peerj-cs.3901\/ref-3","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2109.15099","article-title":"PP-LCNet: a lightweight CPU convolutional neural network","author":"Cui","year":"2021"},{"key":"10.7717\/peerj-cs.3901\/ref-4","doi-asserted-by":"publisher","first-page":"1004","DOI":"10.1109\/ICCCS57501.2023.10150849","article-title":"Object detection for rare birds on the plateau","author":"Dong","year":"2023"},{"issue":"2","key":"10.7717\/peerj-cs.3901\/ref-5","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1080\/00063657.2014.894492","article-title":"Collision risk and micro-avoidance rates of birds with wind turbines in Flanders","volume":"61","author":"Everaert","year":"2014","journal-title":"Bird Study"},{"key":"10.7717\/peerj-cs.3901\/ref-6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.23919\/MVA51890.2021.9511386","article-title":"Distant bird detection for safe drone flight and its dataset","author":"Fujii","year":"2021"},{"key":"10.7717\/peerj-cs.3901\/ref-7","first-page":"1440","article-title":"Fast R-CNN","author":"Girshick","year":"2015"},{"key":"10.7717\/peerj-cs.3901\/ref-8","first-page":"580","article-title":"Rich feature hierarchies for accurate object detection and semantic segmentation","author":"Girshick","year":"2013"},{"key":"10.7717\/peerj-cs.3901\/ref-9","doi-asserted-by":"publisher","first-page":"1577","DOI":"10.1109\/CVPR42600.2020.00165","article-title":"GhostNet: more features from cheap operations","author":"Han","year":"2020"},{"issue":"2","key":"10.7717\/peerj-cs.3901\/ref-10","doi-asserted-by":"publisher","first-page":"520","DOI":"10.1109\/TCSVT.2019.2892802","article-title":"Fine-grained visual-textual representation learning","volume":"30","author":"He","year":"2020","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.7717\/peerj-cs.3901\/ref-11","doi-asserted-by":"publisher","first-page":"595","DOI":"10.1109\/CVPR.2015.7298658","article-title":"Building a bird recognition app and large scale dataset with citizen scientists: the fine print in fine-grained dataset collection","author":"Horn","year":"2015"},{"key":"10.7717\/peerj-cs.3901\/ref-12","doi-asserted-by":"publisher","first-page":"1314","DOI":"10.1109\/iccv.2019.00140","article-title":"Searching for MobileNetV3","author":"Howard","year":"2019"},{"key":"10.7717\/peerj-cs.3901\/ref-13","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1704.04861","article-title":"MobileNets: efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017"},{"key":"10.7717\/peerj-cs.3901\/ref-14","doi-asserted-by":"publisher","first-page":"7132","DOI":"10.1109\/CVPR.2018.00745","article-title":"Squeeze-and-excitation networks","author":"Hu","year":"2018"},{"issue":"2","key":"10.7717\/peerj-cs.3901\/ref-15","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1109\/tmi.2019.2928056","article-title":"3D APA-Net: 3D adversarial pyramid anisotropic convolutional network for prostate segmentation in MR images","volume":"39","author":"Jia","year":"2020","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"10.7717\/peerj-cs.3901\/ref-16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.23919\/MVA57639.2023.10215935","article-title":"MVA2023 small object detection challenge for spotting birds: dataset, methods, and results","author":"Kondo","year":"2023"},{"key":"10.7717\/peerj-cs.3901\/ref-17","doi-asserted-by":"publisher","first-page":"84878","DOI":"10.1109\/ACCESS.2024.3415385","article-title":"SMB-YOLOv5: a lightweight airport flying bird detection algorithm based on deep neural networks","volume":"12","author":"Liang","year":"2024","journal-title":"IEEE Access"},{"key":"10.7717\/peerj-cs.3901\/ref-18","doi-asserted-by":"publisher","first-page":"2999","DOI":"10.1109\/ICCV.2017.324","article-title":"Focal loss for dense object detection","author":"Lin","year":"2017"},{"key":"10.7717\/peerj-cs.3901\/ref-19","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","article-title":"SSD: single shot multibox