APPARATUS AND METHOD FOR VEHICLE POSITIONING

• US 20150199806A1
• Filed: 07/18/2014
• Published: 07/16/2015
• Est. Priority Date: 01/10/2014
• Status: Active Grant

• Current Assignee: Industrial Technology Research Institute
• Original Assignee: Industrial Technology Research Institute
• Inventors: Tseng, Yu-Chee, Chen, Lien-Wu, Tsai, Pei-Chuan, Chang, Chia-Chen, Lu, Yin-Chih
• Granted Patent: US 9,639,939 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30236 Traffic on road, railway or crossing
• CPC Class Codes: G06T 2207/30256 Lane; Road marking
• CPC Class Codes: G06T 7/70 Determining position or orientation of objects or cameras camera calibration G06T7/80
• CPC Class Codes: G08G 1/015 with provision for distinguishing between two or more types of vehicles, e.g. between motor-cars and cycles
• CPC Class Codes: G08G 1/04 using optical or ultrasonic detectors

Abstract

A method for vehicle positioning is provided, which includes the steps of identifying at least one vehicle in an image, obtaining identification information of each vehicle from the image, and transforming coordinates of each vehicle in the image into positioning information of the corresponding vehicle according to mapping information. The positioning information is a position of the corresponding vehicle in real world. Precise lane-level vehicle positioning can be achieved based on comparison with the identification information or the positioning information.

Claims

1. A vehicle positioning apparatus, comprising:

a storage unit storing an image and a mapping information; and

a processing unit, coupled to the storage unit, identifying at least one first vehicle in the image, obtaining identification information of each of the first vehicles from the image, and transforming image coordinates of each of the first vehicles into positioning information according to the mapping information, wherein the image coordinates are coordinates of a corresponding first vehicle in the image, and the positioning information is a position of the corresponding first vehicle in real world.

2. The vehicle positioning apparatus of claim 1, wherein the identification information at least comprises one of a plate number, a vehicle type and a color of the corresponding first vehicle.

3. The vehicle positioning apparatus of claim 1, wherein the image is divided into a plurality of regions, each of the regions comprises at least one pixel of the image, the mapping information comprises a position of each of the regions in real world, and the processing unit associates the image coordinates of each of the first vehicles with one of the regions and sets the position of the associated region as the positioning information of the associated first vehicle.

4. The vehicle positioning apparatus of claim 1, wherein the positioning information comprises latitude and longitude coordinates of the corresponding first vehicle in real world, or a lane number of a road where the corresponding first vehicle is located.

5. The vehicle positioning apparatus of claim 1, further comprising:

a communication unit, coupled to the processing unit, receiving the image and the mapping information, and sending out the identification information and the positioning information of each of the first vehicles.

6. The vehicle positioning apparatus of claim 1, further comprising:

a capturing unit, coupled to the processing unit, and capturing the image; and

a communication unit, coupled to the processing unit, and wirelessly broadcasting the identification information and the positioning information of each of the first vehicles.

7. The vehicle positioning apparatus of claim 6, wherein the communication unit further wirelessly broadcasts a timestamp, and the timestamp is a capturing time of the image.

8. A vehicle positioning apparatus, comprising:

a storage unit, storing an identification information and a positioning information of at least one first vehicle; and

a processing unit, coupled to the storage unit, determining that one of the first vehicles and a second vehicle are the same vehicle according to the identification information and the positioning information of each of the first vehicles, and obtaining positioning information of the second vehicle based on the positioning information of the determined first vehicle, wherein the positioning information is a position of a corresponding first vehicle or the second vehicle in real world.

9. The vehicle positioning apparatus of claim 8, wherein the identification information at least comprises one of a plate number, a vehicle type and a color of the corresponding first vehicle.

10. The vehicle positioning apparatus of claim 8, wherein the positioning information comprises latitude and longitude coordinates of the corresponding first vehicle or the second vehicle in real world, or a lane number of a road where the corresponding first vehicle or the second vehicle is located.

11. The vehicle positioning apparatus of claim 8, wherein the processing unit compares the identification information of each of the first vehicles with identification information of the second vehicle, and when the identification information of one of the first vehicles is identical to the identification information of the second vehicle, or when a part of the identification information of one of the first vehicles is identical to a corresponding part of the identification information of the second vehicle, the processing unit determines that the one first vehicle and the second vehicle are the same vehicle.

12. The vehicle positioning apparatus of claim 8, further comprising:

a sensing unit, coupled to the processing unit, and obtaining a relative position of at least one third vehicle surrounding the second vehicle in relative to the second vehicle, wherein for each of the first vehicles the processing unit calculates relative positions of the rest of the first vehicles in relative to the first vehicle, according to the positioning information of the first vehicles, and locates the first vehicle that makes the relative positions of the rest of the first vehicles most matching to the relative position of the third vehicles, and determines that the located first vehicle and the second vehicle are the same vehicle.

13. The vehicle positioning apparatus of claim 8, further comprising:

a communication unit, coupled to the processing unit, and receiving an image, image coordinates of each of the first vehicles, and a mapping information, wherein the image coordinates are coordinates of the corresponding first vehicle in the image, and the processing unit obtains the identification information of each of the first vehicles from the image and transforms the image coordinates of each of the first vehicles into the positioning information of the corresponding first vehicle according to the mapping information.

14. The vehicle positioning apparatus of claim 13, wherein the image is divided into a plurality of regions, each of the regions comprises at least one pixel of the image, the mapping information comprises a position of each of the regions in real world, and the processing unit associates the image coordinates of each of the first vehicles with one of the regions and sets the position of the associated region as the positioning information of the associated first vehicle.

