2016
DOI: 10.1109/tip.2016.2539683
|View full text |Cite
|
Sign up to set email alerts
|

Comprehensive and Practical Vision System for Self-Driving Vehicle Lane-Level Localization

Abstract: Vehicle lane-level localization is a fundamental technology in autonomous driving. To achieve accurate and consistent performance, a common approach is to use the LIDAR technology. However, it is expensive and computational demanding, and thus not a practical solution in many situations. This paper proposes a stereovision system, which is of low cost, yet also able to achieve high accuracy and consistency. It integrates a new lane line detection algorithm with other lane marking detectors to effectively identi… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
5

Citation Types

0
39
0

Year Published

2017
2017
2024
2024

Publication Types

Select...
6

Relationship

1
5

Authors

Journals

citations
Cited by 65 publications
(39 citation statements)
references
References 41 publications
0
39
0
Order By: Relevance
“…As summarized in the survey paper by Hillel et al in [68], most of the lane line detection algorithms share three common steps: (1) lane line feature extraction, by edge detection [76,77] and color [78,79], by learning algorithms such as SVM [80], or by boost classification [81,82]; (2) fitting the pixels into different models, e.g., straight lines [83,84], parabolas [85,86], hyperbolas [87][88][89], and even zigzag line [90]; (3) estimating the vehicle pose based on the fitted model. A fourth time integration step may exist before the vehicle pose estimation in order to impose temporal continuity, where the detection result in the current frame is used to guide the next search through filter mechanisms, such as Kalman filter [76,91] and particle filter [80,90,92].…”
Section: Lane Line Marking Detectionmentioning
confidence: 99%
See 4 more Smart Citations
“…As summarized in the survey paper by Hillel et al in [68], most of the lane line detection algorithms share three common steps: (1) lane line feature extraction, by edge detection [76,77] and color [78,79], by learning algorithms such as SVM [80], or by boost classification [81,82]; (2) fitting the pixels into different models, e.g., straight lines [83,84], parabolas [85,86], hyperbolas [87][88][89], and even zigzag line [90]; (3) estimating the vehicle pose based on the fitted model. A fourth time integration step may exist before the vehicle pose estimation in order to impose temporal continuity, where the detection result in the current frame is used to guide the next search through filter mechanisms, such as Kalman filter [76,91] and particle filter [80,90,92].…”
Section: Lane Line Marking Detectionmentioning
confidence: 99%
“…A fourth time integration step may exist before the vehicle pose estimation in order to impose temporal continuity, where the detection result in the current frame is used to guide the next search through filter mechanisms, such as Kalman filter [76,91] and particle filter [80,90,92].…”
Section: Lane Line Marking Detectionmentioning
confidence: 99%
See 3 more Smart Citations