Book ChapterDOI
Lane Detection for a Situation Adaptive Lane keeping Support System, the SAFELANE System
Nikolaus Dipl.-Ing. Möhler,Dietrich Dipl.-Inf. John,Marina Voigtländer +2 more
- pp 485-500
Reads0
Chats0
TLDR
A new approach for getting an initial lane model is introduced which can be dynamically adapted from map and positioning data and the detection is extended to the neighbour lanes and a lane markings type classifying component is added.Abstract:
The goal of the SAFELANE project is to develop a situation-adaptive system for enhanced lane keeping support. A prerequisite for lane keeping is reliable information of the vehicle environment. Especially the vehicle position within the lane and the course of the road ahead is important. This information is provided by the lane detection component. The lane tracker is mainly vision based but it is also supplemented by map, positioning and vehicle data. A high dynamic range camera provides the processing unit with image data. Measurement points of lane borders, calculated by a robust edge detection algorithm, are used to estimate a 3D clothoid model of the lane. A new approach for getting an initial lane model is introduced which can be dynamically adapted from map and positioning data. The detection is extended to the neighbour lanes and a lane markings type classifying component is added.read more
Citations
More filters
Journal ArticleDOI
A Situation-Adaptive Lane-Keeping Support System: Overview of the SAFELANE Approach
Angelos Amditis,Matthaios Bimpas,George Thomaidis,M. Tsogas,Mariana Netto,Said Mammar,A Beutner,N Möhler,T Wirthgen,S Zipser,A. Etemad,M. Da Lio,R Cicilloni +12 more
TL;DR: In this paper, the presented system design is divided into three layers: the perception layer, which is responsible for the environment perception, and the decision and action layers, which are responsible for evaluating and executing actions, respectively.
Journal ArticleDOI
Map-Enhanced Ego-Lane Detection in the Missing Feature Scenarios
TL;DR: Li et al. as discussed by the authors exploited prior knowledge contained in digital maps, which has a strong capability to enhance the performance of detection algorithms, and employed the road shape extracted from OpenStreetMap as lane model, which is highly consistent with the real lane shape and irrelevant to lane features.
Posted Content
Map-Enhanced Ego-Lane Detection in the Missing Feature Scenarios
TL;DR: The road shape extracted from OpenStreetMap is used as lane model, which is highly consistent with the real lane shape and irrelevant to lane features, and a search-based optimization algorithm is proposed, which achieves state-of-the-art performance.
Journal ArticleDOI
Toward Self-Referential Autonomous Learning of Object and Situation Models
TL;DR: A detailed description of a system architecture for self-referential autonomous learning which enables the refinement of object and situation models during operation in order to optimize behavior.
Proceedings ArticleDOI
Learning robust driving policies without online exploration
TL;DR: In this paper, a multi-time-scale predictive representation learning method is proposed to efficiently learn robust driving policies in an offline manner that generalize well to novel road geometries, and damaged and distracting lane conditions which are not covered in the offline training data.
References
More filters
Book
introduction to random signals and applied kalman filtering
TL;DR: In this paper, the Discrete Kalman Filter (DFL) is used for smoothing and prediction linearization in the Global Positioning System (GPS) and a case study is presented.
Journal ArticleDOI
Recursive 3-D road and relative ego-state recognition
E.D. Dickmanns,B.D. Mysliwetz +1 more
TL;DR: The general problem of recognizing both horizontal and vertical road curvature parameters while driving along the road has been solved recursively and a differential geometry representation decoupled for the two curvature components has been selected.
Robust lane recognition embedded in a real-time driver assistance system
TL;DR: A robust automatic lane detection approach which is part of a real-time driver assistance system that detects marked as well as unmarked lane borders and was shown to perform well under different traffic and weather conditions.