Optimized YOLOv8 (YOLO-Prime), M-CNN, and Dynamic Linear Regression for Real-Time Aerial Vehicle Detection in Embedded Systems

Basit Öğe Kaydı
dc.contributor.authorCaliskan, Halil Huseyin
dc.contributor.authorKoruk, Talha
dc.date.accessioned2026-02-08T15:15:41Z
dc.date.available2026-02-08T15:15:41Z
dc.date.issued2025
dc.departmentBursa Teknik Üniversitesi
dc.description7th International Congress on Human-Computer Interaction, Optimization and Robotic Applications-ICHORA -- MAY 23-24, 2025 -- Ankara, TURKIYE
dc.description.abstractThis paper introduces a modified architecture of YOLOv8, called YOLO-Prime, to detect aerial vehicles. By employing YOLO-Prime to embedded systems such as Nvidia Jetson Xavier Nx and Rockchip 3588, we reduced the inference time by 130% compared to the YOLOv8m model and by 158% compared to the YOLOv8l model. In addition to YOLO-Prime, we present a Morphological CNN (M-CNN) to classify regions detected by YOLO-Prime. With the integration of M-CNN, we achieved an increase in detection accuracy by 20% in the detection of aerial vehicles. Furthermore, we introduce a dynamic linear regression model to predict the future coordinates of aerial vehicles. As a result of the integration of dynamic linear regression models to embedded systems, GPU utilization of deep learning models decreased by approximately 66%. In summary, the combination of YOLO-Prime, M-CNN, and the dynamic linear regression model contributes to detecting aerial vehicles in embedded systems where energy consumption, inference time, and accuracy are crucial for real-time applications.
dc.description.sponsorshipInstitute of Electrical and Electronics Engineers Inc,Ted University
dc.identifier.doi10.1109/ICHORA65333.2025.11017067
dc.identifier.isbn979-8-3315-1089-3
dc.identifier.isbn979-8-3315-1088-6
dc.identifier.issn2996-4385
dc.identifier.scopus2-s2.0-105008422457
dc.identifier.scopusqualityN/A
dc.identifier.urihttps://doi.org/10.1109/ICHORA65333.2025.11017067
dc.identifier.urihttps://hdl.handle.net/20.500.12885/5900
dc.identifier.wosWOS:001533792800084
dc.identifier.wosqualityN/A
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherIeee
dc.relation.ispartof2025 7Th International Congress on Human-Computer Interaction, Optimization and Robotic Applications, Ichora
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.snmzWOS_KA_20260207
dc.subjectLinear regression
dc.subjectYOLO
dc.subjectimage processing
dc.subjectCNN
dc.titleOptimized YOLOv8 (YOLO-Prime), M-CNN, and Dynamic Linear Regression for Real-Time Aerial Vehicle Detection in Embedded Systems
dc.typeConference Object

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu