{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T22:23:05Z","timestamp":1780525385281,"version":"3.54.1"},"reference-count":54,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,2,19]],"date-time":"2024-02-19T00:00:00Z","timestamp":1708300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Comput. Neurosci."],"abstract":"<jats:p>Gesture serves as a crucial means of communication between individuals and between humans and machines. In football matches, referees communicate judgment information through gestures. Due to the diversity and complexity of referees\u2019 gestures and interference factors, such as the players, spectators, and camera angles, automated football referee gesture recognition (FRGR) has become a challenging task. The existing methods based on visual sensors often cannot provide a satisfactory performance. To tackle FRGR problems, we develop a deep learning model based on YOLOv8s. Three improving and optimizing strategies are integrated to solve these problems. First, a Global Attention Mechanism (GAM) is employed to direct the model\u2019s attention to the hand gestures and minimize the background interference. Second, a P2 detection head structure is integrated into the YOLOv8s model to enhance the accuracy of detecting smaller objects at a distance. Third, a new loss function based on the Minimum Point Distance Intersection over Union (MPDIoU) is used to effectively utilize anchor boxes with the same shape, but different sizes. Finally, experiments are executed on a dataset of six hand gestures among 1,200 images. The proposed method was compared with seven different existing models and 10 different optimization models. The proposed method achieves a precision rate of 89.3%, a recall rate of 88.9%, a mAP@0.5 rate of 89.9%, and a mAP@0.5:0.95 rate of 77.3%. These rates are approximately 1.4%, 2.0%, 1.1%, and 5.4% better than those of the newest YOLOv8s, respectively. The proposed method has right prospect in automated gesture recognition for football matches.<\/jats:p>","DOI":"10.3389\/fncom.2024.1341234","type":"journal-article","created":{"date-parts":[[2024,2,19]],"date-time":"2024-02-19T04:56:14Z","timestamp":1708318574000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Football referee gesture recognition algorithm based on YOLOv8s"],"prefix":"10.3389","volume":"18","author":[{"given":"Zhiyuan","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanyuan","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanfei","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2024,2,19]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1016\/j.psychsport.2017.10.006","article-title":"Football refereeing: an integrative review","volume":"35","author":"Arag\u00e3o e Pina","year":"2018","journal-title":"Psychol. Sport Exerc."},{"key":"ref2","doi-asserted-by":"publisher","first-page":"595","DOI":"10.1080\/00036846.2021.1967863","article-title":"Image is everything! Professional football players' visibility and wages, evidence from the Italian Serie a","volume":"54","author":"Bernardo","year":"2022","journal-title":"Appl. Econ."},{"key":"ref3","author":"Bochkovskiy","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"1185","DOI":"10.1080\/02640410601038576","article-title":"Referee bias contributes to home advantage in English premiership football","volume":"25","author":"Boyko","year":"2007","journal-title":"J. Sports Sci."},{"key":"ref5","author":"Chambers","year":"2004"},{"key":"ref6","author":"Gao","year":"2021"},{"key":"ref7","author":"Ge","year":"2021"},{"key":"ref8","author":"Gevorgyan","year":"2022"},{"key":"ref9","first-page":"1440","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognitionFast r-cnn","author":"Girshick","year":"2015"},{"key":"ref10","first-page":"580","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognitionRich feature hierarchies for accurate object detection and semantic segmentation","author":"Girshick","year":"2014"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1177\/0193723502261003","article-title":"Supporters, followers, fans, and flaneurs: a taxonomy of spectator identities in football","volume":"26","author":"Giulianotti","year":"2002","journal-title":"J. Sport Soc. Issues"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"1929","DOI":"10.1007\/s00138-014-0596-3","article-title":"The chalearn gesture dataset (cgd 2011)","volume":"25","author":"Guyon","year":"2014","journal-title":"Mach. Vis. Appl."},{"key":"ref13","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","article-title":"Spatial pyramid pooling in deep convolutional networks for visual recognition","volume":"37","author":"He","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref14","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1007\/s11573-021-01058-5","article-title":"Monitoring experts: insights from the introduction of video assistant referee (VAR) in elite football","volume":"92","author":"Holder","year":"2022","journal-title":"J. Bus. Econ."},{"key":"ref15","author":"Hu","year":"2018"},{"key":"ref16","author":"Jiang","year":"2020"},{"key":"ref17","volume-title":"Ultralytics\/yolov5: v7. 0-yolov5 sota realtime instance segmentation","author":"Jocher","year":"2022"},{"key":"ref18","author":"Li","year":"2022"},{"key":"ref19","first-page":"21002","article-title":"Generalized focal loss: learning qualified and distributed bounding boxes for dense object detection","volume":"33","author":"Li","year":"2020","journal-title":"Adv. Neural Inf. Proces. Syst."