Preliminary Study on Suppressing False Positive of Single Channel Radar Based In-Cabin Occupancy Detection Utilizing Multipath Characteristics

In-cabin monitoring radar is expected to increase rapidly, driven by the addition of Child Presence Detection (CPD) to the evaluation criteria of Euro NCAP. Although various studies have been conducted on radar-based occupancy detection, there has been little research on false positives caused by people outside the vehicle. Therefore, we propose a method focusing on the shape of the range profiles. We assume that the number of multipath reflections received by the radar changes depending on the position of the person, leading to a change in the shape of the range profiles. To verify the effectiveness of the proposed method, experiments were conducted by installing a 60GHz millimeter-wave radar on a vehicle, and range profiles were obtained separately for a child sitting in each seat inside the vehicle and for an adult standing outside the vehicle. As a result, it was observed that the shape of the range profiles changed depending on the position of the person. Furthermore, by using two features related to the shape of the range profile, we were able to achieve a 100% detection rate of people inside the vehicle while suppressing false positives caused by people outside the vehicle. This method is also cost-effective and offers more flexibility in installation location, as it uses range profiles, not angle of arrival information.

Authors

Institutions

Publication Details

Published
2024-12-21
DOI
https://doi.org/10.1109/apace62360.2024.10877279
Primary Topic
Radar Systems and Signal Processing
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Preliminary Study on Suppressing False Positive of Single Channel Radar Based In-Cabin Occupancy Detection Utilizing Multipath Characteristics

Takumi Takei, Isao Matsushima, Koichi Kai
Radar Systems and Signal Processing
article

Preliminary Study on Suppressing False Positive of Single Channel Radar Based In-Cabin Occupancy Detection Utilizing Multipath Characteristics

Takumi Takei, Isao Matsushima, Koichi Kai
article en

Abstract

In-cabin monitoring radar is expected to increase rapidly, driven by the addition of Child Presence Detection (CPD) to the evaluation criteria of Euro NCAP. Although various studies have been conducted on radar-based occupancy detection, there has been little research on false positives caused by people outside the vehicle. Therefore, we propose a method focusing on the shape of the range profiles. We assume that the number of multipath reflections received by the radar changes depending on the position of the person, leading to a change in the shape of the range profiles. To verify the effectiveness of the proposed method, experiments were conducted by installing a 60GHz millimeter-wave radar on a vehicle, and range profiles were obtained separately for a child sitting in each seat inside the vehicle and for an adult standing outside the vehicle. As a result, it was observed that the shape of the range profiles changed depending on the position of the person. Furthermore, by using two features related to the shape of the range profile, we were able to achieve a 100% detection rate of people inside the vehicle while suppressing false positives caused by people outside the vehicle. This method is also cost-effective and offers more flexibility in installation location, as it uses range profiles, not angle of arrival information.

Mitsubishi Electric (Japan) (JP)
Affordable and clean energy
Openalex Percentile: Top 55%
Radar Systems and Signal Processing
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.