Method and apparatus for dynamic speed aggregation of probe data for high-occupancy vehicle lanes

1. A method comprising:

determining a line that is parallel to a road segment and divides the road segment along a longitudinal axis, wherein a first lane is a high-occupancy-vehicle (HOV) lane of a first side of the line along the road segment, and the second lane is a non-high-occupancy-vehicle (non-HOV) lane of a second side of the line along the road segment;

determining a spatial distribution of probe data collected from the first lane of the first side and second lane of the second side of the road segment with respect to the line;

clustering the probe data into a first cluster for the first lane and a second cluster for the second lane based on speed of a plurality of vehicles traveling in the first lane and the second lane;

outputting a bi-modality event occurring on the first and second lanes of the road segment based on determining that a speed differential between the first cluster of the first lane and the second cluster of the second lane is above a threshold value; and

determining a first distance of a first plurality of probes of the first cluster of the first lane from the line, and a second distance of a second plurality of probes of the second cluster of the second lane from the line,

wherein the spatial distribution is based on the first distance and the second distance, and

wherein the bi-modality event indicates that the HOV lane of the road segment can provide for faster travel than the non-HOV lane of the road segment.

2. The method of claim 1 , the method further comprising:

publishing the bi-modality event as a high-occupancy-vehicle traffic event of the road segment.

3. The method of claim 2 , wherein the road segment is selected based on a road topology indicating that the high-occupancy-vehicle traffic event can be published for the road segment.

4. The method of claim 1 , further comprising:

classifying the first cluster, the second cluster, or a combination thereof as either a high-speed cluster or a low-speed cluster; and

rejecting the bi-modality event based on determining that a cluster of speed of the low-speed cluster is faster than a free-flow speed threshold.

5. The method of claim 1 , further comprising:

classifying the first cluster, the second cluster, or a combination thereof as either a high-speed cluster or a low-speed cluster; and

rejecting the bi-modality event based on determining that the high-speed cluster is not a High Occupancy Vehicle (HOV) lane based on the spatial distribution.

6. The method of claim 2 , further comprising:

creating a dynamic road segment to aggregate the roadway with one or more downstream road segments based on a distance threshold.

7. The method of claim 1 , wherein the first distance, the second distance, or a combination is a closest perpendicular distance to the line.

8. The method of claim 1 , wherein the first distance is a first mean or median distance of the first plurality of probes from the line, and the second distance is a second mean or median distance of the second plurality of probes from the line.

9. 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 and the computer program code configured to, with the at least one processor, cause the apparatus to perform at least the following,

determine a line that is parallel to a road segment and divides the road segment along a longitudinal axis, wherein a first lane is a high-occupancy-vehicle (HOV) lane of a first side of the line along the road segment, and the second lane is a non-high-occupancy-vehicle (non-HOV) lane of a second side of the line along the road segment;

determine a spatial distribution of probe data collected from the first lane of the first side and second lane of the second side of the road segment with respect to the line;

cluster the probe data into a first cluster for the first lane and a second cluster for the second lane based on speed of a plurality of vehicles traveling in the first lane and the second lane;

output a bi-modality event occurring on the first and second lanes of the road segment based on determining that a speed differential between the first cluster of the first lane and the second cluster of the second lane is above a threshold value; and

determine a first distance of a first plurality of probes of the first cluster of the first lane from the line, and a second distance of a second plurality of probes of the second cluster of the second lane from the line,

wherein the spatial distribution is based on the first distance and the second distance, and

wherein the bi-modality event indicates that the HOV lane of the road segment can provide for faster travel than the non-HOV lane of the road segment.

10. The apparatus of claim 9 , wherein the apparatus is further caused to:

publish the bi-modality event as a high-occupancy-vehicle traffic event of the road segment.

11. The apparatus of claim 10 , wherein the road segment is selected based on a road topology indicating that the high-occupancy-vehicle traffic event can be published for the road segment.

12. The apparatus of claim 10 , wherein the apparatus is further caused to:

create a dynamic road segment to aggregate the roadway with one or more downstream road segments based on a distance threshold.

13. A non-transitory computer readable storage medium including one or more sequences of one or more instructions which, when executed by one or more processors, cause an apparatus to at least perform:

determining a line that is parallel to a road segment and divides the road segment along a longitudinal axis, wherein a first lane is a high-occupancy-vehicle (HOV) lane of a first side of the line along the road segment, and the second lane is a non-high-occupancy-vehicle (non-HOV) lane of a second side of the line along the road segment;

determining a spatial distribution of probe data collected from the first lane of the first side and second lane of the second side of the road segment with respect to the line;

clustering the probe data into a first cluster for the first lane and a second cluster for the second lane based on speed of a plurality of vehicles traveling in the first lane and the second lane;

outputting a bi-modality event occurring on the first and second lanes of the road segment based on determining that a speed differential between the first cluster of the first lane and the second cluster of the second lane is above a threshold value; and

determining a first distance of a first plurality of probes of the first cluster of the first lane from the line, and a second distance of a second plurality of probes of the second cluster of the second lane from the line,

wherein the spatial distribution is based on the first distance and the second distance, and

wherein the bi-modality event indicates that the HOV lane of the road segment can provide for faster travel than the non-HOV lane of the road segment.

14. The non-transitory computer readable storage medium of claim 13 , wherein the apparatus is caused to further perform:

publishing the bi-modality event as a high-occupancy-vehicle traffic event of the road segment.

15. The non-transitory computer readable storage medium of claim 14 , wherein the road segment is selected based on a road topology indicating that the high-occupancy-vehicle traffic event can be published for the road segment.

16. The non-transitory computer readable storage medium of claim 14 , wherein the apparatus is caused to further perform:

creating a dynamic road segment to aggregate the roadway with one or more downstream road segments based on a distance threshold.