Abstract:
An approach is provided for point-based map matchers using machine learning. The approach involves retrieving points collected within proximity to a map feature represented by a link of a geographic database. The probe points are collected from sensors of devices traveling near the map feature. The approach also involves determining a probe feature set for each probe point comprising probe attribute values, and determining a link feature set for the link comprising link attribute values. The apparatus further involves classifying, using a machine learning classifier, each probe point to determine a matching probability based on the probe feature set and the link feature to indicate a probability that each probe point is classified as map-matched to the link. The machine learning classifier is trained using ground truth data comprising reference probe points with known map-matches to respective reference links, and comprising known probe attribute values and known link attribute values.
Abstract:
A method, apparatus and computer program product are provided for multi-resolution point of interest boundary identification in digital map rendering. A method is provided for receiving a point of interest selection indication. The method also includes receiving point of interest boundary data and map data associated with the selected point of interest from a memory. The boundary data is based on the physical shape of the structure or region associated with the point of interest. The method also includes overlaying point of interest boundary data on the map data; and causing the map data with point of interest boundary data overlay to be displayed on a user interface.
Abstract:
An approach is provided for point-based map matchers using machine learning. The approach involves retrieving points collected within proximity to a map feature represented by a link of a geographic database. The probe points are collected from sensors of devices traveling near the map feature. The approach also involves determining a probe feature set for each probe point comprising probe attribute values, and determining a link feature set for the link comprising link attribute values. The apparatus further involves classifying, using a machine learning classifier, each probe point to determine a matching probability based on the probe feature set and the link feature to indicate a probability that each probe point is classified as map-matched to the link. The machine learning classifier is trained using ground truth data comprising reference probe points with known map-matches to respective reference links, and comprising known probe attribute values and known link attribute values.
Abstract:
Systems and methods for the detection and analysis of curvature data are described. A method includes: receiving position data of a vehicle turning maneuver along a portion of a roadway, where the position data includes measured position data collected by sensors of a vehicle while traversing the vehicle turning maneuver; associating the received position data with map data of the portion of the roadway; generating a spline based on the position data, the spline being a smooth curve representing the vehicle turning maneuver from a first road segment to a second road segment; identifying a segment of the spline containing a turning point of the vehicle turning maneuver, the turning point representing a change of a vehicle path from along the first road segment to along the second road segment; and determining a maximum curvature value for the identified segment of the spline.
Abstract:
A method, apparatus and computer program product are provided for multi-resolution point of interest boundary identification in digital map rendering. A method is provided for receiving a point of interest selection indication. The method also includes receiving point of interest boundary data and map data associated with the selected point of interest from a memory. The boundary data is based on the physical shape of the structure or region associated with the point of interest. The method also includes overlaying point of interest boundary data on the map data; and causing the map data with point of interest boundary data overlay to be displayed on a user interface.
Abstract:
An approach is provided for providing a map matcher tolerant to wrong map features. The approach involves, for instance, finding a segment of a probe trajectory containing a plurality of low-speed probe points. The approach also involves forming a line between a first and a last probe point of the segment. The approach further involves calculating a distance from each probe point of the segment to the line. The approach further involves splitting the segment based on comparing the distance to a threshold at a turning point of the segment. The approach further involves creating a new probe trajectory based on a plurality of high-speed probe points in the probe trajectory and the turning point. The approach further involves estimating a heading of the turning point of the segment based on the new trajectory, and then performing a feasibility check between two consecutive probe points of the new trajectory.
Abstract:
A method map matches probe data to a candidate road segment or node. Methods may include: searching for candidate road segments or nodes for each probe data point to be matched to, where searching for candidate road segments or nodes includes: searching within a predefined radius of each probe data point for road segments or nodes and in response to no road segments or nodes being found within the predefined radius of the respective probe data point, iteratively increasing the predefined radius and searching again until a predefined maximum radius is reached or at least two road segment candidates or node candidates are found; map matching each probe data point to a respective road segment candidate or node candidate based on the road segment candidate or node candidate found in the search; and generating a path based on the map matched probe data points from a respective probe.
Abstract:
Systems and methods for the detection and analysis of curvature data are described. A method includes: receiving position data of a vehicle turning maneuver along a portion of a roadway, where the position data includes measured position data collected by sensors of a vehicle while traversing the vehicle turning maneuver; associating the received position data with map data of the portion of the roadway; generating a spline based on the position data, the spline being a smooth curve representing the vehicle turning maneuver from a first road segment to a second road segment; identifying a segment of the spline containing a turning point of the vehicle turning maneuver, the turning point representing a change of a vehicle path from along the first road segment to along the second road segment; and determining a maximum curvature value for the identified segment of the spline.