Related Experiment Video
Updated: May 4, 2026
Author Spotlight: Innovations in iTUG Test for Enhanced Risk Assessment and Cognitive Insights
Published on: October 25, 2024
Fall risk assessment and early-warning for toddler behaviors at home
Mau-Tsuen Yang1, Min-Wen Chuang
1Department of Computer Science & Information Engineering, National Dong-Hwa University, No. 1, Sec. 2, Da-Hsueh Rd., Shoufeng, Hualien 974, Taiwan. mtyang@mail.ndhu.edu.tw.
Insights
This study introduces an early-warning system to monitor toddlers' fall-prone behaviors at home, preventing injuries. The system accurately assesses fall risks and triggers alarms, enhancing child safety.
Area of Science:
- Childcare technology
- Robotics and intelligent systems
- Human-computer interaction
Background:
- Accidental falls are a primary cause of serious toddler injuries, frequently occurring in home environments.
- Existing fall detection systems rely on immediate observation, lacking proactive risk assessment.
- Home environments present unique challenges for monitoring toddler behavior and fall risks.
Purpose of the Study:
- To develop an early-warning childcare system for monitoring fall-prone behaviors in toddlers at home.
- To move beyond immediate fall detection towards proactive risk assessment using behavioral analysis.
- To enhance the safety of toddlers by identifying and mitigating potential fall hazards.
Main Methods:
- Utilized a Kinect system for depth image capture, enabling 3D human skeleton tracking and floor plane detection.
- Developed eight fall-prone behavioral modules for toddlers, categorized by posture, motion, balance, and altitude.
- Implemented a multi-modal fusion approach, employing weighted mean thresholding or Support Vector Machine (SVM) classification for fall risk assessment.
Main Results:
- The proposed system achieved a 92% accuracy rate in assessing fall risks and triggering alarms.
- The system operates efficiently at a speed of 20 frames per second, suitable for real-time monitoring.
- Optimizations were performed on local and global parameters to enhance system performance.
Conclusions:
- The developed early-warning system effectively monitors toddlers' fall-prone behaviors, offering proactive safety measures.
- The system demonstrates high accuracy and speed, making it a viable solution for home-based childcare safety.
- This approach represents a significant advancement in preventing fall-related injuries in young children.
Abstract:
Accidental falls are the major cause of serious injuries in toddlers, with most of these falls happening at home. Instead of providing immediate fall detection based on short-term observations, this paper proposes an early-warning childcare system to monitor fall-prone behaviors of toddlers at home. Using 3D human skeleton tracking and floor plane detection based on depth images captured by a Kinect system, eight fall-prone behavioral modules of toddlers are developed and organized according to four essential criteria: posture, motion, balance, and altitude. The final fall risk assessment is generated by a multi-modal fusion using either a weighted mean thresholding or a support vector machine (SVM) classification. Optimizations are performed to determine local parameter in each module and global parameters of the multi-modal fusion. Experimental results show that the proposed system can assess fall risks and trigger alarms with an accuracy rate of 92% at a speed of 20 frames per second.
