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

arXiv: https://arxiv.org/abs/2607.12909 · HTML: https://mlsanity.com/paper/2607.12909/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 25 references that are in the map.
- First posted on arXiv 14 Jul 2026.

## Builds on (most cited first, 8 of 8)

- [Liquid Time-constant Networks](https://mlsanity.com/paper/2006.04439/) (2020)
- [Convergence of Edge Computing and Deep Learning: A Comprehensive Survey](https://mlsanity.com/paper/1907.08349/) (2019)
- [Learning Stable Deep Dynamics Models](https://mlsanity.com/paper/2001.06116/) (2020)
- [Closed-form Continuous-time Neural Models](https://mlsanity.com/paper/2106.13898/) (2021)
- [Distributed Deep Learning Model for Intelligent Video Surveillance Systems with Edge Computing](https://mlsanity.com/paper/1904.06400/) (2019)
- [Causal Navigation by Continuous-time Neural Networks](https://mlsanity.com/paper/2106.08314/) (2021)
- [Vision-Based Fall Event Detection in Complex Background Using Attention Guided Bi-directional LSTM](https://mlsanity.com/paper/2007.07773/) (2020)
- [Liquid-Graph Time-Constant Network for Multi-Agent Systems Control](https://mlsanity.com/paper/2404.13982/) (2024)

## Abstract (arXiv)

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.