Adaptative Road Lanes Detection and Classification

Abstract

Abstract. This paper presents a Road Detection and Classification algorithm for Driver Assistance Systems (DAS), which tracks several road lanes and identifies the type of lane boundaries. The algorithm uses an edge filter to extract the longitudinal road markings to which a straight lane model is fitted. Next, the type of right and left lane boundaries (continuous, broken or merge line) is identified using a Fourier analysis. Adjacent lanes are searched when broken or merge lines are detected. Although the knowledge of the line type is essential for a robust DAS, it has been seldom considered in previous works. This knowledge helps to guide the search for other lanes, and it is the basis to identify the type of road (one-way, two-way or freeway), as well as to tell the difference between allowed and forbidden maneuvers, such as crossing a continuous line.

A featureless and stochastic approach to on-board stereo vision system pose

“…For instance, (a) a road with a constant width is assumed [13,12]; (b) the car is driven along two parallel lane markings, which are projected to the left and to the right of the image [25]; (c) after an initial calibration process the camera's position and pitch angle remain constant through the time [28]; to mention a few.…”

Automatic Detection and Classification of Road Lane Markings Using Onboard Vehicular Cameras

“…In [9] (as cited in [10]), Collado et al split the problem into a few steps: to create a birds-eye view of the road, to segment the pixels which belong to longitudinal road markings, to extract the lane boundaries using the Hough Transform, and to realize adjustments in the pitch angle. Then, lane boundaries are classified as continuous (also called solid or single-solid), broken (known as dashed) or merged, computed by the power spectrum of the FFT.…”

Lane Characterization Under Challenging Scenarios for Autonomous Driving System

“…Dashed lanes exhibit a periodic pattern and the periodicity varies based on speed of the vehicle and then gap between the dashes. In contrast to the auto regression and frequency domain based techniques, which are computationally complex [4], here we propose a statistical analysis based technique. StartPointDistance for the previous 'N' frames are analysed to determine the zero crossings with respect to ZeroReference.…”

“…Lee et al [12] proposed a method to detect lane color using support vector machine. However, the classifier based methods for lane type [5], [6], [7] are highly data dependent and computationally intensive and histogram methods [4] face issues in curvy road scenarios. Color segmentation methods for lane color [9], [10] suffer during illumination variations and image sensor settings which are very common in autonomous driving environment.…”

“…Several lane detection algorithms are proposed based on low level features such as edge and curve fitting [2], shape and structure of lane [3], histogram based [4] and lane models [2]. Performance of the lane detection algorithms vary based on the image quality and illumination levels.…”