Vehicle detection apparatus and vehicle detection method

• US 9,196,160 B2
• Filed: 01/31/2014
• Issued: 11/24/2015
• Est. Priority Date: 08/03/2011
• Status: Active Grant

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: Aoki, Yasuhiro, Sato, Toshio, Takahashi, Yusuke
• Primary Examiner(s): Mehta, Bhavesh
• Assistant Examiner(s): Lee, Jonathan S
• Application Number:
  US14/170,284
• Publication Number:
  US 20140147008A1
• Time in Patent Office: 662 Days
• US Class Current: 1/1
• CPC Class Codes: G01B 11/002 for measuring two or more coordinates
• CPC Class Codes: G01C 11/06 by comparison of two or more pictures of the same area
• CPC Class Codes: G06T 2207/10012 Stereo images
• CPC Class Codes: G06T 2207/30236 Traffic on road, railway or crossing
• CPC Class Codes: G06T 7/593 from stereo images
• CPC Class Codes: G06T 7/75 involving models
• CPC Class Codes: G06V 10/243 by compensating for image skew or non-uniform image deformations
• CPC Class Codes: G06V 20/10 Terrestrial scenes scenes under surveillance with static cameras G06V20/52; scenes perceived from the exterior of a vehicle G06V20/56; scenes perceived from the interior of a vehicle G06V20/59
• CPC Class Codes: G06V 20/64 Three-dimensional objects
• CPC Class Codes: G06V 2201/08 Detecting or categorising vehicles
• CPC Class Codes: G08G 1/0175 by photographing vehicles, e.g. when violating traffic rules
• CPC Class Codes: G08G 1/123 indicating the position of vehicles, e.g. scheduled vehicles; Managing passenger vehicles circulating according to a fixed timetable, e.g. buses, trains, tramstransmission of navigation instructions to vehicles G08G1/0968

Abstract

A vehicle detection apparatus according to an embodiment comprises a controller detecting a vehicle from an image obtained by photographing the vehicle. The controller extracts a plurality of line-segment components indicating a boundary between a specific region of the vehicle and a vehicle body and included in the image. The controller measures a position of the vehicle based on coordinate information between the extracted line-segment components and photographing position information of the image.

Claims

1. A vehicle detection apparatus comprising:

a processor, the processor being configured to;

detect a vehicle from an image obtained by photographing the vehicle, the image including a left image and a right image that are photographed from left and right directions with respect to the vehicle;

extract a plurality of line-segment components indicating a boundary between a specific region of the vehicle and a vehicle body and included in the image for each of the left and right images; and

align at least one line-segment component between the left and right images among the line-segment components forming a closed loop for each of the left and right images, and measure a position of the closed loop as the position of the vehicle based on coordinate information between the aligned line-segment components and photographing position information where the left and right images have been photographed.

2. The vehicle detection apparatus according to claim 1, wherein the processor is further configured to:

execute a polygon approximation by executing approximation with a polygon forming the closed loop using some of the line-segment components extracted from the image, for each of the left and right images.

3. The vehicle detection apparatus according to claim 1, wherein the processor is configured to align all of the line-segment components forming the closed loop.

4. The vehicle detection apparatus according to claim 1, wherein left and right photographing positions of the photographing module are placed to include a windshield of the vehicle and side surfaces of the vehicle, and are arranged along a direction substantially parallel with a longitudinal direction of an upper side and a lower side of the windshield.

5. The vehicle detection apparatus according to claim 1, wherein the processor is further configured to:

classify the extracted line-segment components according to directions, change parameters used in extraction of the line-segment components based on a number and a length of the line-segment components for each of the directions to increase the number of the line-segment components and reduce the length of the line-segment components, and re-execute processing of extracting the line-segment components based on the changed parameters.

6. The vehicle detection apparatus according to claim 2, wherein the processor is further configured to:

extract a plurality of first line-segment components forming the windshield region of the vehicle; and

extract a plurality of second line-segment components forming a rectangular region of a number plate frame of the vehicle, and

wherein the processor executes the polygon approximation using the extracted second line-segment components, when the closed loop cannot be formed based on the extracted first line-segment components.

7. The vehicle detection apparatus according to claim 5, wherein the processor changes the parameters used in extraction of the line-segment components to reduce the number of the line-segment components and increase the length of the line-segment components when the windshield region has a size greater than a reference size, and to increase the number of the line-segment components and reduce the length of the line-segment components when the windshield region has a size equal to or less than the reference size.

8. The vehicle detection apparatus according to claim 1, wherein the processor is further configured to calculate a length of a bottom side of the windshield region of the vehicle as a width of the vehicle, based on the coordinate information.

9. The vehicle detection apparatus according to claim 1, wherein the processor is further configured to calculate a height of an upper side of the windshield region of the vehicle as a height of the vehicle, based on the coordinate information.

10. A vehicle detection method applied to a vehicle detection apparatus detecting a vehicle from an image obtained by photographing the vehicle, the image including a left image and a right image that are photographed from left and right directions with respect to the vehicle, and the method comprising:

extracting a plurality of line-segment components indicating a boundary between a specific region of the vehicle and a vehicle body and included in the image for each of the left and right images; and

aligning at least one line-segment component between the left and right images among the line-segment components forming a closed loop for each of the left and right images, and measuring a position of the closed loop as the position of the vehicle based on coordinate information between the aligned line-segment components and photographing position information where the left and right images have been photographed.