Dataset Information

Lane-Level Map-Matching Method for Vehicle Localization Using GPS and Camera on a High-Definition Map.

ABSTRACT: Accurate vehicle localization is important for autonomous driving and advanced driver assistance systems. Existing precise localization systems based on the global navigation satellite system cannot always provide lane-level accuracy even in open-sky environments. Map-based localization using high-definition (HD) maps is an interesting method for achieving greater accuracy. We propose a map-based localization method using a single camera. Our method relies on road link information in the HD map to achieve lane-level accuracy. Initially, we process the image-acquired using the camera of a mobile device-via inverse perspective mapping, which shows the entire road at a glance in the driving image. Subsequently, we use the Hough transform to detect the vehicle lines and acquire driving link information regarding the lane on which the vehicle is moving. The vehicle position is estimated by matching the global positioning system (GPS) and reference HD map. We employ iterative closest point-based map-matching to determine and eliminate the disparity between the GPS trajectories and reference map. Finally, we perform experiments by considering the data of a sophisticated GPS/inertial navigation system as the ground truth and demonstrate that the proposed method provides lane-level position accuracy for vehicle localization.

SUBMITTER: Kang JM

PROVIDER: S-EPMC7218736 | biostudies-literature | 2020 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Lane-Level Map-Matching Method for Vehicle Localization Using GPS and Camera on a High-Definition Map.

Kang Jeong Min JM Yoon Tae Sung TS Kim Euntai E Park Jin Bae JB

Sensors (Basel, Switzerland) 20200411 8

Accurate vehicle localization is important for autonomous driving and advanced driver assistance systems. Existing precise localization systems based on the global navigation satellite system cannot always provide lane-level accuracy even in open-sky environments. Map-based localization using high-definition (HD) maps is an interesting method for achieving greater accuracy. We propose a map-based localization method using a single camera. Our method relies on road link information in the HD map ...[more]

PMID: 32290441

Similar Datasets

Project description:The purpose of this study is to reveal the response of multi Lane pre disintegrated carbonaceous mudstone embankment under vehicle dynamic load. In this paper, the pre-disintegrated carbonaceous mudstone samples whose fractal dimension meets the requirements are obtained through the indoor disintegration test of carbonaceous mudstone. Geotechnical basic tests such as particle analysis experiments, compaction tests, and direct shear tests were carried out on the pre-disintegrated carbonaceous mudstone samples, and the physical and mechanical parameters of the pre-disintegrated carbonaceous mudstone were obtained. On this basis, a two-way 4-lane pre-disintegration carbonaceous mudstone embankment model of the expressway was established by ABAQUS numerical software. Three different working conditions are set up to study the dynamic response of multi-lane pre-disintegrated carbonaceous mudstone embankment under vehicle load. The results show that the stress change trend on the surface of the pre-disintegrated carbonaceous mudstone embankment without vehicles is the same as that on the side with vehicles. Under this condition, the vertical displacement of the pre-disintegrated carbonaceous mudstone embankment surface can be as high as 4.33mm, and the vertical displacement change of the embankment in the 0-0.6s phase is basically the same as the stress amplitude distribution. When a traffic jam occurs on one side, the maximum increase in vertical stress on the surface of the embankment on the normal driving side is about 170 kPa compared to condition one, and the vertical displacement at each depth of the embankment has been significantly increased. When a traffic jam occurs on one side, it can significantly increase the vertical stress on the surface of the pre-disintegrated carbonaceous mudstone embankment in this lane. The middle part of the stress time curve of monitoring points 3 and 4 in working condition three is more stable and significant than in working condition one, and the maximum vertical displacement is increased by about 1.70mm. The research results can reference the stability analysis of carbonaceous mudstone embankments and engineering practice.

Dataset Information

Lane-Level Map-Matching Method for Vehicle Localization Using GPS and Camera on a High-Definition Map.

Publications

Lane-Level Map-Matching Method for Vehicle Localization Using GPS and Camera on a High-Definition Map.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets