Method, apparatus, and system for estimating a lane width
An approach is provided for lane width estimation from incomplete lane marking detections of a road lane. The approach, for example, involves generating one or more perpendicular lines respectively from location centers of one or more first lane marking detections. A respective lane marking detection represents at least a portion of a boundary of the road lane as a line delimited by two location data points in accordance with detections by at least one sensor device onboard at least one vehicle. The approach also involves identifying second lane marking detections that each respectively intersect one of the one or more perpendicular lines. The approach further involves selecting one or more candidate lane widths based on one or more respective distances from the location centers to the second lane marking detections. The approach further involves determining an estimated lane width of the road lane based on the one or more candidate lane widths.
1. A method for lane width estimation from incomplete lane marking detections of a road lane, the method comprising:
generating, by one or more processors, one or more perpendicular lines respectively from location centers of one or more first lane marking detections, wherein a respective lane marking detection represents at least a portion of a boundary of the road lane as a line delimited by two location data points in accordance with one or more detections by at least one sensor device onboard at least one vehicle;
identifying, by the one or more processors, one or more second lane marking detections that each respectively intersect one of the one or more perpendicular lines, wherein the one or more first lane marking detections and the one or more second lane marking detections take a form of singular lane marking detections that have been generated from continuous lane marking detections, wherein each respective continuous lane marking detection comprises an ordered set of location data points representing one or more lane markings of the road lane, and wherein each respective singular lane marking detection comprises only two consecutive location data points from a respective ordered set of location points included in a respective continuous lane marking detection;
selecting, by the one or more processors, one or more candidate lane widths based on one or more respective distances from the location centers to the one or more second lane marking detections; and
determining, by the one or more processors, an estimated lane width of the road lane based on the one or more candidate lane widths.
2. The method of claim 1 , further comprising:
filtering the one or more candidate lane widths based on a lane width specification threshold,
wherein the estimated lane width is determined based on the filtered one or more candidate lane widths.
3. The method of claim 2 , wherein the estimated lane width specification threshold is based on a road specification standard.
4. The method of claim 2 , further comprising:
increasing the estimated lane width specification threshold by a designated value based on determining that the road lane is associated with a single-lane road.
5. The method of claim 1 , further comprising:
determining that two of the one or more candidate lane widths are duplicate candidates; and
filtering one of the duplicate candidates based on respective lengths of respective lane marking detections associated with the duplicate candidates,
wherein the estimated lane width is determined based on the filtered one or more candidate lane widths.
6. The method of claim 1 , wherein the estimated lane width is determined based on an average or a median of the one or more candidate lane widths.
7. The method of claim 6 , wherein the average or the median is weighted based on a respective length of the one or more second lane marking detections.
8. The method of claim 1 , wherein the estimated lane width is determined based on a minimum or a maximum of the one or more candidate lane widths.
9. The method of claim 1 , further comprising:
clustering the one or more first lane marking detections, the one or more second lane marking detections, or a combination thereof into two or more clusters based on respective distances to a map-matched road link segment,
wherein at least one cluster represents a first lane marking row, and
wherein at least one other cluster represents at least one second lane marking row.
10. The method of claim 9 , wherein the one or more first lane marking detections are associated with the first lane marking row, and wherein the one or more second lane marking detections are associated with the at least one second lane marking row.
11. The method of claim 1 , wherein each of the one or more perpendicular lines is perpendicular to a respective one of the one or more first lane marking detections, a respective one of the one or more second lane marking detections, or a combination thereof.
12. An apparatus for lane width estimation from incomplete lane marking detections of a road lane, 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, within the at least one processor, cause the apparatus to perform at least the following,
generate one or more perpendicular lines respectively from location centers of one or more first lane marking detections, wherein a respective lane marking detection represents at least a portion of a boundary of the road lane as a line delimited by two location data points in accordance with one or more detections by at least one sensor device onboard at least one vehicle;
identify one or more second lane marking detections that each respectively intersect one of the one or more perpendicular lines, wherein the one or more first lane marking detections and the one or more second lane marking detections take a form of singular lane marking detections that have been generated from continuous lane marking detections, wherein each respective continuous lane marking detection comprises an ordered set of location data points representing one or more lane markings of the road lane, and wherein each respective singular lane marking detection comprises only two consecutive location data points from a respective ordered set of location points included in a respective continuous lane marking detection;
select one or more candidate lane widths based on one or more respective distances from the location centers to the one or more second lane marking detections; and
determine an estimated lane width of the road lane based on the one or more candidate lane widths.
13. The apparatus of claim 12 , wherein the apparatus is further caused to:
filter the one or more candidate lane widths based on a lane width specification threshold,
wherein the estimated lane width is determined based on the filtered one or more candidate lane widths.
14. The apparatus of claim 13 , wherein the estimated lane width specification threshold is based on a road specification standard.
15. The apparatus of claim 12 , wherein the apparatus is further caused to:
determine that two of the one or more candidate lane widths are duplicate candidates; and
filter one of the duplicate candidates based on respective lengths of respective lane marking detections associated with the duplicate candidates,
wherein the estimated lane width is determined based on the filtered one or more candidate lane widths.
16. A non-transitory computer-readable storage medium for lane width estimation from incomplete lane marking detections of a road lane, carrying one or more sequences of one or more instructions which, when executed by one or more processors, cause an apparatus to perform:
generating one or more perpendicular lines respectively from location centers of one or more first lane marking detections, wherein a respective lane marking detection represents at least a portion of a boundary of the road lane as a line delimited by two location data points in accordance with one or more detections by at least one sensor device onboard at least one vehicle;
identifying one or more second lane marking detections that each respectively intersect one of the one or more perpendicular lines, wherein the one or more first lane marking detections and the one or more second lane marking detections take a form of singular lane marking detections that have been generated from continuous lane marking detections, wherein each respective continuous lane marking detection comprises an ordered set of location data points representing one or more lane markings of the road lane, and wherein each respective singular lane marking detection comprises only two consecutive location data points from a respective ordered set of location points included in a respective continuous lane marking detection;
selecting one or more candidate lane widths based on one or more respective distances from the location centers to the one or more second lane marking detections; and
determining an estimated lane width of the road lane based on the one or more candidate lane widths.
17. The non-transitory computer-readable storage medium of claim 16 , wherein the apparatus is caused to further perform:
filtering the one or more candidate lane widths based on a lane width specification threshold,
wherein the estimated lane width is determined based on the filtered one or more candidate lane widths.