Study on Multi-Heterogeneous Sensor Data Fusion Method Based on Millimeter-Wave Radar and Camera

This study presents a novel multimodal heterogeneous perception cross-fusion framework for intelligent vehicles that combines data from millimeter-wave radar and camera to enhance target tracking accuracy and handle system uncertainties. The framework employs a multimodal interaction strategy to pre...

Full description

Bibliographic Details
Main Author: Jianyu Duan
Format: Article
Language:English
Published: MDPI AG 2023-06-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/23/13/6044
_version_ 1797436090327498752
author Jianyu Duan
author_facet Jianyu Duan
author_sort Jianyu Duan
collection DOAJ
description This study presents a novel multimodal heterogeneous perception cross-fusion framework for intelligent vehicles that combines data from millimeter-wave radar and camera to enhance target tracking accuracy and handle system uncertainties. The framework employs a multimodal interaction strategy to predict target motion more accurately and an improved joint probability data association method to match measurement data with targets. An adaptive root-mean-square cubature Kalman filter is used to estimate the statistical characteristics of noise under complex traffic scenarios with varying process and measurement noise. Experiments conducted on a real vehicle platform demonstrate that the proposed framework improves reliability and robustness in challenging environments. It overcomes the challenges of insufficient data fusion utilization, frequent leakage, and misjudgment of dangerous obstructions around vehicles, and inaccurate prediction of collision risks. The proposed framework has the potential to advance the state of the art in target tracking and perception for intelligent vehicles.
first_indexed 2024-03-09T10:57:40Z
format Article
id doaj.art-d665dba95751485e8abe199e3e1f3dd3
institution Directory Open Access Journal
issn 1424-8220
language English
last_indexed 2024-03-09T10:57:40Z
publishDate 2023-06-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj.art-d665dba95751485e8abe199e3e1f3dd32023-12-01T01:33:56ZengMDPI AGSensors1424-82202023-06-012313604410.3390/s23136044Study on Multi-Heterogeneous Sensor Data Fusion Method Based on Millimeter-Wave Radar and CameraJianyu Duan0School of Transportation Science and Engineering, Beihang University, Beijing 100191, ChinaThis study presents a novel multimodal heterogeneous perception cross-fusion framework for intelligent vehicles that combines data from millimeter-wave radar and camera to enhance target tracking accuracy and handle system uncertainties. The framework employs a multimodal interaction strategy to predict target motion more accurately and an improved joint probability data association method to match measurement data with targets. An adaptive root-mean-square cubature Kalman filter is used to estimate the statistical characteristics of noise under complex traffic scenarios with varying process and measurement noise. Experiments conducted on a real vehicle platform demonstrate that the proposed framework improves reliability and robustness in challenging environments. It overcomes the challenges of insufficient data fusion utilization, frequent leakage, and misjudgment of dangerous obstructions around vehicles, and inaccurate prediction of collision risks. The proposed framework has the potential to advance the state of the art in target tracking and perception for intelligent vehicles.https://www.mdpi.com/1424-8220/23/13/6044autonomous vehiclesensor fusionuncertaintyperception sensorscameraradar
spellingShingle Jianyu Duan
Study on Multi-Heterogeneous Sensor Data Fusion Method Based on Millimeter-Wave Radar and Camera
Sensors
autonomous vehicle
sensor fusion
uncertainty
perception sensors
camera
radar
title Study on Multi-Heterogeneous Sensor Data Fusion Method Based on Millimeter-Wave Radar and Camera
title_full Study on Multi-Heterogeneous Sensor Data Fusion Method Based on Millimeter-Wave Radar and Camera
title_fullStr Study on Multi-Heterogeneous Sensor Data Fusion Method Based on Millimeter-Wave Radar and Camera
title_full_unstemmed Study on Multi-Heterogeneous Sensor Data Fusion Method Based on Millimeter-Wave Radar and Camera
title_short Study on Multi-Heterogeneous Sensor Data Fusion Method Based on Millimeter-Wave Radar and Camera
title_sort study on multi heterogeneous sensor data fusion method based on millimeter wave radar and camera
topic autonomous vehicle
sensor fusion
uncertainty
perception sensors
camera
radar
url https://www.mdpi.com/1424-8220/23/13/6044
work_keys_str_mv AT jianyuduan studyonmultiheterogeneoussensordatafusionmethodbasedonmillimeterwaveradarandcamera