aiqbenchInformații despre AI & calcul cuantic

...

Română · beta. Traducerea a fost făcută automat și este încă în curs de revizuire. Citește pagina în engleză

perspectiva aiqbenchMachine learning

This research presents a privacy-preserving framework for real-time fall detection by replacing RGB video streams with unsupervised motion keypoints and predictive modeling to reduce bandwidth usage. The study demonstrates that while supervised pose estimation performs better when anatomical landmarks are visible, the proposed unsupervised approach maintains robust sensitivity under occlusion conditions where traditional methods fail significantly. For AI readers in computer vision applications, this work highlights critical trade-offs between representation choices regarding visibility constraints versus false positive rates in safety-critical monitoring systems.

Sursă care acoperăarXiv

Ce este aceastaLectura unui model asupra articolului și a acoperirii conexe, scrisă pentru aiqbench. Nu sunt cuvintele publicației.

Unsupervised Keypoints for Real-Time Fall Detection: Comparative Analysis Under Real-world Conditions with Predictive Bandwidth Reduction

arXiv21 iulie 20263 min de cititArticolul și perspectiva sunt în engleză.

arXiv:2607.15400v2 Announce Type: replace-cross Abstract: Falls among older adults are a major safety challenge, but continuous monitoring is difficult to sustain. Video captures fall-related posture and motion, yet deployment is limited by privacy, computation, and bandwidth. Supervised pose estimation is anatomically interpretable but vulnerable to occlusion and partial body visibility. We propose a privacy-preserving framework that replaces RGB transmission with compact motion representations based on unsupervised keypoints and predictive temporal modeling. Local processing performs segmentation and keypoint extraction; variational recurrent prediction and sequence classification then detect falls from observed and forecasted motion. We evaluate the framework on the UR Fall Detection and Human Fall datasets using random, subject-disjoint, and occlusion-based splits. Under random splits, neither representation consistently dominates, suggesting that standard protocols may hide meaningful differences. Under subject-disjoint evaluation, supervised keypoints show a statistically significant advantage, but performance varies by subject: they perform better when anatomical landmarks are visible, whereas unsupervised keypoints are more robust to occlusion and partial visibility, though they produce more false positives for complex activities. Under occlusion-based evaluation, supervised keypoints miss nearly half of all falls, while unsupervised keypoints retain strong sensitivity and substantially outperform them. Their anatomical independence allows spatial anchors to adapt to visible body structure rather than fail on absent landmarks. The gap widens under bandwidth constraints, where supervised localization errors compound through the temporal model. These findings show that representation choice should reflect expected visual conditions and that unsupervised keypoints offer an advantage when body visibility is compromised.

Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)

arXiv:2607.15400 [cs.CV]

(or arXiv:2607.15400v2 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2607.15400 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Text integral sub licența deschisă a publicației · 98 cuvinte

Citește pe arXiv ↗Întreabă despre acest articol