Automated efficient traffic gesture recognition using swin transformer-based multi-input deep network with radar images

Basit Öğe Kaydı
dc.authoridUZEN, Huseyin/0000-0002-0998-2130
dc.authoridAtila, Orhan/0000-0001-7211-913X
dc.authoridFIRAT, Huseyin/0000-0002-1257-8518
dc.contributor.authorFirat, Huseyin
dc.contributor.authorUzen, Huseyin
dc.contributor.authorAtila, Orhan
dc.contributor.authorSengur, Abdulkadir
dc.date.accessioned2025-02-22T14:09:05Z
dc.date.available2025-02-22T14:09:05Z
dc.date.issued2025
dc.departmentDicle Üniversitesien_US
dc.description.abstractRadar-based artificial intelligence (AI) applications have gained significant attention recently, spanning from fall detection to gesture recognition. The growing interest in this field has led to a shift towards deep convolutional networks, and transformers have emerged to address limitations in convolutional neural network methods, becoming increasingly popular in the AI community. In this paper, we present a novel hybrid approach for radar-based traffic hand gesture classification using transformers. Traffic hand gesture recognition (HGR) holds importance in AI applications, and our proposed three-phase approach addresses the efficiency and effectiveness of traffic HGR. In the initial phase, feature vectors are extracted from input radar images using the pre-trained DenseNet-121 model. These features are then consolidated by concatenating them to gather information from diverse radar sensors, followed by a patch extraction operation. The concatenated features from all inputs are processed in the Swin transformer block to facilitate further HGR. The classification stage involves sequential application of global average pooling, Dense, and Softmax layers. To assess the effectiveness of our method on ULM university radar dataset, we employ various performance metrics, including accuracy, precision, recall, and F1-score, achieving an average accuracy score of 90.54%. We compare this score with existing approaches to demonstrate the competitiveness of our proposed method.en_US
dc.identifier.doi10.1007/s11760-024-03664-6
dc.identifier.issn1863-1703
dc.identifier.issn1863-1711
dc.identifier.issue1en_US
dc.identifier.scopus2-s2.0-85211089403en_US
dc.identifier.scopusqualityQ2en_US
dc.identifier.urihttps://doi.org/10.1007/s11760-024-03664-6
dc.identifier.urihttps://hdl.handle.net/11468/29786
dc.identifier.volume19en_US
dc.identifier.wosWOS:001375699800001
dc.identifier.wosqualityQ3
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.language.isoenen_US
dc.publisherSpringer London Ltden_US
dc.relation.ispartofSignal Image and Video Processingen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.snmzKA_WOS_20250222
dc.subjectDeep learningen_US
dc.subjectRadar imagesen_US
dc.subjectSwin transformersen_US
dc.subjectTraffic hand gestureen_US
dc.titleAutomated efficient traffic gesture recognition using swin transformer-based multi-input deep network with radar imagesen_US
dc.typeArticleen_US

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu