Detecting and obtaining lane level insight in unplanned incidents
System and methods for detecting and obtaining lane level insight in unplanned incidents. Probe-based vehicles and lane-level insight using a lane-level map-matcher are used to acquire information. This information is aggregated and used to differentiate lane activity in terms of traffic and safe navigation. With the identification of probes per-lane and probe speeds per-lane, sudden reductions in probe speeds may be obtained at a lane-based level. This is used to verify or detect lane-level incident or hazard warnings and consequently alert a driver to safer navigation paths ahead of time, for example alerting the driver to maneuver to a different lane or to take an alternative route.
1. A method for detecting and obtaining lane-level insight in unplanned incidents, the method comprising:
acquiring, from a plurality of probe vehicles, probe data for a road strand comprising a plurality of lanes;
map matching, using a lane level map matcher, the probe data;
splitting the road strand into a plurality of lane strands;
generating, using a clustering algorithm and the map matched probe data, three or more clusters of vehicles each comprising one or more probe vehicles on a same lane strand of the plurality of lane strands within a threshold distance of other probe vehicles in a respective cluster, wherein at least two of the three or more clusters of vehicles are located on different lane strands of the plurality of lane strands;
determining an average speed for each cluster of the three or more clusters;
sorting each of the three of more clusters in a sequential order using an x-value in a center of each of the three or more cluster;
calculating a speed-ratio for each contiguous pair of clusters of the three or more clusters where the speed-ratio=(average speed of a first cluster and a next sequential cluster)/(average speed of the first cluster);
computing a JAM factor for each of the three or more clusters, wherein the JAM factor comprises a speed-ratio of the average speed vs a free flow speed of the road strand;
calculating a LOS delta value or a change in a JAM factor across K clusters of the three or more clusters using LOS delta value=JAM.Factor of k+1−JAM.Factor of k, wherein if the LOS delta value is greater than a predefined threshold, then a cluster k is determined to have an unplanned traffic incident.
2. The method of claim 1 , wherein the probe data comprises at least a latitude and longitude value.
3. The method of claim 1 , wherein map matching comprises:
matching positional coordinates for respective probe data against lane-based probabilities for historical probe data.
4. The method of claim 1 , wherein the clustering algorithm comprises a k-means clustering algorithm.
5. The method of claim 4 , wherein a distance metric for the k-means clustering algorithm is a composite of a probe vehicle's distance along the road strand and a speed.
6. The method of claim 1 , further comprising:
receiving a request for a route from a navigation device;
generating the route based at least in part on the identified unplanned incident locations; and
transmitting the route to the navigation device.
7. The method of claim 1 , wherein the unplanned incident comprises at least one of a traffic accident, a slow vehicle, or a roadway obstruction.
8. An intelligent transportation system for detecting and obtaining lane-level insight in unplanned incidents, the system comprising:
one or more probe devices configured to acquire probe data for a road strand comprising a plurality of lanes strands;
a geographic database configured to store map data relating to the road strand; and
a mapping server configured to map match, using a lane level map matcher and the map data, the probe data, generate, using a clustering algorithm and the map matched probe data, three or more clusters of vehicles each comprising one or more probe vehicles on a same lane strand of the plurality of lanes strand within a threshold distance of other probe vehicles in a respective cluster, wherein at least two of the three or more clusters of vehicles are located on different lane strands of the plurality of lane strands, determine an average speed for each cluster of the three or more clusters, calculate a speed-ratio for each contiguous pair of clusters of the three or more clusters where the speed-ratio=(average speed of k+1)/(average speed of k), and calculate a LOS delta value or a change in a JAM factor across K clusters of the three or more clusters using LOS delta value=JAM.Factor of k+1−JAM.Factor of k, wherein if the LOS delta value and speed-ratio is greater than respective predefined threshold, then a cluster k is determined to have an unplanned traffic incident.
9. The intelligent transportation system of claim 8 , wherein the probe data comprises at least a latitude and longitude value.
10. The intelligent transportation system of claim 8 , wherein the mapping server is configured to map match the probe data by matching positional coordinates for respective probe data against lane-based probabilities for historical probe data.
11. The intelligent transportation system of claim 8 , wherein the clustering algorithm comprises a k-means clustering algorithm.
12. The intelligent transportation system of claim 11 , wherein a distance metric for the k-means clustering algorithm is a composite of a probe vehicle's distance along the road strand and a speed.
13. The intelligent transportation system of claim 8 , wherein the mapping server is further configured to publish the unplanned incident locations for use by navigation devices in making routing decisions.
14. An apparatus comprising:
at least one processor; and
at least one memory including computer program code for one or more programs; the at least one memory configured to store the computer program code configured to, with the at least one processor, cause the at least one processor to:
acquire, from a plurality of probe vehicles, probe data for a road strand comprising two or more lanes;
map match, using a lane level map matcher, the probe data;
split the road strand into a plurality of lane strands;
generate, using a clustering algorithm and the map matched probe data, three or more clusters of vehicles each comprising one or more probe vehicles on a same lane of the one or more lanes within a threshold distance of other probe vehicles in a respective cluster, wherein at least two of the three or more clusters of vehicles are located on different lane strands of the plurality of lane strands;
determine an average speed for each cluster of the three or more clusters;
calculate a speed-ratio for each contiguous pair of clusters of the three or more clusters where the speed-ratio=(average speed of k+1)/(average speed of k); and
calculate a LOS delta value or a change in a JAM factor across K clusters of the three or more clusters using LOS delta value=JAM.Factor of k+1−JAM.Factor of k, wherein if the LOS delta value and speed-ratio is greater than respective predefined threshold, then a cluster k is determined to have an unplanned traffic incident.
15. The apparatus of claim 14 , wherein the clustering algorithm comprises a k-means clustering algorithm.