detector","author":"Liu","year":"2016"},{"key":"10.7717\/peerj-cs.3901\/ref-20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2404.11202","article-title":"GhostNetV3: exploring the training strategies for compact models","author":"Liu","year":"2024"},{"key":"10.7717\/peerj-cs.3901\/ref-21","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/2253\/1\/012024","article-title":"Airport UAV and birds detection based on deformable DETR","author":"Liu","year":"2022"},{"key":"10.7717\/peerj-cs.3901\/ref-22","doi-asserted-by":"publisher","first-page":"5694","DOI":"10.1109\/CVPR52733.2024.00544","article-title":"Rewrite the stars","author":"Ma","year":"2024"},{"key":"10.7717\/peerj-cs.3901\/ref-23","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1007\/978-3-030-01264-9_8","article-title":"ShuffleNet V2: practical guidelines for efficient CNN architecture design","author":"Ma","year":"2018"},{"key":"10.7717\/peerj-cs.3901\/ref-24","doi-asserted-by":"publisher","first-page":"667384","DOI":"10.3389\/fevo.2021.667384","article-title":"Flight altitudes of raptors in Southern Africa highlight vulnerability of threatened species to wind turbines","volume":"9","author":"McClure","year":"2021","journal-title":"Frontiers in Ecology and Evolution"},{"key":"10.7717\/peerj-cs.3901\/ref-25","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1007\/978-981-99-6755-1_10","article-title":"Object detection in autonomous maritime vehicles: comparison between YOLO V8 and EfficientDet","author":"Mehla","year":"2023"},{"key":"10.7717\/peerj-cs.3901\/ref-26","doi-asserted-by":"publisher","first-page":"285","DOI":"10.23919\/MIKON48703.2020.9253826","article-title":"Radar-based detection of birds at wind turbine installations: results from a field study","author":"Moll","year":"2020"},{"key":"10.7717\/peerj-cs.3901\/ref-27","doi-asserted-by":"publisher","first-page":"64026","DOI":"10.1109\/ACCESS.2023.3287861","article-title":"Unlocking the potential of wind energy with machine learning-based bird detection: a call to action","volume":"11","author":"Principato","year":"2023","journal-title":"IEEE Access"},{"key":"10.7717\/peerj-cs.3901\/ref-28","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1007\/978-3-031-73661-2_5","article-title":"MobileNetV4\u2014universal models for the mobile ecosystem","author":"Qin","year":"2024"},{"key":"10.7717\/peerj-cs.3901\/ref-29","first-page":"779","article-title":"You only look once: unified, real-time object detection","author":"Redmon","year":"2015"},{"issue":"6","key":"10.7717\/peerj-cs.3901\/ref-30","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: towards real-time object detection with region proposal networks","volume":"39","author":"Ren","year":"2017","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.7717\/peerj-cs.3901\/ref-31","doi-asserted-by":"publisher","first-page":"4510","DOI":"10.1109\/cvpr.2018.00474","article-title":"MobileNetV2: inverted residuals and linear bottlenecks","author":"Sandler","year":"2018"},{"issue":"1","key":"10.7717\/peerj-cs.3901\/ref-32","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1016\/j.renene.2014.12.064","article-title":"Curtailing wind turbine operations to reduce avian mortality","volume":"78","author":"Singh","year":"2015","journal-title":"Renewable Energy"},{"issue":"1","key":"10.7717\/peerj-cs.3901\/ref-33","doi-asserted-by":"publisher","first-page":"2149","DOI":"10.1038\/s41597-025-04872-6","article-title":"FBD-SV-2024: flying bird object detection dataset in surveillance video","volume":"12","author":"Sun","year":"2025","journal-title":"Scientific Data"},{"key":"10.7717\/peerj-cs.3901\/ref-34","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1007\/978-3-031-26348-4_24","article-title":"AirBirds: a large-scale challenging dataset for bird strike prevention in real-world airports","volume":"13845","author":"Sun","year":"2023"},{"key":"10.7717\/peerj-cs.3901\/ref-35","doi-asserted-by":"publisher","first-page":"9969","DOI":"10.52202\/068431-0724","article-title":"GhostNetV2: