CNN‐based estimation of heading direction of vehicle using automotive radar sensor
Abstract Modern autonomous vehicles are being equipped with various automotive sensors to perform special functions. Especially, it is important to predict the heading direction of the front vehicle to adjust the speed of the ego‐vehicle and select appropriate actions. Here, we propose a method for...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-06-01
|
| Series: | IET Radar, Sonar & Navigation |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/rsn2.12084 |
| _version_ | 1811209693895327744 |
|---|---|
| author | Sohee Lim Jaehoon Jung Byeong‐ho Lee Seong‐Cheol Kim Seongwook Lee |
| author_facet | Sohee Lim Jaehoon Jung Byeong‐ho Lee Seong‐Cheol Kim Seongwook Lee |
| author_sort | Sohee Lim |
| collection | DOAJ |
| description | Abstract Modern autonomous vehicles are being equipped with various automotive sensors to perform special functions. Especially, it is important to predict the heading direction of the front vehicle to adjust the speed of the ego‐vehicle and select appropriate actions. Here, we propose a method for estimating the instantaneous heading direction of a vehicle using automotive radar sensor data. First, using a frequency‐modulated continuous wave (FMCW) radar in the 77 GHz band, we accumulate the automotive radar sensor data for different movements of the front vehicle (e.g., stop, going ahead, reversing, turning left, and turning right). To distinguish the different movements of the vehicle, we use the convolutional neural network (CNN) and train it using the acquired radar sensor data. Because the CNN algorithm usually uses image data as input, it is essential to convert radar sensor data into image data. Therefore, we apply a high‐resolution angle estimation algorithm to the obtained radar data and convert it into a two‐dimensional range map. After the CNN model is trained with the obtained radar sensor data, various movements of the front vehicle can be classified with over 94% of accuracy. |
| first_indexed | 2024-04-12T04:43:46Z |
| format | Article |
| id | doaj.art-9a5922fede714d5983eab8ff3b830c9a |
| institution | Directory Open Access Journal |
| issn | 1751-8784 1751-8792 |
| language | English |
| last_indexed | 2024-04-12T04:43:46Z |
| publishDate | 2021-06-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Radar, Sonar & Navigation |
| spelling | doaj.art-9a5922fede714d5983eab8ff3b830c9a2022-12-22T03:47:33ZengWileyIET Radar, Sonar & Navigation1751-87841751-87922021-06-0115661862610.1049/rsn2.12084CNN‐based estimation of heading direction of vehicle using automotive radar sensorSohee Lim0Jaehoon Jung1Byeong‐ho Lee2Seong‐Cheol Kim3Seongwook Lee4Department of Electrical and Computer Engineering and Institute of New Media & Communications (INMC) College of Engineering Seoul National University (SNU) Seoul Republic of KoreaDepartment of Electrical and Computer Engineering and Institute of New Media & Communications (INMC) College of Engineering Seoul National University (SNU) Seoul Republic of KoreaDepartment of Electrical and Computer Engineering and Institute of New Media & Communications (INMC) College of Engineering Seoul National University (SNU) Seoul Republic of KoreaDepartment of Electrical and Computer Engineering and Institute of New Media & Communications (INMC) College of Engineering Seoul National University (SNU) Seoul Republic of KoreaSchool of Electronics and Information Engineering College of Engineering Korea Aerospace University Gyeonggi‐do Republic of KoreaAbstract Modern autonomous vehicles are being equipped with various automotive sensors to perform special functions. Especially, it is important to predict the heading direction of the front vehicle to adjust the speed of the ego‐vehicle and select appropriate actions. Here, we propose a method for estimating the instantaneous heading direction of a vehicle using automotive radar sensor data. First, using a frequency‐modulated continuous wave (FMCW) radar in the 77 GHz band, we accumulate the automotive radar sensor data for different movements of the front vehicle (e.g., stop, going ahead, reversing, turning left, and turning right). To distinguish the different movements of the vehicle, we use the convolutional neural network (CNN) and train it using the acquired radar sensor data. Because the CNN algorithm usually uses image data as input, it is essential to convert radar sensor data into image data. Therefore, we apply a high‐resolution angle estimation algorithm to the obtained radar data and convert it into a two‐dimensional range map. After the CNN model is trained with the obtained radar sensor data, various movements of the front vehicle can be classified with over 94% of accuracy.https://doi.org/10.1049/rsn2.12084CW radarFM radarimage resolutionradar signal processingroad vehicle radarsensors |
| spellingShingle | Sohee Lim Jaehoon Jung Byeong‐ho Lee Seong‐Cheol Kim Seongwook Lee CNN‐based estimation of heading direction of vehicle using automotive radar sensor IET Radar, Sonar & Navigation CW radar FM radar image resolution radar signal processing road vehicle radar sensors |
| title | CNN‐based estimation of heading direction of vehicle using automotive radar sensor |
| title_full | CNN‐based estimation of heading direction of vehicle using automotive radar sensor |
| title_fullStr | CNN‐based estimation of heading direction of vehicle using automotive radar sensor |
| title_full_unstemmed | CNN‐based estimation of heading direction of vehicle using automotive radar sensor |
| title_short | CNN‐based estimation of heading direction of vehicle using automotive radar sensor |
| title_sort | cnn based estimation of heading direction of vehicle using automotive radar sensor |
| topic | CW radar FM radar image resolution radar signal processing road vehicle radar sensors |
| url | https://doi.org/10.1049/rsn2.12084 |
| work_keys_str_mv | AT soheelim cnnbasedestimationofheadingdirectionofvehicleusingautomotiveradarsensor AT jaehoonjung cnnbasedestimationofheadingdirectionofvehicleusingautomotiveradarsensor AT byeongholee cnnbasedestimationofheadingdirectionofvehicleusingautomotiveradarsensor AT seongcheolkim cnnbasedestimationofheadingdirectionofvehicleusingautomotiveradarsensor AT seongwooklee cnnbasedestimationofheadingdirectionofvehicleusingautomotiveradarsensor |