Crosswalk detection
AssigneeGM Cruise Holdings LLC
InventorsHarman Kumar, Juan Fasola, Yu-Cheng Lin
Life of this patent
Estimating the term…
Abstract
Systems and methods are disclosed for detecting crosswalk locations. Crosswalk locations can be detected by determining at least two painted lines on a road surface, and then combining the at least two painted lines on the road surface into a grouping of related elements. The grouping of related elements can be classified into a crosswalk (or in some embodiments a type of crosswalk) based on attributes of the grouping of related elements, where the attributes of the grouping of the elements includes a distance between the at least two painted lines, and an orientation of the grouping of related elements on the road surface.
Claims20
A method for crosswalk detection comprising:
- classifying a candidate crosswalk as a zebra-type crosswalk or a parallel line-type crosswalk;
- identifying an inconsistency of the classifying the candidate crosswalk as the zebra-type crosswalk or the parallel line-type crosswalk by comparing a set of pre-mapped data stored in a map database associated with a navigated route to data collected by a plurality of sensors;
- updating the pre-mapped data based on the classifying the zebra-type crosswalk or the parallel line-type crosswalk;
- and
- controlling a direction of movement of an autonomous vehicle during navigation, based on the updating of the pre-mapped data.
A non-transitory computer readable medium comprising instructions stored thereon, the instructions to cause at least one processor to:
- classify a candidate crosswalk as a zebra-type crosswalk or a parallel line-type crosswalk;
- identify an inconsistency of the classifying the candidate crosswalk as the zebra-type crosswalk or the parallel line-type crosswalk by comparing a set of pre-mapped data stored in a map database associated with a navigated route to data collected by a plurality of sensors;
- update the pre-mapped data based on the classifying the zebra-type crosswalk or the parallel line-type crosswalk;
- and
- control a direction of movement of an autonomous vehicle during navigation, based on the updating of the pre-mapped data.
A computing system comprising:
- at least one non-transitory computer readable medium comprising instructions stored thereon, wherein the instructions are to cause the computing system to:
- classify a candidate crosswalk as a zebra-type crosswalk or a parallel line-type crosswalk;
- identify an inconsistency of the classifying the candidate crosswalk as the zebra-type crosswalk or the parallel line-type crosswalk by comparing a set of pre-mapped data stored in a map database associated with a navigated route to data collected by a plurality of sensors;
- update the pre-mapped data based on the classifying the zebra-type crosswalk or the parallel line-type crosswalk;
- and
- control a direction of movement of an autonomous vehicle during navigation, based on the updating of the pre-mapped data.
Dependencies are inferred from the claim text.