Research of Target Detection and Classification Techniques Using Millimeter-Wave Radar and Vision Sensors
The development of autonomous vehicles and unmanned aerial vehicles has led to a current research focus on improving the environmental perception of automation equipment. The unmanned platform detects its surroundings and then makes a decision based on environmental information. The major challenge...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-03-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/13/6/1064 |
_version_ | 1797541765425659904 |
---|---|
author | Zhangjing Wang Xianhan Miao Zhen Huang Haoran Luo |
author_facet | Zhangjing Wang Xianhan Miao Zhen Huang Haoran Luo |
author_sort | Zhangjing Wang |
collection | DOAJ |
description | The development of autonomous vehicles and unmanned aerial vehicles has led to a current research focus on improving the environmental perception of automation equipment. The unmanned platform detects its surroundings and then makes a decision based on environmental information. The major challenge of environmental perception is to detect and classify objects precisely; thus, it is necessary to perform fusion of different heterogeneous data to achieve complementary advantages. In this paper, a robust object detection and classification algorithm based on millimeter-wave (MMW) radar and camera fusion is proposed. The corresponding regions of interest (ROIs) are accurately calculated from the approximate position of the target detected by radar and cameras. A joint classification network is used to extract micro-Doppler features from the time-frequency spectrum and texture features from images in the ROIs. A fusion dataset between radar and camera is established using a fusion data acquisition platform and includes intersections, highways, roads, and playgrounds in schools during the day and at night. The traditional radar signal algorithm, the Faster R-CNN model and our proposed fusion network model, called RCF-Faster R-CNN, are evaluated in this dataset. The experimental results indicate that the mAP(mean Average Precision) of our network is up to 89.42% more accurate than the traditional radar signal algorithm and up to 32.76% higher than Faster R-CNN, especially in the environment of low light and strong electromagnetic clutter. |
first_indexed | 2024-03-10T13:20:22Z |
format | Article |
id | doaj.art-764f6292c6ae474985b1d29ed8d14b5e |
institution | Directory Open Access Journal |
issn | 2072-4292 |
language | English |
last_indexed | 2024-03-10T13:20:22Z |
publishDate | 2021-03-01 |
publisher | MDPI AG |
record_format | Article |
series | Remote Sensing |
spelling | doaj.art-764f6292c6ae474985b1d29ed8d14b5e2023-11-21T10:03:28ZengMDPI AGRemote Sensing2072-42922021-03-01136106410.3390/rs13061064Research of Target Detection and Classification Techniques Using Millimeter-Wave Radar and Vision SensorsZhangjing Wang0Xianhan Miao1Zhen Huang2Haoran Luo3School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaThe development of autonomous vehicles and unmanned aerial vehicles has led to a current research focus on improving the environmental perception of automation equipment. The unmanned platform detects its surroundings and then makes a decision based on environmental information. The major challenge of environmental perception is to detect and classify objects precisely; thus, it is necessary to perform fusion of different heterogeneous data to achieve complementary advantages. In this paper, a robust object detection and classification algorithm based on millimeter-wave (MMW) radar and camera fusion is proposed. The corresponding regions of interest (ROIs) are accurately calculated from the approximate position of the target detected by radar and cameras. A joint classification network is used to extract micro-Doppler features from the time-frequency spectrum and texture features from images in the ROIs. A fusion dataset between radar and camera is established using a fusion data acquisition platform and includes intersections, highways, roads, and playgrounds in schools during the day and at night. The traditional radar signal algorithm, the Faster R-CNN model and our proposed fusion network model, called RCF-Faster R-CNN, are evaluated in this dataset. The experimental results indicate that the mAP(mean Average Precision) of our network is up to 89.42% more accurate than the traditional radar signal algorithm and up to 32.76% higher than Faster R-CNN, especially in the environment of low light and strong electromagnetic clutter.https://www.mdpi.com/2072-4292/13/6/1064target trackingmillimeter-wave radarmicro Dopplertime-frequency analysisinformation fusion |
spellingShingle | Zhangjing Wang Xianhan Miao Zhen Huang Haoran Luo Research of Target Detection and Classification Techniques Using Millimeter-Wave Radar and Vision Sensors Remote Sensing target tracking millimeter-wave radar micro Doppler time-frequency analysis information fusion |
title | Research of Target Detection and Classification Techniques Using Millimeter-Wave Radar and Vision Sensors |
title_full | Research of Target Detection and Classification Techniques Using Millimeter-Wave Radar and Vision Sensors |
title_fullStr | Research of Target Detection and Classification Techniques Using Millimeter-Wave Radar and Vision Sensors |
title_full_unstemmed | Research of Target Detection and Classification Techniques Using Millimeter-Wave Radar and Vision Sensors |
title_short | Research of Target Detection and Classification Techniques Using Millimeter-Wave Radar and Vision Sensors |
title_sort | research of target detection and classification techniques using millimeter wave radar and vision sensors |
topic | target tracking millimeter-wave radar micro Doppler time-frequency analysis information fusion |
url | https://www.mdpi.com/2072-4292/13/6/1064 |
work_keys_str_mv | AT zhangjingwang researchoftargetdetectionandclassificationtechniquesusingmillimeterwaveradarandvisionsensors AT xianhanmiao researchoftargetdetectionandclassificationtechniquesusingmillimeterwaveradarandvisionsensors AT zhenhuang researchoftargetdetectionandclassificationtechniquesusingmillimeterwaveradarandvisionsensors AT haoranluo researchoftargetdetectionandclassificationtechniquesusingmillimeterwaveradarandvisionsensors |