A Machine Vision System for Lane-Departure Detection

Lee, Joon Woong

doi:10.1006/cviu.2002.0958

Cited by 131 publications

(71 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We first merge any contour fragments whose union produces a smooth curve (i.e. does not introduce discontinuities or high curvature); unlike other methods (Lee 2002;Lee and Yi 2005;Kang and Jung 2003), we do not enforce straight line constraints. Next, we fit parabolic arcs to the merged curves and recursively break them at points of high deviation.…”

Section: Road Paint From Symmetric Contoursmentioning

confidence: 99%

Finding multiple lanes in urban road networks with vision and lidar

et al. 2009

View full text Add to dashboard Cite

This paper describes a system for detecting and estimating the properties of multiple travel lanes in an urban road network from calibrated video imagery and laser range data acquired by a moving vehicle. The system operates in real-time in several stages on multiple processors, fusing detected road markings, obstacles, and curbs into a stable non-parametric estimate of nearby travel lanes. The system incorporates elements of a provided piecewise-linear road network as a weak prior.Our method is notable in several respects: it detects and estimates multiple travel lanes; it fuses asynchronous, heterogeneous sensor streams; it handles high-curvature roads; and it makes no assumption about the position or orientation of the vehicle with respect to the road.We analyze the system's performance in the context of the 2007 DARPA Urban Challenge. With five cameras and thirteen lidars, our method was incorporated into a closedloop controller to successfully guide an autonomous vehicle through a 90 km urban course at speeds up to 40 km/h amidst moving traffic.

show abstract

Section: Road Paint From Symmetric Contoursmentioning

confidence: 99%

Finding multiple lanes in urban road networks with vision and lidar

et al. 2009

View full text Add to dashboard Cite

show abstract

“…Like Kreucher, the range of approximation by the model is narrow and the problems of low accuracy approximation remain. Lee (2002) proposed approximating the shape with a linear model or a polygonal line model and estimating parameters with Hough transform. Although this method requires no assumption of the number of white lines to detect, detection accuracy decreases for curved white lines that are difficult to approximate with straight lines.…”

Section: Introductionmentioning

confidence: 99%

Edge filter for road white-line detection using brightness gradient approximation by discrete values

Furushou

Mouri

2017

JAMDSM

View full text Add to dashboard Cite

We propose an edge filter for road white-line detection. Many methods for white-line detection have been proposed for standardized roads. These methods are composed of two stages of processing, i.e., edge detection on an image taken with a camera and then extraction of edge clusters of white-line contours by model fitting. It is difficult to apply these methods to non-standardized roads of for which modeling are difficult. To expand the scope of white-line detection to common roads in the future, it is necessary to achieve processing through clustering without models. However, while clustering can apply to diverse contour lines, there is concern about degrading noise reduction that has so far been done by model fitting. In this study, for the first-stage processing, we developed an edge filter that utilizes the characteristics of white-line contours and detects noise correctly. This filter uses brightness-gradient approximation by discrete values, for which we obtained an idea for a non-linear filter that approximates a low-pass filter plus differential calculus. By applying the method to the images taken by on-board camera, we demonstrate that white-line detection that can apply to diverse road environments but is hardly affected by noise can be realized through combination with model-less clustering.

show abstract

“…Although people enjoy the convenience of the automobiles, we are also facing serious traffic problems and traffic accidents occurring frequently at the same time. In recent years, automatic detection of lane-departure has attracted much attention because many traffic accident fatalities are related to unintended lane-departures [1]. Countries all over the world are actively researching and developing the vehicle safety assistant.…”

Section: Introductionmentioning

confidence: 99%

Research on the Algorithms of Lane Recognition based on Machine Vision

Niu¹,

Zhang²,

Li³

2015

IJIES

View full text Add to dashboard Cite

Lane recognition is a kind of technology which can reconstruct either continuous or discontinuous lanes in the driving region into the continuous curves from the images of the road containing the lane markings. It is the basis and prerequisite for the whole lane departure warning system and the key technology in intelligent traffic safety assistant driving now. Generally speaking, the road images which the camera captures are processed by three steps: image preprocessing, image threshold segment and lane recognition. This paper proposed an efficient system to detect the lanes and mainly made experimental research on the images simulation of the three kinds of algorithms of the threshold segment and used the principle of Hough Transform in the lane recognition. Finally, the relatively efficient and accurate lane recognition processing algorithm was obtained according to the experimental results. Undoubtedly, this would lay a theoretical foundation for putting lane detection algorithm into practical application.

show abstract

A Machine Vision System for Lane-Departure Detection

Cited by 131 publications

References 11 publications

Finding multiple lanes in urban road networks with vision and lidar

Finding multiple lanes in urban road networks with vision and lidar

Edge filter for road white-line detection using brightness gradient approximation by discrete values

Research on the Algorithms of Lane Recognition based on Machine Vision

Contact Info

Product

Resources

About