15. The vehicle positioning apparatus of claim 8, further comprising:

a communication unit, coupled to the processing unit, and receiving an image and a mapping information, wherein the processing unit identifies the first vehicles in the image, obtains the identification information of each of the first vehicles from the image and transforms image coordinates of each of the first vehicles into the positioning information of the corresponding first vehicle according to the mapping information, wherein the image coordinates are coordinates of the corresponding first vehicle in the image.

16. The vehicle positioning apparatus of claim 8, further comprising:

a communication unit, coupled to the processing unit, and obtaining a timestamp, wherein the timestamp is a capturing time of the image, and the processing unit corrects the positioning information of the determined first vehicle according to a forward speed and a forward direction of the second vehicle and a time difference between a current time and the timestamp, and sets the positioning information of the second vehicle to the corrected positioning information.

17. A method for vehicle positioning, comprising:

identifying at least one first vehicle in an image;

obtaining an identification information of each of the first vehicles from the image; and

transforming image coordinates of each of the first vehicles into positioning information according to a mapping information, wherein the image coordinates are coordinates of a corresponding first vehicle in the image, and the positioning information is a position of the corresponding first vehicle in real world.

18. The method for vehicle positioning of claim 17, wherein the identification information at least comprises one of a plate number, a vehicle type and a color of the corresponding first vehicle.

19. The method for vehicle positioning of claim 17, wherein the image is divided into a plurality of regions, each of the regions comprises at least one pixel of the image, the mapping information comprises a position of each of the regions in real world, and the step of transforming the image coordinates of each of the first vehicles into the positioning information comprises:

associating the image coordinates of each of the first vehicles with one of the regions; and

setting the position of the associated region as the positioning information of the associated first vehicle.

20. The method for vehicle positioning of claim 17, wherein the positioning information comprises latitude and longitude coordinates of the corresponding first vehicle in real world, or a lane number of a road where the corresponding first vehicle is located.

21. The method for vehicle positioning of claim 17, further comprising:

receiving the image and the mapping information; and

sending out the identification information and the positioning information of each of the first vehicles.

22. The method for vehicle positioning of claim 17, further comprising:

capturing the image; and

wirelessly broadcasting the identification information and the positioning information of each of the first vehicles.

23. The method for vehicle positioning of claim 22, further comprising:

wirelessly broadcasting a timestamp, wherein the timestamp is a capturing time of the image.

24. A method for vehicle positioning, comprising:

according to identification information and positioning information of at least one first vehicle, determining that one of the first vehicles and a second vehicle are the same vehicle; and

obtaining positioning information of the second vehicle based on the positioning information of the determined first vehicle, wherein the positioning information is a position of a corresponding first vehicle or the second vehicle in real world.

25. The method for vehicle positioning of claim 24, wherein the identification information at least comprises one of a plate number, a vehicle type and a color of the corresponding first vehicle.

26. The method for vehicle positioning of claim 24, wherein the positioning information comprises latitude and longitude coordinates of the corresponding first vehicle or the second vehicle in real world, or a lane number of a road where the corresponding first vehicle or the second vehicle is located.

27. The method for vehicle positioning of claim 24, wherein the step of determining that one of the first vehicles and the second vehicle are the same vehicle comprises:

comparing the identification information of each of the first vehicles with identification information of the second vehicle; and

when the identification information of one of the first vehicles is identical to the identification information of the second vehicle, or when a part of the identification information of one of the first vehicles is identical to a corresponding part of the identification information of the second vehicle, determining that the one first vehicle and the second vehicle are the same vehicle.

28. The method for vehicle positioning of claim 24, wherein the step of determining that one of the first vehicles and the second vehicle are the same vehicle comprises:

obtaining a relative position of at least one third vehicle surrounding the second vehicle in relative to the second vehicle;

for each of the first vehicles, calculating relative positions of the rest of the first vehicles in relative to the first vehicle, according to the positioning information of the first vehicles; and

locating the first vehicle that makes the relative positions of the rest of the first vehicles most matching to the relative position of the third vehicles, and determining that the located first vehicle and the second vehicle are the same vehicle.

29. The method for vehicle positioning of claim 24, further comprising:

receiving an image, image coordinates of each of the first vehicles, and mapping information, wherein the image coordinates are coordinates of the corresponding first vehicle in the image;

obtaining the identification information of each of the first vehicles from the image; and

transforming the image coordinates of each of the first vehicles into the positioning information according to the mapping information.

30. The method for vehicle positioning of claim 29, wherein the image is divided into a plurality of regions, each of the regions comprises at least one pixel of the image, the mapping information comprises a position of each of the regions in real world, and the step of transforming the image coordinates of each of the first vehicles into the positioning information comprises:

associating the image coordinates of each of the first vehicles with one of the regions; and

setting the position of the associated region as the positioning information of the associated first vehicle.

31. The method for vehicle positioning of claim 24, further comprising:

receiving an image and mapping information;

identifying the first vehicles in the image;

obtaining the identification information of each of the first vehicles from the image; and

transforming image coordinates of each of the first vehicles into the positioning information of the corresponding first vehicle according to the mapping information, wherein the image coordinates are coordinates of the corresponding first vehicle in the image.

32. The method for vehicle positioning of claim 24, further comprising:

providing a forward speed and a forward direction of the second vehicle;

obtaining a timestamp, wherein the timestamp is a capturing time of the image;

correcting the positioning information of the determined first vehicle according to the forward speed and the forward direction of the second vehicle and a time difference between a current time and the timestamp; and

setting the positioning information of the second vehicle to the corrected positioning information.