CyanKitten: AI-Driven Markerless Motion Capture for Improved Elderly Well-Being

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Guo, Mengyao, Nie, Yu, Han, Jinda, Li, Zongxing, Gao, Ze
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909551568093184
author Guo, Mengyao
Nie, Yu
Han, Jinda
Li, Zongxing
Gao, Ze
author_facet Guo, Mengyao
Nie, Yu
Han, Jinda
Li, Zongxing
Gao, Ze
contents This paper introduces CyanKitten, an interactive virtual companion system tailored for elderly users, integrating advanced posture recognition, behavior recognition, and multimodal interaction capabilities. The system utilizes a three-tier architecture to process and interpret user movements and gestures, leveraging a dual-camera setup and a convolutional neural network trained explicitly on elderly movement patterns. The behavior recognition module identifies and responds to three key interactive gestures: greeting waves, petting motions, and heart-making gestures. A multimodal integration layer also combines visual and audio inputs to facilitate natural and intuitive interactions. This paper outlines the technical implementation of each component, addressing challenges such as elderly-specific movement characteristics, real-time processing demands, and environmental adaptability. The result is an engaging and accessible virtual interaction experience designed to enhance the quality of life for elderly users.
format Preprint
id arxiv_https___arxiv_org_abs_2503_19398
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CyanKitten: AI-Driven Markerless Motion Capture for Improved Elderly Well-Being
Guo, Mengyao
Nie, Yu
Han, Jinda
Li, Zongxing
Gao, Ze
Human-Computer Interaction
F.2.2; I.2.7
This paper introduces CyanKitten, an interactive virtual companion system tailored for elderly users, integrating advanced posture recognition, behavior recognition, and multimodal interaction capabilities. The system utilizes a three-tier architecture to process and interpret user movements and gestures, leveraging a dual-camera setup and a convolutional neural network trained explicitly on elderly movement patterns. The behavior recognition module identifies and responds to three key interactive gestures: greeting waves, petting motions, and heart-making gestures. A multimodal integration layer also combines visual and audio inputs to facilitate natural and intuitive interactions. This paper outlines the technical implementation of each component, addressing challenges such as elderly-specific movement characteristics, real-time processing demands, and environmental adaptability. The result is an engaging and accessible virtual interaction experience designed to enhance the quality of life for elderly users.
title CyanKitten: AI-Driven Markerless Motion Capture for Improved Elderly Well-Being
topic Human-Computer Interaction
F.2.2; I.2.7
url https://arxiv.org/abs/2503.19398