enhance cheap operation with long-range attention","author":"Tang","year":"2022"},{"key":"10.7717\/peerj-cs.3901\/ref-36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/ADICS58448.2024.10533619","article-title":"YOLOv8: a novel object detection algorithm with enhanced performance and robustness","author":"Varghese","year":"2024"},{"key":"10.7717\/peerj-cs.3901\/ref-37","doi-asserted-by":"publisher","first-page":"9718","DOI":"10.1109\/CVPR52734.2025.00908","article-title":"LSNet: see large, focus small","author":"Wang","year":"2025"},{"issue":"24","key":"10.7717\/peerj-cs.3901\/ref-38","doi-asserted-by":"publisher","first-page":"13122","DOI":"10.3390\/app132413122","article-title":"BA-YOLO for object detection in satellite remote sensing images","volume":"13","author":"Wang","year":"2023","journal-title":"Applied Sciences"},{"issue":"2","key":"10.7717\/peerj-cs.3901\/ref-39","doi-asserted-by":"publisher","first-page":"101927","DOI":"10.1016\/j.ecoinf.2022.101927","article-title":"A review of automatic recognition technology for bird vocalizations in the deep learning era","volume":"73","author":"Xie","year":"2023","journal-title":"Ecological Informatics"},{"key":"10.7717\/peerj-cs.3901\/ref-40","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1109\/AIIIP61647.2023.00062","article-title":"A new strategy for bird detection in coastal wetlands based on improved YOLOv6 3.0","author":"Yang","year":"2023"},{"key":"10.7717\/peerj-cs.3901\/ref-41","doi-asserted-by":"publisher","first-page":"4248","DOI":"10.1109\/ICIP.2015.7351607","article-title":"Construction of a bird image dataset for ecological investigations","author":"Yoshihashi","year":"2015"},{"key":"10.7717\/peerj-cs.3901\/ref-42","doi-asserted-by":"publisher","first-page":"1","DOI":"10.48550\/arxiv.1511.07122","article-title":"Multi-Scale Context Aggregation by Dilated Convolutions","author":"Yu","year":"2015"},{"key":"10.7717\/peerj-cs.3901\/ref-43","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1710.09412","article-title":"mixup: beyond empirical risk minimization","author":"Zhang","year":"2017"},{"issue":"9","key":"10.7717\/peerj-cs.3901\/ref-44","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1016\/j.neucom.2022.07.042","article-title":"Focal and efficient IOU loss for accurate bounding box regression","volume":"506","author":"Zhang","year":"2022","journal-title":"Neurocomputing"},{"key":"10.7717\/peerj-cs.3901\/ref-45","doi-asserted-by":"publisher","first-page":"6848","DOI":"10.1109\/CVPR.2018.00716","article-title":"ShuffleNet: an extremely efficient convolutional neural network for mobile devices","author":"Zhang","year":"2018"},{"key":"10.7717\/peerj-cs.3901\/ref-46","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1109\/AIAM57466.2022.00090","article-title":"Bird movement recognition research based on YOLOv4\u00a0model","author":"Zhao","year":"2022"},{"key":"10.7717\/peerj-cs.3901\/ref-47","doi-asserted-by":"publisher","first-page":"16965","DOI":"10.1109\/CVPR52733.2024.01605","article-title":"DETRs beat YOLOs on real-time object detection","author":"Zhao","year":"2024"}],"container-title":["PeerJ Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/cs-3901.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3901.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3901.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3901.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T08:52:52Z","timestamp":1779958372000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/cs-3901"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,28]]},"references-count":47,"alternative-id":["10.7717\/peerj-cs.3901"],"URL":"https:\/\/doi.org\/10.7717\/peerj-cs.3901","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2376-5992"],"issn-type":[{"value":"2376-5992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,28]]},"article-number":"e3901"}}