FIXED-THRESHOLD RGB–POSE FALL DETECTION ACROSS PARTICIPANTS UNDER CONTROLLED IMAGE DEGRADATION
Eurasia Journal of Science and Technology · 2026
DOI: 10.61784/ejst3168 ↗Kurz gefasst
Fachartikel in der Zeitschrift Eurasia Journal of Science and Technology, 2026. Verfasst von YanFei Yuan und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
This study evaluates how fixed-threshold RGB–pose fall detection transfers across participants and responds to controlled image degradation. On UP-Fall, participants are separated into fitting, confirmation and final evaluation groups. A frozen image encoder and a geometric temporal pose classifier are combined by equal probability averaging at threshold 0.5. On final clean trials, the predefined primary seed achieves 94.42% window recall, 1.54% normal-window false-positive rate and 39/39 event hits. On matched trials, recall falls from 90.95% to 87.16% under darkening and 73.49% under strong blur. Across three seeds, mean blur recall is 44.87%, while valid pose geometry covers 19.91% of blurred sampled frames. The evaluation quantifies fixed-threshold tradeoffs and shows why event hits should be reported alongside window recall, seed sensitivity and pose coverage.
Zitieren
APA
Yuan, Y., & Liu, X. (2026). FIXED-THRESHOLD RGB–POSE FALL DETECTION ACROSS PARTICIPANTS UNDER CONTROLLED IMAGE DEGRADATION. Eurasia Journal of Science and Technology. https://doi.org/10.61784/ejst3168
Vancouver
Yuan Y, Liu X. FIXED-THRESHOLD RGB–POSE FALL DETECTION ACROSS PARTICIPANTS UNDER CONTROLLED IMAGE DEGRADATION. Eurasia Journal of Science and Technology. 2026. doi:10.61784/ejst3168
BibTeX
@article{Yuan2026,
author = {Yuan, YanFei and Liu, XiaoNi},
title = {FIXED-THRESHOLD RGB–POSE FALL DETECTION ACROSS PARTICIPANTS UNDER CONTROLLED IMAGE DEGRADATION},
journal = {Eurasia Journal of Science and Technology},
year = {2026},
doi = {10.61784/ejst3168}
}
EUVIMED