Data processing apparatus, data processing method, and program

• US 9,946,950 B2
• Filed: 05/14/2013
• Issued: 04/17/2018
• Est. Priority Date: 09/14/2012
• Status: Active Grant

• Current Assignee: OKI Electric Industry Company Limited
• Original Assignee: OKI Electric Industry Company Limited
• Inventors: Mae, Takahiro, Watanabe, Takamitsu, Watanabe, Takahiro
• Primary Examiner(s): Beasley, Deidre
• Application Number:
  US14/428,352
• Publication Number:
  US 20150363659A1
• Time in Patent Office: 1,799 Days
• Field of Search: 348143
• CPC Class Codes: G06T 2207/30232 Surveillance
• CPC Class Codes: G06T 2207/30236 Traffic on road, railway or crossing
• CPC Class Codes: G06T 2207/30242 Counting objects in image
• CPC Class Codes: G06T 3/00 Geometric image transformations in the plane of the image
• CPC Class Codes: G06T 7/80 Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
• CPC Class Codes: G06V 20/54 of traffic, e.g. cars on the road, trains or boats
• CPC Class Codes: G08G 1/04 using optical or ultrasonic detectors

Abstract

An aspect of the present invention provides a data processing apparatus, including: an image acquisition section that acquires a captured image depicting a road along which vehicles pass; a calibration section that computes a road parameter for converting coordinates in the captured image to coordinates in real space based on the captured image and road data related to the road; a vehicle lane region detection section that detects a vehicle lane region in the captured image based on the captured image and the road parameter; and a processing region setting section that, based on the vehicle lane region, sets a processing region in the vehicle lane region for detecting a vehicle passing.

Claims

1. A data processing apparatus, comprising:

an image acquisition section that acquires a captured image depicting a road along which vehicles pass;

a calibration section that computes a road parameter that is an equation for converting two dimensional coordinates in the captured image to three dimensional coordinates in real space based on the captured image and road data related to the road;

a vehicle lane region detection section that detects a vehicle lane region in the captured image based on the captured image and the road parameter;

a processing region setting section that, based on the vehicle lane region, sets a processing region in the vehicle lane region for detecting a vehicle passing; and

a processing region adjustment section that adjusts the processing region based on a blocking object that blocks a portion of the vehicle lane region;

wherein when the blocking object blocks a portion of the processing region, the processing region adjustment section masks a portion of the processing region blocked by the blocking object and determines a size of a masking portion that masks the processing region and a position of the processing region based on an amount of decrease in detection precision due to the size of the masking portion and based on an amount of decrease in detection precision due to the position of the processing region.

2. The data processing apparatus of claim 1, wherein the processing region setting section sets the processing region to an end portion at a near side of the vehicle lane region.

3. The data processing apparatus of claim 2, wherein the processing region setting section disposes an entire near-side end portion of the processing region within the captured image.

4. The data processing apparatus of claim 1, wherein the processing region adjustment section sets the processing region to a position avoiding the blocking object and disposes the processing region at a near-side end portion of a region to a far side of the blocking object.

5. The data processing apparatus of claim 1, wherein the processing region adjustment section determines a size of the masking portion that masks the processing region and the position of the processing region such that a value of a sum of the amount of decrease in detection precision due to the size of the masking portion and the amount of decrease in detection precision due to the position of the processing region is a minimum.

6. The data processing apparatus of claim 1, wherein:

there is a plurality of the vehicle lane regions present; and

the processing region adjustment section sets at least a portion of a processing region of a vehicle lane region not blocked by the blocking object based on at least the portion of the processing region of the vehicle lane region blocked by the blocking object.

7. The data processing apparatus of claim 1, wherein:

the processing region setting section sets a boundary portion between the vehicle lane region and a road side strip region as a two wheeled vehicle detection processing region.

8. The data processing apparatus of claim 7, wherein:

the processing region setting section sets a processing region for vehicles other than two wheeled vehicles at a position avoiding the two wheeled vehicle detection processing region.

9. The data processing apparatus of claim 1, wherein the processing region setting section adjusts the processing region based on user operation.

10. The data processing apparatus of claim 1, wherein the vehicle lane region detection section detects a vehicle lane region in the captured image based on user operation.

12. The data processing apparatus of claim 1, wherein the processing region is three dimensional.

11. A data processing method comprising:

a step of acquiring a captured image depicting a road along which vehicles pass;

a step of computing a road parameter that is an equation for converting two dimensional coordinates in the captured image to three dimensional coordinates in real space based on the captured image and road data related to the road;

a step of detecting a vehicle lane region in the captured image based on the captured image and the road parameter;

a step of, based on the vehicle lane region, setting a processing region in the vehicle lane region for detecting a passing vehicle; and

a step of adjusting the processing region based on a blocking object that blocks a portion of the vehicle lane region;

wherein

in the adjusting step, when the blocking object blocks a portion of the processing region, the portion in the processing region blocked by the blocking object is masked, and a size of a masking portion that masks the processing region and a position of the processing region are determined based on an amount of decrease in detection precision due to the size of the masking portion and based on an amount of decrease in detection precision due to the position of the processing region.

13. The data processing method of claim 11, wherein in the setting step, the processing region is set to an end portion at a near side of the vehicle lane region.

14. The data processing method of claim 13, wherein in the setting step, an entire near-side end portion of the processing region is disposed within the captured image.

15. The data processing method of claim 11, wherein

in the adjusting step, the processing region is disposed at a position that avoids the blocking object and is at a near-side end portion of a region to a far side of the blocking object.

16. The data processing method of claim 11, wherein in the adjusting step, a size of the masking portion that masks the processing region and the position of the processing region are determined such that a value of a sum of the amount of decrease in detection precision due to the size of the masking portion and the amount of decrease in detection precision due to the position of the processing region is a minimum.

17. The data processing method of claim 11, wherein

there is a plurality of the vehicle lane regions present, and

the adjusting step includes setting at least a portion of a processing region of a vehicle lane region not blocked by the blocking object based on at least the portion of the processing region of the vehicle lane region blocked by the blocking object.

18. The data processing method of claim 11, wherein

the setting step includes setting a boundary portion between the vehicle lane region and a road side strip region as a two wheeled vehicle detection processing region.

19. The data processing method of claim 18, wherein:

the setting step includes setting a processing region for vehicles other than two wheeled vehicles at a position avoiding the two wheeled vehicle detection processing region.

20. The data processing method of claim 11, wherein the setting step includes adjusting the processing region based on user operation.

21. The data processing method of claim 11, wherein the setting step includes detecting a vehicle lane region in the captured image based on user operation.

22. The data processing method of claim 11, wherein the processing region is three dimensional.