Vehicle periphery monitor device

• US 10,565,438 B2
• Filed: 01/10/2013
• Issued: 02/18/2020
• Est. Priority Date: 03/12/2012
• Status: Active Grant

• Current Assignee: Arriver Software AB (Qualcomm, Inc.)
• Original Assignee: Honda Motor Co., Ltd. (Honda Motor Company)
• Inventors: Nagaoka, Nobuharu, Aimura, Makoto
• Primary Examiner(s): Czekaj, Dave
• Assistant Examiner(s): Abimbola, Kehinde
• Application Number:
  US14/378,222
• Publication Number:
  US 20150035962A1
• Time in Patent Office: 2,595 Days
• CPC Class Codes: B60R 1/24 in front of the vehicle
• CPC Class Codes: B60R 1/30 providing vision in the non-visible spectrum, e.g. night or infrared vision
• CPC Class Codes: B60R 2300/307 virtually distinguishing relevant parts of a scene from the background of the scene
• CPC Class Codes: B60R 2300/8033 for pedestrian protection
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06V 10/143 Sensing or illuminating at different wavelengths
• CPC Class Codes: G06V 20/56 exterior to a vehicle by using sensors mounted on the vehicle
• CPC Class Codes: G06V 20/58 Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
• CPC Class Codes: G06V 20/584 of vehicle lights or traffic lights
• CPC Class Codes: G06V 2201/07 Target detection
• CPC Class Codes: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
• CPC Class Codes: G08G 1/166 for active traffic, e.g. moving vehicles, pedestrians, bikes
• CPC Class Codes: H04N 5/33 Transforming infrared radiation cameras or camera modules for generating image signals from infrared radiation H04N23/20; circuitry of SSIS for transforming infrared radiation into image signals H04N25/20

Abstract

Provided is a vehicle periphery monitor device for accurately distinguishing between and detecting two side-by-side pedestrians and a vehicle that is lighting lights. With regard to a pedestrian candidate having at least two head candidates, a reference image creation unit creates the peripheral image of one of the head candidates as a reference image and creates an inverted image in which the right and left sides of the reference image are inverted. An object determination unit sets the peripheral image of the other heat candidate as a comparative image, and determines whether the head candidates are the pedestrians or the vehicle on the basis of the consistency of the reference image and the inverted image relative to the comparative image.

Claims

1. A vehicle periphery monitoring apparatus for monitoring pedestrians in periphery of a vehicle based on an image captured by an infrared camera that is mounted on the vehicle, comprising:

a head candidate extractor for extracting at least two head candidates, which are spaced apart from each other in a substantially horizontal direction, from the image;

a reference image generator for generating a peripheral image including one of the extracted at least two head candidates as a reference image; and

a target object determiner, which uses a peripheral image including another of the head candidates as a comparison image, determining a degree of horizontal symmetry between the comparison image including the another of the at least two head candidates and the reference image including the one of the at least two head candidates and judging whether the at least two head candidates represent pedestrians or a vehicle based on the degree of horizontal symmetry between the comparison image and the reference image, and

wherein the reference image generator generates the reference image in such a manner that another feature is included in the peripheral image in addition to the one of the extracted at least two head candidates.

2. The vehicle periphery monitoring apparatus according to claim 1, wherein the reference image generator generates an image of only the one head candidate as the peripheral image including the one head candidate for use as the reference image;

and

the target object determiner uses an image of only the other head candidate as the peripheral image including the other head candidate for use as the comparison image, and judges whether the at least two head candidates represent pedestrians or a vehicle based on the degree of symmetry between the image of only the other head candidate and the image of only the one head candidate.

3. The vehicle periphery monitoring apparatus according to claim 1, wherein the reference image generator generates the peripheral image including the one of the extracted at least two head candidates as the reference image, and generates an inverted image, which is a horizontal inversion of the reference image;

and

the target object determiner uses the peripheral image including the other head candidate as the comparison image, and judges whether the at least two head candidates represent pedestrians or a vehicle based on a degree of coincidence between the reference image and the comparison image, and a degree of coincidence between the inverted image and the comparison image.

4. The vehicle periphery monitoring apparatus according to claim 1, wherein the other feature comprises a substantially vertically extending edge, which is offset from the head candidates to the left or right of the head candidates.

5. The vehicle periphery monitoring apparatus according to claim 1, wherein the target object determiner judges whether the at least two head candidates represent pedestrians or lights mounted in left and right positions on the vehicle.

6. A vehicle periphery monitoring method of monitoring pedestrians in periphery of a vehicle based on an image captured by an infrared camera that is mounted on the vehicle, comprising steps of:

(i) extracting, by using a computer, at least two head candidates, which are spaced apart from each other in a substantially horizontal direction, from the image;

(ii) generating, by using a computer, a peripheral image including one of the extracted at least two head candidates as a reference image; and

(iii) determining, by using a computer, by using a peripheral image including another of the head candidates as a comparison image, a degree of horizontal symmetry between the comparison image including the another of the at least two head candidates and the reference image including the one of the at least two head candidates and judging whether the at least two head candidates represent pedestrians or a vehicle based on the degree of horizontal symmetry between the comparison image and the reference image, and

wherein the step (ii) generates the reference image in such a manner that another feature is included in the peripheral image in addition to the one of the extracted at least two head candidates.