Related Experiment Video
Updated: Jun 27, 2026

Tracking Infiltration Front Depth Using Time-lapse Multi-offset Gathers Collected with Array Antenna Ground Penetrating Radar
Published on: May 1, 2018
High-Accuracy Indoor Multiple-Extended-Target Tracking Algorithm Based on 60 GHz Millimeter-Wave Radar
Bo Gao1, Jianzhong Chen2, Bo Huang1
1College of Information and Control Engineering, Xi'an University of Architecture and Technology, Xi'an 710055, China.
This study introduces a novel radar-based tracking algorithm for smart homes, overcoming visual sensor limitations. The new method accurately tracks multiple people indoors, ensuring privacy and reliability.
Area of Science:
- Computer Science
- Electrical Engineering
- Robotics
Background:
- Visual sensors in smart homes face challenges like poor lighting, occlusion, and privacy issues.
- Frequency-modulated continuous-wave (FMCW) millimeter-wave radar offers a privacy-preserving alternative, unaffected by lighting or environmental changes.
Purpose of the Study:
- To develop a high-accuracy tracking algorithm for multiple extended targets in cluttered indoor environments using FMCW radar.
- To enhance the reliability and privacy of sensing solutions for smart homes and elderly care.
Main Methods:
- An improved Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm was used for radar point cloud clustering.
- An optimized Nearest-Neighbor Data Association (NNDA) scheme integrated clustering information for improved measurement matching.
- An Extended Kalman Filter (EKF) was employed for state estimation of tracked targets.
Main Results:
- The algorithm achieved tracking errors below 0.4 m in typical motion scenarios.
- Continuous tracking was maintained during two-person crossing scenarios.
- A 93.3% counting accuracy was reached in five-person scenarios, outperforming a commercial radar system.
Conclusions:
- The proposed radar-based tracking algorithm provides a reliable and privacy-preserving sensing solution for smart homes, elderly care, and intelligent buildings.
- The method effectively addresses the limitations of visual sensors in indoor environments.
Related Concept Videos
Vector Functions and Motion: Problem Solving
Errors in Global Positioning System
Real-World Applications of Space Curves
Types of Global Positioning System Surveys

