2000
DOI: 10.1016/s0167-8655(00)00021-0
|View full text |Cite
|
Sign up to set email alerts
|

Lane detection using spline model

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
120
0
4

Year Published

2005
2005
2020
2020

Publication Types

Select...
4
3
2

Relationship

1
8

Authors

Journals

citations
Cited by 250 publications
(124 citation statements)
references
References 16 publications
0
120
0
4
Order By: Relevance
“…Computation can be largely simplified in special applications. Taking the lane detection as an example, the biological principles are to detect and recognize a line, which can work well even if the lanes are partly missing [62][63][64], as seen in Figure 6.…”
Section: Simulation and Discussionmentioning
confidence: 99%
“…Computation can be largely simplified in special applications. Taking the lane detection as an example, the biological principles are to detect and recognize a line, which can work well even if the lanes are partly missing [62][63][64], as seen in Figure 6.…”
Section: Simulation and Discussionmentioning
confidence: 99%
“…Finally and third, from each segment a feature vector is extracted, and a Support Vector Machine (SVM) classifier is employed to distinguish segments based on their geometric features. Since some background segments can have similar shapes as road markings, we model the lanes that appear in the image, using RANSAC and a Catmull-Rom spline [10] with the lane marking candidates classified by SVM. Many non-road marking segments can be rejected based on the lane positions and the orientation of the segments (the orientation should be consistent with the orientation of the lane markings).…”
Section: Road Marking Detection and Recognitionmentioning
confidence: 99%
“…For this purpose, we model lanes, based on lane marking candidates classified by the SVM. Since lanes can appear both straight and curved in the top-view image, two models are applied consecutively: RANSAC to model straight lanes and Catmull-Rom spline to interpolate curved lanes [10]. First, by default we search to fit a straight line using RANSAC.…”
Section: Lane Modelingmentioning
confidence: 99%
“…이어서, 밝고 어두운 영역의 평균 들의 차이로 노면의 상태를 판단하고, 노면의 상태에 따라 Canny 검출에 사용되는 파라미터의 값을 조절하여 에지를 검출한다 [4] . 획득한 에지 정보로부터 Hough 변환을 이용하 여 소실점을 구하고, 소실점 하부에 있는 영역을 6개로 분 할하여 Catmull Rom Spline 을 구한다 [5] . 본 논문의 특징은 Canny 검출 시 적용되는 파라미터 값을 Otsu 방법을 통하 여 환경 변화에 자동적으로 획득함으로써 환경 변화에 강 건한 에지 검출을 할 수 있도록 하는 것이다.…”
unclassified