EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

HIGH-PRECISION AERIAL OBJECT DETECTION MODEL UTILIZING YOLO V10 DEEP NEURAL NETWORK

Ayman Javid Hussain, Dr. Lalitha Saroja CH, Ruqiya Fatima

International Journal of AI Electronics and Nexus Energy · 14.08.2026 · 2 (3) · 262-271

DOI: 10.64751/6k1bdy24 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of AI Electronics and Nexus Energy, online erschienen am 14.08.2026. Verfasst von Ayman Javid Hussain und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The installation of a real-time visual tracking system with an active pan-tilt camera for indoor human motion detection is presented in this study. For precise and effective human detection in every video frame, the system makes use of the cutting-edge YOLOv10 object detection model. YOLOv10 is perfect for real-time applications due to its fast inference and enhanced detection accuracy, especially in difficult illumination and occlusion situations. The system uses a multiple object tracking (MOT) framework that keeps a dynamic graph structure to guarantee robustness. Several theories about the quantity and temporal trajectories of identified persons are handled by this graph. YOLOv10 allows frame-wise object detection with fewer false positives and missing detections than traditional frame differencing techniques. In order to achieve consistent tracking throughout time, the MOT module performs temporal data association, checking and confirming YOLOv10's frame-wise predictions. Because of this close interaction, the tracker can estimate object placements and increase overall tracking reliability by giving feedback to the detection module. In order to choose the most plausible explanation for the observed video, tracking hypotheses are continuously expanded and trimmed. The system's efficacy in real-time human motion tracking scenarios is demonstrated by experimental results, which show that the inclusion of YOLOv10 significantly improves detection precision and temporal consistency.

Zitieren

APA

Hussain, A. J., CH, D. L. S., & Fatima, R. (2026). HIGH-PRECISION AERIAL OBJECT DETECTION MODEL UTILIZING YOLO V10 DEEP NEURAL NETWORK. International Journal of AI Electronics and Nexus Energy, 2(3), 262-271. https://doi.org/10.64751/6k1bdy24

Vancouver

Hussain AJ, CH DLS, Fatima R. HIGH-PRECISION AERIAL OBJECT DETECTION MODEL UTILIZING YOLO V10 DEEP NEURAL NETWORK. International Journal of AI Electronics and Nexus Energy. 2026;2(3):262-271. doi:10.64751/6k1bdy24

BibTeX
@article{Hussain2026,
  author = {Hussain, Ayman Javid and CH, Dr. Lalitha Saroja and Fatima, Ruqiya},
  title = {HIGH-PRECISION AERIAL OBJECT DETECTION MODEL UTILIZING YOLO V10 DEEP NEURAL NETWORK},
  journal = {International Journal of AI Electronics and Nexus Energy},
  year = {2026},
  volume = {2},
  number = {3},
  pages = {262--271},
  doi = {10.64751/6k1bdy24}
}
Kostenlos starten →