Video-Based Lane Estimation and Tracking for Driver Assistance: Survey, System, and Evaluation

Abstract

Abstract-Driver-assistance systems that monitor driver intent, warn drivers of lane departures, or assist in vehicle guidance are all being actively considered. It is therefore important to take a critical look at key aspects of these systems, one of which is lane-position tracking. It is for these driver-assistance objectives that motivate the development of the novel "video-based lane estimation and tracking" (VioLET) system. The system is designed using steerable filters for robust and accurate lane-marking detection. Steerable filters provide an efficient method for detecting circular-reflector markings, solid-line markings, and segmented-line markings under varying lighting and road conditions. They help in providing robustness to complex shadowing, lighting changes from overpasses and tunnels, and road-surface variations. They are efficient for lane-marking extraction because by computing only three separable convolutions, we can extract a wide variety of lane markings. Curvature detection is made more robust by incorporating both visual cues (lane markings and lane texture) and vehicle-state information. The experiment design and evaluation of the VioLET system is shown using multiple quantitative metrics over a wide variety of test conditions on a large test path using a unique instrumented vehicle. A justification for the choice of metrics based on a previous study with human-factors applications as well as extensive ground-truth testing from different times of day, road conditions, weather, and driving scenarios is also presented. In order to design the VioLET system, an up-to-date and comprehensive analysis of the current state of the art in lane-detection research was first performed. In doing so, a comparison of a wide variety of methods, pointing out the similarities and differences between methods as well as when and where various methods are most useful, is presented.

Finding multiple lanes in urban road networks with vision and lidar

“…McCall and Trivedi provide an excellent survey (McCall and Trivedi 2006). Lane-finding systems intended to support autonomous operation have typically focused on highway driving (Dickmanns and Mysliwetz 1992;Thorpe et al 1988), where roads have low curvature and prominent lane markings, rather than on urban environments.…”

“…Finally, lanes are estimated and tracked over time, influenced by curvature constraints and priors generated from map data if available Although state information could be tracked over time and transferred between frames to assist extraction and curve fitting, we kept the approach stateless since the higher-level lane fusion and tracking stages perform both spatial and temporal filtering in local coordinates. We also eliminate substantial computational expense by operating directly on raw camera images rather than on inverse-perspective corrected images (McCall and Trivedi 2006;Kim 2008), while still reaping the benefits of calibrated cameras and realworld measurements.…”

“…We chose the support so that double-yellow lines in the center of the road are detected successfully. Our matched filter approach is similar to that of McCall and Trivedi, who used steerable filters (McCall and Trivedi 2006). Our fixed vertical and horizontal kernels are approximations that have the advantage of executing faster and the disadvantage of being less sensitive to certain line orientations.…”

Pedestrian Detection for Android Mobile Devices

“…Pedestrian detection can be defined as whether the picture contains pedestrians, if there are pedestrians we will give location information, it is the first step in the processing of driver assistance [1], intelligent video surveillance and analysis of human behavior [2] and so on. In recent years, the pedestrian detection is also used in aerial images, victims of rescue and other emerging areas.…”

Stable Road Lane Model Based on Clothoids

“…By using the Distillation Algorithm to track the vehicles pose relative to the road and their width, the system seems to be stable in situations that are critical for vision-based lane trackers. A comparison of lane position detection and tracking techniques is presented in [4]. One of the methods listed is described in detail in [5].…”