| 摘要 |
The invention relates to a method for estimating traffic lanes, which method is preferably used in a driver assistance system. According to the invention, the method uses multiple pieces of input data to estimate traffic lanes. The input data are the position and direction of feature vectors, which are measured from multiple different sensors independently of one another. A feature vector is formed by a position in the coordinate system of the driver's vehicle, which position describes a point on the edge of a traffic lane, and a device or an angle which indicates the direction in which the edge of the traffic lane runs at this position. Further input data are variables which represent the quality of the measurement of the positional accuracy and the directional accuracy and the probability of the existence of a feature vector. The method has the following steps: the input data are accumulated chronologically together (S10). The geometry of traffic lanes is estimated (S20) from the accumulated input data taking into account the quality of the measurement (positional and directional accuracy as well as probability of existence of the feature vector). The estimated geometry of traffic lanes is output (S30), which in turn can, in particular, be carried out generically as a position and direction of feature vectors, as a result of which the estimated profile of traffic lanes is described quantitatively. |
