Accurate Road Geometry Estimation for a Safe Speed Application

Abstract

In Europe, a considerable part of lives lost in traffic accidents is due to inappropriate vehicle speed or headway. Excessive speed is one of the major causes of accidents on European roads, responsible for one-third of all road accidents. SASPENCE, as part of the EU founded integrated project PReVENT, is developing and evaluating an innovative system able to perform the reliable and comfortable Safe Speed and Safe Distance concept, which helps the driver to avoid dangerous situations related to excessive speed or too small headway.In this paper, the high precise reconstruction of the road geometry is discussed. This information about the road geometry is needed in the project to be able to calculate the risk of a given scenario and given speed. A sensor fusion method is proposed to combine information from a vision sensor, a radar system, digital maps, a GPS sensor and odometric sensors to one common description of the road geometry in front of the vehicle. Thereby, the sensor information is used to localize the own vehicle relative to the map data. The system has been tested using real data and the results are shown in the paper.

Combined lane and road attributes extraction by fusing data from digital map, laser scanner and camera

“…Equations Eqs. (12) and (17) form a dynamic stochastic system which is solved through a typical Kalman optimal estimator. State vector's initialization takes place at the first scan or more often when the previous scan was a scan of 'deletion' (i.e.…”

“…In this work fusion in lane coefficient level and in spatial coordinates were examined. In [12] an algorithm for reconstruction of the road geometry is proposed that includes sensor data fusion to combine information from a vision sensor, a radar system, digital maps, a GPS sensor and odometric sensors. Similar combination is given in [1] with a system including a CMOS camera, a positioning system utilizing digital maps, radar for detecting traffic and on-board inertial sensors for estimating ego-vehicle dynamics.…”

“…[13]) to model the road or lane geometry, while in several approaches circular models (i.e. [12]) or alternative models (such as parabolic curves [14]) are used. There is still a dispute on which model represents better the road geometry and if clothoid is suitable for data fusion [15], however authors support that clothoid road modelling performs well as it agrees with how roads are constructed [16].…”

Multiple Condensation filters for road detection and tracking

“…However, Cramer et al pointed out that a clothoid model is unreliable when the road curvature varies significantly [28,29]. Instead, they model the road as connected arc segments with the aid of digital map data.…”

Robust Road Modeling and Tracking Using Condensation

“…However, Cramer et al [17], [18] have pointed out that the clothoid road model is unreliable when the road curvature tends to significantly vary. They instead model the road as connected arc segments with the help of a digital map.…”