Related Experiment Video
Updated: Feb 25, 2026
08:05
Design and Analysis for Fall Detection System Simplification
Published on: April 6, 2020
11.2K
Simultaneous Indoor Tracking and Activity Recognition Using Pyroelectric Infrared Sensors.
Xiaomu Luo1, Qiuju Guan2, Huoyuan Tan3
1School of Medical Information Engineering, Guangzhou University of Chinese Medicine, Guangzhou 510000, China. woodwood2000@163.com.
Sensors (Basel, Switzerland)
|August 1, 2017
Summary
This study introduces a novel wireless sensor network (WSN) using pyroelectric infrared (PIR) sensors for simultaneous indoor human tracking and activity recognition, achieving high accuracy for ambient assistive living.
Area of Science:
- Computer Science
- Engineering
- Artificial Intelligence
Background:
- Indoor human tracking and activity recognition are crucial for ambient assistive living.
- Existing methods often address these problems separately, limiting potential synergies.
Purpose of the Study:
- To develop a unified system for simultaneous indoor human tracking and activity recognition.
- To leverage the combined spatial-temporal information for improved performance.
Main Methods:
- A wireless sensor network (WSN) composed of pyroelectric infrared (PIR) sensor arrays with modulated fields of view (FOV).
- A modified partial filter algorithm for human target localization.
- A two-layer random forest (RF) classifier for activity recognition, integrating location and activity features.
Main Results:
- Mean localization error of approximately 0.85 meters.
- Mean accuracy exceeding 92% for recognizing five daily activities via 10-fold cross-validation.
Conclusions:
- The proposed system effectively integrates human tracking and activity recognition.
- The method demonstrates significant potential for enhancing ambient assistive living environments.
