Robust lane markings detection and road geometry computation

López, Antonio; Serrat, Joan; Cañero, C.; Lumbreras, Felipe; Graf, T.

doi:10.1007/s12239-010-0049-6

Cited by 96 publications

(48 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Geo-referenced imagery from digital cameras on MM vehicles were proposed for the detection of lane markings (López et al, 2010), and/or for the extraction of information to support road inventory activities (de Frutos and Castro, 2014). The level of accuracy attainable using these systems can range from centimeters to meters, depending on the technology used and the quality of the output signal.…”

Section: Related Workmentioning

confidence: 99%

Mobile mapping systems and spatial data collection strategies assessment in the identification of horizontal alignment of highways

Marinelli

Bassani

Piras

et al. 2017

Transportation Research Part C: Emerging Technologies

View full text Add to dashboard Cite

The horizontal alignment of existing highways may be identified by using several terrestrial or aerial geomatics technologies. Such technologies involve different levels of precision and accuracy; hence, different results can be expected. At present, there are no comparisons available between the solutions resulting from the use of different technologies and data sources for the same road alignment.In this investigation, a number of terrestrial mobile mapping techniques and data collection strategies were evaluated. The centerline of a 3.6 km section of a highway was used to estimate radii, centers of curvature and orientation of tangents. Two statistical fitting methods were used to back-calculate these parameters, and the results were then compared with as-built alignment data.Terrestrial images from a mobile mapping vehicle were used to determine the centerline, which was also estimated as the average line of the carriageway and pavement edges, and as the average line of the two driving trajectories. Positions were surveyed using low-cost sensors (an integrated GPS-IMU platform, HD webcam). For comparison purposes, aerial orthophotos and a GNSS (high-cost) receiver were used simultaneously. Although the GPS-IMU data and estimated trajectories provided results comparable to those of the GNSS receiver, the use of georeferenced images proved less accurate. The results and comments in the paper should be of use to survey practitioners when they need to select an acquisition methodology appropriate to the desired level of accuracy and in line with budget constraints.

show abstract

Section: Related Workmentioning

confidence: 99%

Mobile mapping systems and spatial data collection strategies assessment in the identification of horizontal alignment of highways

Marinelli

Bassani

Piras

et al. 2017

Transportation Research Part C: Emerging Technologies

View full text Add to dashboard Cite

show abstract

“…Many studies of lane marking detection have been carried out, some of which using RANSAC [4,6] or the Hough transform. In this paper, the Hough transform was used to detect the lane markings.…”

Section: Lane Recognition Based On Hough Transformmentioning

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

“…The line model has been utilized most widely in the existing lane detection systems [14,15] because it combines parallel line and planar ground surface constraints, which are suitable for most of the freeway applications. In addition, the model requires lesser parameters which lead to more accurate and faster parameter estimation.…”

Section: Analysis For Lane Modelingmentioning

confidence: 99%

“…(12). (12) The mean intensity value of the pixel assigned to class   is Lane Detection Algorithm for Night-time Digital Image Based on Distribution Feature … -Feng You et al 193 (13) Similarly, the mean intensity value of the pixel assigned to class   is (14) The cumulative mean up to level  is given by (15) And the average intensity of the entire image is given by (16) In order to evaluate the 'goodness' of the threshold at level  we use the normalized and dimensionless metric (17) Where    is the global variance (18) And    is the between-class variance, defined as …”

Section: Thresholding Based On Maximum Entropymentioning

confidence: 99%

Lane Detection Algorithm for Night-time Digital Image Based on Distribution Feature of Boundary Pixels

Feng¹,

Zhang²,

Zhong³

et al. 2013

Journal of the Optical Society of Korea

View full text Add to dashboard Cite

This paper presents a novel algorithm for nighttime detection of the lane markers painted on a road at night. First of all, the proposed algorithm uses neighborhood average filtering, 8-directional Sobel operator and thresholding segmentation based on OTSU's to handle raw lane images taken from a digital CCD camera. Secondly, combining intensity map and gradient map, we analyze the distribution features of pixels on boundaries of lanes in the nighttime and construct 4 feature sets for these points, which are helpful to supply with sufficient data related to lane boundaries to detect lane markers much more robustly. Then, the searching method in multiple directions-horizontal, vertical and diagonal directions, is conducted to eliminate the noise points on lane boundaries. Adapted Hough transformation is utilized to obtain the feature parameters related to the lane edge. The proposed algorithm can not only significantly improve detection performance for the lane marker, but it requires less computational power. Finally, the algorithm is proved to be reliable and robust in lane detection in a nighttime scenario.

show abstract

Robust lane markings detection and road geometry computation

Cited by 96 publications

References 13 publications

Mobile mapping systems and spatial data collection strategies assessment in the identification of horizontal alignment of highways

Mobile mapping systems and spatial data collection strategies assessment in the identification of horizontal alignment of highways

Research on the Algorithms of Lane Recognition based on Machine Vision

Lane Detection Algorithm for Night-time Digital Image Based on Distribution Feature of Boundary Pixels

Contact Info

Product

Resources

About