Lane Endpoint Detection and Position Accuracy Evaluation for Sensor Fusion-Based Vehicle Localization on Highways
Landmark-based vehicle localization is a key component of both autonomous driving and advanced driver assistance systems (ADAS). Previously used landmarks in highways such as lane markings lack information on longitudinal positions. To address this problem, lane endpoints can be used as landmarks. T...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2018-12-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/18/12/4389 |
id |
doaj-101572a72b6144668f6390c98d5d42ec |
---|---|
record_format |
Article |
spelling |
doaj-101572a72b6144668f6390c98d5d42ec2020-11-24T20:42:56ZengMDPI AGSensors1424-82202018-12-011812438910.3390/s18124389s18124389Lane Endpoint Detection and Position Accuracy Evaluation for Sensor Fusion-Based Vehicle Localization on HighwaysEun Seok Jang0Jae Kyu Suhr1Ho Gi Jung2Department of Electronic Engineering, Korea National University of Transportation, 50 Daehak-ro, Chungju-si, Chungbuk 27469, KoreaSchool of Intelligent Mechatronics Engineering, Sejong University, 209 Neungdong-ro, Gwangjin-gu, Seoul 05006, KoreaDepartment of Electronic Engineering, Korea National University of Transportation, 50 Daehak-ro, Chungju-si, Chungbuk 27469, KoreaLandmark-based vehicle localization is a key component of both autonomous driving and advanced driver assistance systems (ADAS). Previously used landmarks in highways such as lane markings lack information on longitudinal positions. To address this problem, lane endpoints can be used as landmarks. This paper proposes two essential components when using lane endpoints as landmarks: lane endpoint detection and its accuracy evaluation. First, it proposes a method to efficiently detect lane endpoints using a monocular forward-looking camera, which is the most widely installed perception sensor. Lane endpoints are detected with a small amount of computation based on the following steps: lane detection, lane endpoint candidate generation, and lane endpoint candidate verification. Second, it proposes a method to reliably measure the position accuracy of the lane endpoints detected from images taken while the camera is moving at high speed. A camera is installed with a mobile mapping system (MMS) in a vehicle, and the position accuracy of the lane endpoints detected by the camera is measured by comparing their positions with ground truths obtained by the MMS. In the experiment, the proposed methods were evaluated and compared with previous methods based on a dataset acquired while driving on 80 km of highway in both daytime and nighttime.https://www.mdpi.com/1424-8220/18/12/4389lane endpoint detectionposition accuracy evaluationvehicle localizationsensor fusionintelligent vehicle |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Eun Seok Jang Jae Kyu Suhr Ho Gi Jung |
spellingShingle |
Eun Seok Jang Jae Kyu Suhr Ho Gi Jung Lane Endpoint Detection and Position Accuracy Evaluation for Sensor Fusion-Based Vehicle Localization on Highways Sensors lane endpoint detection position accuracy evaluation vehicle localization sensor fusion intelligent vehicle |
author_facet |
Eun Seok Jang Jae Kyu Suhr Ho Gi Jung |
author_sort |
Eun Seok Jang |
title |
Lane Endpoint Detection and Position Accuracy Evaluation for Sensor Fusion-Based Vehicle Localization on Highways |
title_short |
Lane Endpoint Detection and Position Accuracy Evaluation for Sensor Fusion-Based Vehicle Localization on Highways |
title_full |
Lane Endpoint Detection and Position Accuracy Evaluation for Sensor Fusion-Based Vehicle Localization on Highways |
title_fullStr |
Lane Endpoint Detection and Position Accuracy Evaluation for Sensor Fusion-Based Vehicle Localization on Highways |
title_full_unstemmed |
Lane Endpoint Detection and Position Accuracy Evaluation for Sensor Fusion-Based Vehicle Localization on Highways |
title_sort |
lane endpoint detection and position accuracy evaluation for sensor fusion-based vehicle localization on highways |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2018-12-01 |
description |
Landmark-based vehicle localization is a key component of both autonomous driving and advanced driver assistance systems (ADAS). Previously used landmarks in highways such as lane markings lack information on longitudinal positions. To address this problem, lane endpoints can be used as landmarks. This paper proposes two essential components when using lane endpoints as landmarks: lane endpoint detection and its accuracy evaluation. First, it proposes a method to efficiently detect lane endpoints using a monocular forward-looking camera, which is the most widely installed perception sensor. Lane endpoints are detected with a small amount of computation based on the following steps: lane detection, lane endpoint candidate generation, and lane endpoint candidate verification. Second, it proposes a method to reliably measure the position accuracy of the lane endpoints detected from images taken while the camera is moving at high speed. A camera is installed with a mobile mapping system (MMS) in a vehicle, and the position accuracy of the lane endpoints detected by the camera is measured by comparing their positions with ground truths obtained by the MMS. In the experiment, the proposed methods were evaluated and compared with previous methods based on a dataset acquired while driving on 80 km of highway in both daytime and nighttime. |
topic |
lane endpoint detection position accuracy evaluation vehicle localization sensor fusion intelligent vehicle |
url |
https://www.mdpi.com/1424-8220/18/12/4389 |
work_keys_str_mv |
AT eunseokjang laneendpointdetectionandpositionaccuracyevaluationforsensorfusionbasedvehiclelocalizationonhighways AT jaekyusuhr laneendpointdetectionandpositionaccuracyevaluationforsensorfusionbasedvehiclelocalizationonhighways AT hogijung laneendpointdetectionandpositionaccuracyevaluationforsensorfusionbasedvehiclelocalizationonhighways |
_version_ |
1716821140702232576 |