Road-terrain detection method and system for driver assistance systems

A road-terrain detection system for driver assistance systems, the road-terrain detection system being adapted to

• sense with at least one sensor the environment of a vehicle;
• transform at least one sensor signal from at least one sensor into at least one confidence map of local properties of the environment by using at least one base classifier;
• generate, for base points on the at least one confidence map, each reflecting a specific location in the environment of the vehicle, spatial features for local properties based on the at least one confidence map;
• and
• classify, based on the generated spatial features, locations in the environment of the vehicle to a certain category of road terrain corresponding to a type of surface of a road, wherein the generation of a spatial feature for a specific location in the environment of the vehicle comprises
• extracting a ray, wherein a ray is defined as a directed line with a certain angular orientation starting from the location in the environment, and
• analyzing confidence values along the ray to extract spatial feature.

A road-terrain detection method for driver assistance systems, wherein the road-terrain detection method comprises

• sensing the environment of a vehicle with at least one sensor;
• transforming a sensor signal from the at least one sensor into at least one confidence map of local properties of the environment by using at least one base classifier;
• generating, for base points on the at least one confidence map, each reflecting a specific location in the environment of the vehicle, spatial features for the local properties based on the at least one confidence map;
• and
• classifying, based on the generated spatial features, locations in the environment of the vehicle to a certain category of road terrain corresponding to the type of surface of the road, wherein the method comprises
• a base classifier for visual boundary classification, in order to find visual features that discriminate a road boundary from a road-like area, wherein the method
• includes feature generation,
• uses a positive training set with polygonal training regions for the road boundary, and
• uses a negative training set with polygonal training regions for road-like area excluding areas with lane-markings.

A non-transitory computer-readable medium encoded with instructions that, when run on a computing device in a land vehicle, perform a method, the method comprising:

• sensing the environment of a vehicle with at least one sensor;
• transforming a sensor signal from the at least one sensor into at least one confidence map of local properties of the environment by using at least one base classifier;
• generating, for base points on the at least one confidence map, each reflecting a specific location in the environment of the vehicle, spatial features for the local properties based on the at least one confidence map;
• and
• classifying, based on the generated spatial features, locations in the environment of the vehicle to a certain category of road terrain corresponding to a type of surface of a road, wherein the generation of a spatial feature for a specific location in the environment of the vehicle comprises
• extracting a ray, wherein a ray is defined as a directed line with a certain angular orientation starting from the location in the environment, and
• analyzing confidence values along the ray to extract spatial feature.

A road-terrain detection system for driver assistance systems, the road-terrain detection system being adapted to

• sense the environment of a vehicle with at least one sensor;
• transform a sensor signal from the at least one sensor into at least one confidence map of local properties of the environment by using at least one base classifier;
• generate, for base points on the at least one confidence map, each reflecting a specific location in the environment of the vehicle, spatial features for the local properties based on the at least one confidence map;
• and
• classify, based on the generated spatial features, locations in the environment of the vehicle to a certain category of road terrain corresponding to the type of surface of the road,
• wherein a base classifier is provided for visual boundary classification, in order to find visual features that discriminate a road boundary from a road-like area,
• wherein the system is adapted to
• include feature generation,
• use a positive training set with polygonal training regions for the road boundary, and
• use a negative training set with polygonal training regions for road-like area excluding areas with lane-markings.