Positioning system

• US 9,104,702 B2
• Filed: 09/26/2011
• Issued: 08/11/2015
• Est. Priority Date: 10/06/2010
• Status: Active Grant

• Current Assignee: NEC Corporation
• Original Assignee: NEC Corporation
• Inventors: Takahashi, Katsuhiko
• Primary Examiner(s): Cunningham, Gregory F
• Application Number:
  US13/877,944
• Publication Number:
  US 20130188837A1
• Time in Patent Office: 1,415 Days
• Field of Search: 235/411, 345/135, 345/700, 345/E5.067, 348/169, 348/208.14, 348/E13.023, 348/E13.043, 348/E13.066, 382/103, 386/341, 701/25, 701/26, 701/56, 701/409, 701/421, 701/438, 701/446, 701/448, 701/455, 701/460, 701/461
• US Class Current: 1/1
• CPC Class Codes: G01C 21/20 Instruments for performing navigational calculations G01C21/24, G01C21/26 take precedence
• CPC Class Codes: G01C 21/26 specially adapted for navigation in a road network
• CPC Class Codes: G01S 5/16 using electromagnetic waves other than radio waves
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: G06F 16/5854 using shape and object relationship
• CPC Class Codes: G06T 11/00 2D [Two Dimensional] image generation
• CPC Class Codes: G06T 2207/30252 Vehicle exterior; Vicinity of vehicle
• CPC Class Codes: G06T 7/74 involving reference images or patches

Abstract

An object of the present invention is to provide a positioning system which makes it possible to perform positioning processing in a positioning target mobile object with a smaller calculation amount.

A scenery image database according to an aspect of the present invention is characterized by comprising a plurality of scenery image data and image acquisition locations at which the scenery image data have been acquired are correlated with each other and stored, wherein each of the plurality of scenery image data include a feature amount of a feature point corresponding to a thing other than a thing of which a location or a shape is unlikely to be kept as it is on the real world during a period larger than or equal to a predetermined period.

Claims

1. A scenery image database, comprising:

a hard disk having a plurality of scenery image data corresponding to a plurality of acquired scenery images stored thereon, wherein each of the plurality of the scenery image data includes an extracted portion of a corresponding one of the plurality of acquired scenery images,

wherein the extracted portion includes one or more feature amounts of one or more extracted feature points corresponding to one or more things that are identified to remain in a stationary state during a predetermined period, and the extracted portion does not include non-extracted feature points corresponding to one or more things that are identified to not remain in the stationary state during a period larger than or equal to the predetermined period.

2. The scenery image database according to claim 1, wherein the one or more things that are identified to not remain in the stationary state comprises a vehicle.

3. The scenery image database according to claim 1, wherein the one or more things that are identified to not remain in the stationary state comprises a person.

4. A database building apparatus comprising:

the scenery image database according to claim 1,

a first imaging unit configured to acquire the plurality of acquired scenery images; and

a feature point extraction unit configured to extract the one or more extracted feature points from the plurality of acquired scenery images acquired by the first imaging unit.

5. The database building apparatus according to claim 4, wherein the first imaging unit is configured to acquire the plurality of acquired scenery images by capturing light having a wavelength band not included in the visible-light region.

6. A positioning target apparatus comprising:

the scenery image database according to claim 1;

an imaging unit configured to acquire a scenery image;

a feature point extraction unit configured to extract one or more feature amounts of corresponding feature points from the scenery image acquired by the imaging unit; and

an image-collation and location-identification unit configured to compare the extracted one or more feature amounts of the corresponding feature points extracted by the feature point extraction unit to the plurality of scenery image data stored in the scenery image database to identify a current location of a mobile object.

7. The positioning target apparatus according to claim 6, further comprising a location acquisition unit configured to acquire an approximate location of the positioning target apparatus,

wherein the image-collation and location-identification unit compares the extracted one or more feature amounts of the corresponding feature points extracted by the feature point extraction unit to a subset of the plurality of scenery image data, wherein the subset of the plurality of scenery image data corresponds to a subset of the plurality of acquired scenery images created at a location around the approximate location of the positioning target apparatus.

11. The scenery image database of claim 1, comprising image acquisition locations at which the plurality of the scenery image data are acquired, wherein the image acquisition locations are correlated with the plurality of scenery image data.

12. The scenery image database according to claim 1, wherein the one or more things that are identified to not remain in the stationary state comprises a plant.

8. A database building method, comprising:

acquiring, with an imaging unit, a scenery image;

extracting, from the scenery image, with a feature point extraction unit, an extracted portion comprising feature amounts of feature points corresponding to one or more things in the scenery image that are identified to remain in a stationary state during a predetermined period, and not feature amounts of feature points corresponding to one or more things in the scenery image that are identified to not remain in the stationary state during a period larger than or equal to the predetermined period; and

storing the extracted portion in a scenery image database.

9. The database building method according to claim 8,

wherein acquiring the scenery image comprises acquiring a wavelength band included in a visible-light region and a wavelength band not included in the visible-light region.

13. The database building method according to claim 8, wherein the one or more things that are identified to not remain in the stationary state comprises a plant.

14. The database building method according to claim 8, comprising acquiring location information corresponding to the acquired scenery image.

15. The database building method according to claim 14, comprising correlating the acquired location information with the extracted portion of the scenery image in the scenery image database.

16. The database building method according to claim 8, wherein the one or more things that are identified to not remain in the stationary state comprises a person.

17. The database building method according to claim 8, wherein the one or more things that are identified to not remain in the stationary state comprises a vehicle.

10. A non-transitory tangible machine-readable media encoding instructions which, when executed by a processor, cause the processor to perform acts comprising:

acquiring a scenery image;

extracting, from the scenery image, an extracted portion comprising feature amounts of feature points corresponding to one or more things in the scenery image that are identified to remain in a stationary state during a predetermined period, and not feature amounts of feature points corresponding to one or more things in the scenery image that are identified to not remain in the stationary state during a period larger than or equal to the predetermined period; and

storing the extracted portion in a scenery image database.

18. The non-transitory tangible machine-readable media according to claim 10, encoding instructions which, when executed by a processor, cause the processor to perform acts further comprising acquiring location information corresponding to the acquired scenery image.

19. The non-transitory tangible machine-readable media according to claim 18, encoding instructions which, when executed by a processor, cause the processor to perform acts further comprising correlating the acquired location information with the extracted portion of the scenery image in the scenery image database.

20. The non-transitory tangible machine-readable media according to claim 10, wherein the one or more things that are identified to not remain in the stationary state comprises a person.