US 12,461,948 B2
Method, apparatus, and computer program product for map data conflation
Nileshkumar Kadam, Pune (IN); Xiang Liu, Berlin (DE); Ricky Singh, Assam (IN); Jivitesh Sharma, Haryana (IN); and Ganesh Singadkar, Aurangabad (IN)
Assigned to HERE GLOBAL B.V., Eindhoven (NL)
Filed by HERE GLOBAL B.V., Eindhoven (NL)
Filed on Sep. 23, 2022, as Appl. No. 17/934,900.
Prior Publication US 2024/0104121 A1, Mar. 28, 2024
Int. Cl. G06F 16/29 (2019.01); G06F 16/28 (2019.01); H04W 4/02 (2018.01)
CPC G06F 16/29 (2019.01) [G06F 16/285 (2019.01); H04W 4/025 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving observation data associated with a geographic area;
identifying at least one observed object within the observation data, the at least one observed object including an observed object location and an observed object type;
determining at least one confidence score for the at least one observed object;
estimating similarity between the at least one observed object and at least one other observed object;
merging the at least one observed object and the at least one other observed object based on a clustering algorithm and the similarity in response to the at least one confidence score satisfying a predetermined threshold, wherein merging the at least one observed object and the at least one other observed object based on the clustering algorithm and the similarity comprises grouping the at least one observed object and the at least one other observed object based on the similarity using the clustering algorithm;
conflating the at least one observed object and the at least one other observed object to obtain a conflated object in response to merging the at least one observed object and the at least one other observed object;
providing for storage of the conflated object; and
providing for at least one of navigational guidance or at least semi-autonomous vehicle control using the stored, conflated object.