跳到正文
arXiv cs.AI· Wenjun Xia, Zhicheng Peng, Haopeng Li, Zhengdi Zhang·· 4 小时前AI 评分10

基于视觉的低功耗边缘平台实时跌倒检测框架

Real-time fall detection based on vision for low-power edge platforms

AI 导读

一篇提出物理信息跌倒检测框架的 arXiv 论文已被作者 Wenjun Xia 撤稿,原因是发现术语不准确并准备替换投稿。该框架将跌倒建模为耦合动力系统的失稳事件,采用双 LTC 架构(质心与支撑基子系统)加可学习耦合模块和稳定性流形分类器,网络参数不足 50K,可在资源受限边缘设备上实时推理。初步研究仅在二分类数据集上验证核心稳定性判别能力,三状态预测留待后续工作。

正文 · 原文

This paper has been withdrawn by Wenjun Xia

No PDF available, click to view other formats

Abstract:Falling detection is vital for elderly care and intelligent surveillance; however, prevailing vision-based approaches predominantly frame it as static pose classification or discrete temporal pattern matching, fundamentally overlooking the instability dynamics of the human support system. This paper proposes a physics-informed falling detection framework that recasts falling as a stability-loss event in a coupled dynamical system. We introduce a novel dual-LTC architecture comprising a Center-of-Mass (CoM) subsystem and a Base-of-Support (BoS) subsystem, both instantiated as Liquid Time-Constant (LTC) neural networks to continuously model inertial trajectory evolution and ground-contact adjustment through adaptive time constants, Physical interpretability of falling motion. A learnable coupling module emulates physical interaction between the two subsystems, while a Stability Manifold classifier operates in the joint latent space to detect boundary crossing via Lyapunov-inspired stability metrics. Complementary counterfactual trajectory projection and Time-to-Collision (TTC) estimation further enable irreversibility assessment and early warning. The architecture is designed to support a three-state prediction paradigm (Normal, Falling, Fallen); in this preliminary study, we validate the core stability discrimination capability on a two-class dataset (Normal vs. Falling), leaving the full three-state temporal transition to future work. Unlike conventional CNN--RNN pipelines, the proposed formulation encodes continuous-time mechanical inertia, yielding a sub-50K-parameter network capable of real-time inference on resource-constrained edge devices. Extensive experiments demonstrate competitive accuracy with superior physical interpretability, validating its efficacy for low-compute visual fall detection.
Comments: We have discovered a terminological inaccuracy in our manuscript. We are replacing the submission to correct this misnomer and revise the related context
Subjects: Neurons and Cognition (q-bio.NC); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
Cite as: arXiv:2607.12909 [q-bio.NC]
  (or arXiv:2607.12909v2 [q-bio.NC] for this version)
  https://doi.org/10.48550/arXiv.2607.12909

arXiv-issued DOI via DataCite

Submission history

From: Wenjun Xia [view email]
[v1] Tue, 14 Jul 2026 15:43:41 UTC (337 KB)
[v2] Tue, 17 Nov 2026 12:48:00 UTC (1 KB) (withdrawn)

来源:arXiv cs.AI · arxiv.org