Library

On the Use of Low-Cost Radars and Machine Learning for In-Vehicle Passenger Monitoring

In this paper, we use a low-cost low-power mm-wave frequency modulated continuous wave (FMCW) radar for in-vehicle occupant monitoring. We propose an algorithm to identify occupied seats. Instead of using a high-resolution radar which increases the cost and area, we integrate machine learning algorithms with the results of covariance-based angle of arrival estimation Capon beamformer. We apply three classifiers, support vector machine (SVM), K-Nearest Neighbors (KNN) and Random Forest (RF). Our proposed system using SVM classifier achieved 96% accuracy on average in identifying the occupied seats in the test vehicles.

EngineeringComputer Science
Source

Paper

Full text

PDF

On the Use of Low-Cost Radars and Machine Learning for In-Vehicle Passenger Monitoring

Semantic Scholar · Engineering · 2020

Abstract

In this paper, we use a low-cost low-power mm-wave frequency modulated continuous wave (FMCW) radar for in-vehicle occupant monitoring. We propose an algorithm to identify occupied seats. Instead of using a high-resolution radar which increases the cost and area, we integrate machine learning algorithms with the results of covariance-based angle of arrival estimation Capon beamformer. We apply three classifiers, support vector machine (SVM), K-Nearest Neighbors (KNN) and Random Forest (RF). Our proposed system using SVM classifier achieved 96% accuracy on average in identifying the occupied seats in the test vehicles.

Source of record · Semantic Scholar

Similar papers

Machine Learning based In-Cabin Radar System for Passenger Monitoring SystemE. Hyun, Yi Jin, Jieun Bae et al.2023 · IEEE Vehicular Technology Conference · 2 citations In Library
Novel Radar based In-Vehicle Occupant Detection Using Convolutional Neural NetworksAshwini Kanakapura Sriranga, Qian Lu, Stewart A. Birrell2022 · IEEE Symposium Series on Computational Intelligence · 4 citations In Library
Machine Learning-Based Human Recognition Scheme Using a Doppler Radar Sensor for In-Vehicle ApplicationsE. Hyun, Youngseok Jin, Jae-Hyun Park et al.2020 · Italian National Conference on Sensors · 14 citations In Library
Non-Invasive Driver Activity Recognition using mmWave RadarAlhumaily, Basim, Ayaz, Fahad, Hussain, Sajjad et al.2025 · ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam) In Library
Non-Invasive Driver Activity Recognition using mmWave RadarBasim Alhumaily, Fahad Ayaz, Sajjad Hussain et al.2026 In Library
Low-Cost FMCW Radar Human-Vehicle Classification Based on Transfer LearningAli Rizik, A. Randazzo, R. Vio et al.2020 · International Congress of Mathematicans · 4 citations In Library
Weakly Supervised Deep Learning Method for Vulnerable Road User Detection in FMCW RadarMartin D. Dimitrievski, Ivana Shopovska, D. V. Hamme et al.2020 · 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC) · 23 citations In Library
Indoor Seat Occupancy Classification with Wi-Fi Channel State Information and Machine Learning MethodsYichuan Zhang, Jiefeng Li, Han Wang2021 · International Conference on Sensors, Signal and Image Processing · 1 citation In Library
In-cabin occupant monitoring system based on improved Yolo, deep reinforcement learning, and multi-task CNN for autonomous drivingChadia Khraief Ouled Azaiz, Jessica Dacleu Ndengue2023 · International Conference on Machine Vision · 3 citations In Library
Deep Neural Network-Based In-Vehicle People Localization Using Ultra-Wideband RadarSohee Lim, Jaehoon Jung, Seong-Cheol Kim et al.2020 · IEEE Access · 27 citations In Library
© 2026 NYSGPT2525 LLC