PulseAugur
EN
LIVE 08:18:14

On-device learning system MAUPITI enables smart IR sensors for pose and gesture recognition

By PulseAugur Editorial · [1 sources] ·

Researchers have developed MAUPITI, a novel on-device learning system for smart infrared sensors. This system utilizes a prototype-based Nearest Class Mean (NCM) classifier with a quantized Convolutional Neural Network (CNN) encoder to achieve pose and gesture recognition under strict memory and power constraints. Experiments demonstrate that MAUPITI offers accuracy comparable to conventional classifiers with minimal latency, enabling continuous adaptation of perception frameworks. AI

IMPACT Enables privacy-preserving, low-power AI capabilities in edge devices for real-time sensing applications.

RANK_REASON This is a research paper detailing a novel system for on-device learning on a smart infrared sensor. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

On-device learning system MAUPITI enables smart IR sensors for pose and gesture recognition

COVERAGE [1]

  1. arXiv cs.LG TIER_1 English(EN) · Beatrice Alessandra Motetti, Tanguy Dugas du Villard, Matteo Risso, Alessio Burrello, Francesco Daghero, Enrico Macii, Massimo Poncino, Marco Castellano, Alfio Basile, Daniele Jahier Pagliari ·

    MAUPITI: On-Device Prototype-Based Learning on a Smart Infrared Sensor

    arXiv:2608.07192v1 Announce Type: new Abstract: Low-resolution infrared (IR) array sensors represent an interesting solution for privacy-preserving human sensing in embedded systems. In this letter, we describe a smart multi-pixel IR sensor integrating a 16$\times$16 thermal MOSF…

RELATED TOPICS