EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Lightweight Fall Detection Framework for Smart-City CCTV Using Distilled Pose and Interpretable Features

Doniyorjon Mukhtorov, Young Im Cho

Applied Sciences · 08.05.2026 · 16 (10) · 4632

DOI: 10.3390/app16104632 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 08.05.2026. Verfasst von Doniyorjon Mukhtorov und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Gachon University research fund of 2025.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Vision-based fall detection for smart-city CCTV must be fast, interpretable, and robust to nuisance alarms. In real surveillance scenes, false alarms are often caused by sitting, crouching, duplicate detections, short-lived pose noise, and brief posture changes that do not correspond to actual falls. This paper presents a lightweight CCTV fall-detection framework evaluated on URFD, Le2i, and UP-Fall. The proposed method combines teacher-guided distillation from ViTPose to a YOLO26s-pose student, custom person detection, full-body ROI extraction, nine interpretable posture features, Random Forest classification, tracking-based duplicate suppression, and post-event false-positive rejection. The distillation stage improves pose mAP50-95 from 66.8% to 70.9% and pose mAP50 from 88.9% to 91.2%. In the final stand/fall setting, Random Forest with false-positive rejection achieves 98.46% accuracy, 98.61% precision, 98.43% recall, and 98.52% F1-score. The main contribution of this work is a practical and interpretable surveillance framework that integrates distilled lightweight pose estimation, posture-based fall representation, and tracking-aware false-positive suppression for robust deployment-oriented fall detection.

Förderung

  • Gachon University research fund of 2025

Zitieren

APA

Mukhtorov, D., & Cho, Y. I. (2026). A Lightweight Fall Detection Framework for Smart-City CCTV Using Distilled Pose and Interpretable Features. Applied Sciences, 16(10), 4632. https://doi.org/10.3390/app16104632

Vancouver

Mukhtorov D, Cho YI. A Lightweight Fall Detection Framework for Smart-City CCTV Using Distilled Pose and Interpretable Features. Applied Sciences. 2026;16(10):4632. doi:10.3390/app16104632

BibTeX
@article{Mukhtorov2026,
  author = {Mukhtorov, Doniyorjon and Cho, Young Im},
  title = {A Lightweight Fall Detection Framework for Smart-City CCTV Using Distilled Pose and Interpretable Features},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {10},
  pages = {4632},
  doi = {10.3390/app16104632}
}
Kostenlos starten →