Modeling point cloud data using hierarchies of gaussian mixture models
US-2017249401-A1 · Aug 31, 2017 · US
US11526498B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-11526498-B2 |
| Application number | US-202117219597-A |
| Country | US |
| Kind code | B2 |
| Filing date | Mar 31, 2021 |
| Priority date | Mar 31, 2021 |
| Publication date | Dec 13, 2022 |
| Grant date | Dec 13, 2022 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
A method for storing shard data and data formats for storing shard data are proposed. Shard data entries are generated and stored, wherein each shard data entry comprises a definition of one or more semantic objects covered by the shard data entry. Shard metadata is generated and stored, wherein the metadata comprises references to the shard data entries and, for each of the shard data entries, data representative of a bounding box indicative of an area in a geographical area that is covered by the shard data entry.
Opening claim text (preview).
What is claimed is: 1. A method for storing shard data, the method comprising: utilizing guiding sections defining different parts of a geographical area to identify semantic objects within each guiding section; applying one or more map consistency rules to determine whether semantic objects within a given guiding section are to be kept together in a shard; generating and storing shard data entries in a shard-to-object relations database, wherein each shard data entry in the shard-to-object relations database identifies a given shard and which semantic objects are part of the given shard; and generating and storing shard metadata entries, wherein each shard metadata entry corresponds to a given shard, and includes: (1) an integer value as an identifier of the given shard; (2) a non-unique string value representing a subtype of the given shard; (3) a unique string value representing a name of the given shard constructed from the non-unique string value and a sequence number; and (4) four floating point values defining corners of a bounding box covered by the semantic objects of the given shard; exporting shard data and storing the shard data as shard files based on the shard metadata entries and the shard-to-object relations database; and providing shard files to clients including one or more of an autonomous vehicle, a vehicle, and a computer environment. 2. The method according to claim 1 , wherein the shard data entries are stored in a database format, and wherein the shard metadata entries are stored in a database format. 3. The method according to claim 1 , wherein the four floating point values are indicative of a minimum x-coordinate, a maximum x-coordinate, a minimum y-coordinate and a maximum y-coordinate, respectively. 4. The method according to claim 1 , wherein the subtype indicates the shard being related to a type of the guiding section used in generating the shard. 5. The method according to claim 1 , wherein the subtype indicates the shard being related to city-wide objects, indicative of the shard including city-wide objects. 6. The method according to claim 1 , wherein the subtype indicates the shard being related to experiments for simulation purposes. 7. The method according to claim 1 , wherein the shard metadata entry for the given shard is used to generate the shard file for each of the shard data entries, wherein each shard file comprises a definition of the semantic objects covered by the shard data entry. 8. The method according to claim 1 , wherein the shard metadata entry for the given shard is used to generate the shard file for each for the shard data entries, and wherein the subtype is used as a part of a filename of the shard file. 9. The method according to claim 1 , further comprising: generating and storing a shard metadata file from the shard metadata entries, wherein the shard metadata file comprises references to the shard files. 10. The method according to claim 9 , wherein the shard metadata file is stored in a json file format. 11. One or more non-transitory computer-readable storage media comprising instruction for execution which, when executed by a processor, are operable to perform operations for storing shard data, the operations comprising: utilizing guiding sections defining different arts of a geographical area to identify semantic objects within each guiding section; applying one or more map consistency rules to determine whether semantic objects within a given guiding section are to be kept to ether in a shard; generating shard data entries in a shard-to-object relations database, wherein each shard data entry in the shard-to-object relations database identifies a given shard and which semantic objects are part of a given shard; generating shard metadata entries, wherein each shard metadata entry corresponds to a given shard, and includes: (1) an integer value as an identifier of the given shard; (2) a non-unique string value representing a subtype of the given shard; (3) a unique string value representing a name of the given shard constructed from the non-unique string value and a sequence number; and (4) four floating point values defining corners of a bounding box covered by the semantic objects of the given shard; exporting shard data and storing the shard data as shard files based on the shard metadata entries and the shard-to-object relations database; and providing shard files to clients including one or more of an autonomous vehicle a vehicle, and a computer environment. 12. The one or more non-transitory computer-readable storage media according to claim 11 , wherein the four floating point values are indicative of a minimum x-coordinate, a maximum x-coordinate, a minimum y-coordinate and a maximum y-coordinate, respectively. 13. The one or more non-transitory computer-readable storage media according to claim 11 , wherein the subtype indicates the shard being related to a type of the guiding section used in generating the shard. 14. The one or more non-transitory computer-readable storage media according to claim 11 , wherein the subtype indicates the shard being related to city-wide objects, indicative of the shard including city-wide objects. 15. The one or more non-transitory computer-readable storage media according to claim 11 , wherein the subtype indicates the shard being related to experiments for simulation purposes. 16. The one or more non-transitory computer-readable storage media according to claim 11 , wherein the operations further comprise: loading the shard metadata entries; for each shard data entry, obtaining the subtype from the loaded shard metadata entries; and generating the shard file for each of the shard data entries, wherein a filename of each of the shard files comprises the subtype. 17. The one or more non-transitory computer-readable storage media according to claim 11 , wherein the operations further comprise: generating a shard metadata file from the shard metadata entries, wherein the shard metadata file comprises references to the shard files. 18. A computer system comprising: one or more processors; one or more non-transient computer-readable storage devices storing instructions; one or more database storage devices storing one or more databases; a database exporter, encoded in the instructions to export shard data from the one or more database storage devices based on: a shard-to-object relations database stored on the one or more database storage devices, wherein each entry in the shard-to-object relations database identifies a given shard and which semantic objects are part of the given shard; and shard metadata entries stored on the one or more database storage devices, wherein each metadata entry corresponds to a given shard, and includes: (1) an integer value as an identifier of the given shard; (2) a non-unique string value representing a subtype of the given shard; (3) a unique string value representing a name of the given shard constructed from the non-unique string value and a sequence number; and (4) four floating point values defining corners of a bounding box covered by the semantic objects of the given shard; a file storage system to receive shard data exported b the database exporter and to store the shard data as shard files, where one shard file includes data for one shard; and an u loader encoded in the instructions to upload the shard files to clients including one or more of an autonomous vehicle, a vehicle, and a computer environment. 19. The computer system of claim 18
Updates performed during online database operations; commit processing · CPC title
Geographical information databases · CPC title
specially adapted to land vehicles · CPC title
Control of position or course in two dimensions [2D] · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.