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2021\/9562782","article-title":"Computer aided teaching system based on artificial intelligence in football teaching and training","volume":"2021","author":"Li","year":"2021","journal-title":"Mob. Inf. Syst."},{"key":"ref21","author":"Lin","year":"2017"},{"key":"ref22","author":"Liu","year":"2018"},{"key":"ref23","author":"Liu","year":"2021"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"435","DOI":"10.14569\/IJACSA.2023.0140435","article-title":"Hand gesture recognition based on various deep learning YOLO models","volume":"14","author":"Mesbahi","year":"2023","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"ref25","doi-asserted-by":"publisher","first-page":"4164","DOI":"10.3390\/app11094164","article-title":"Real-time hand gesture recognition based on deep learning YOLOv3 model","volume":"11","author":"Mujahid","year":"2021","journal-title":"Appl. Sci."},{"key":"ref26","author":"Ni","year":"2018"},{"key":"ref27","author":"Pan","year":"2018"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"3172","DOI":"10.1109\/TCYB.2020.3007173","article-title":"A hierarchical hand gesture recognition framework for sports referee training-based Emg and accelerometer sensors","volume":"52","author":"Pan","year":"2020","journal-title":"IEEE Trans Cybern"},{"key":"ref29","author":"Pantzalis","year":"2020"},{"key":"ref30","author":"Park","year":"2018"},{"key":"ref31","author":"Park","year":"2018"},{"key":"ref32","author":"Redmon","year":"2016"},{"key":"ref33","author":"Redmon","year":"2017"},{"key":"ref34","author":"Redmon","year":"2018"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster r-cnn: towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Adv. Neural Inf. Proces. Syst."},{"key":"ref36","author":"Rezatofighi","year":"2019"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"5393","DOI":"10.30534\/ijatcse\/2020\/175942020","article-title":"Binary cross entropy with deep learning technique for image classification","volume":"9","author":"Ruby","year":"2020","journal-title":"Int. J. Adv. Trends Comput. Sci. Eng"},{"key":"ref38","author":"Siliang","year":"2023"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1080\/02640414.2020.1809163","article-title":"Video assistant referees (VAR): the impact of technology on decision making in association football referees","volume":"39","author":"Spitz","year":"2021","journal-title":"J. Sports Sci."},{"key":"ref40","author":"Sun","year":"2021"},{"key":"ref41","author":"Terven","year":"2023"},{"key":"ref42","first-page":"7464","volume-title":"YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","author":"Wang","year":"2023"},{"key":"ref43","first-page":"5130","article-title":"Football match intelligent editing system based on deep learning","volume":"13","author":"Wang","year":"2019","journal-title":"Ksii Trans Internet Information Syst"},{"key":"ref44","author":"Woo","year":"2018"},{"key":"ref45","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1080\/24748668.2013.11868645","article-title":"The role of performance analysts within the coaching process: performance analysts survey \u2018the role of performance analysts in elite football club settings.\u2019","volume":"13","author":"Wright","year":"2013","journal-title":"Int. J. Perform. Anal. Sport"},{"key":"ref46","doi-asserted-by":"publisher","first-page":"596","DOI":"10.3390\/electronics12030596","article-title":"Static gesture recognition algorithm based on improved Yolov5s","volume":"12","author":"Wu","year":"2023","journal-title":"Electronics"},{"key":"ref47","author":"Yeh","year":"2017"},{"key":"ref48","doi-asserted-by":"publisher","first-page":"953","DOI":"10.1016\/j.procs.2018.04.095","article-title":"Recognition of basketball referee signals from videos using histogram of oriented gradients (HOG) and support vector machine (SVM)","volume":"130","author":"\u017demgulys","year":"2018","journal-title":"Proc Comput Sci"},{"key":"ref49","doi-asserted-by":"publisher","first-page":"979","DOI":"10.1007\/s12652-019-01209-1","article-title":"Recognition of basketball referee signals from real-time videos","volume":"11","author":"\u017demgulys","year":"2020","journal-title":"J. Ambient. Intell. Humaniz. Comput."},{"key":"ref50","doi-asserted-by":"publisher","first-page":"107625","DOI":"10.1016\/j.compag.2023.107625","article-title":"Lightweight tomato real-time detection method based on improved YOLO and mobile deployment","volume":"205","author":"Zeng","year":"2023","journal-title":"Comput. Electron. Agric."},{"key":"ref51","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1080\/17511321.2020.1857823","article-title":"Rules, standards, and the video assistant referee in football","volume":"16","author":"Zglinski","year":"2022","journal-title":"Sport Ethics Philos"},{"key":"ref52","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":"ref53","author":"Zheng","year":"2020"},{"key":"ref54","author":"Zhou","year":"2016"}],"container-title":["Frontiers in Computational Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fncom.2024.1341234\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,19]],"date-time":"2024-02-19T04:56:20Z","timestamp":1708318580000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fncom.2024.1341234\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,19]]},"references-count":54,"alternative-id":["10.3389\/fncom.2024.1341234"],"URL":"https:\/\/doi.org\/10.3389\/fncom.2024.1341234","relation":{},"ISSN":["1662-5188"],"issn-type":[{"value":"1662-5188","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,19]]},"article-number":"1341234"}}