IMAGE GENERATOR

• US 20130093851A1
• Filed: 10/12/2012
• Published: 04/18/2013
• Est. Priority Date: 10/13/2011
• Status: Active Grant

• Current Assignee: Aisin Seiki Co., Ltd. (Aisin Corp.)
• Original Assignee: Aisin Seiki Co., Ltd. (Aisin Corp.)
• Inventors: WATANABE, Kazuya, YAMAMOTO, Kinji
• Granted Patent: US 9,019,347 B2
• Time in Patent Office: Days
• US Class Current: 348/46
• CPC Class Codes: G01S 13/867 Combination of radar systems with cameras
• CPC Class Codes: G01S 13/931 of land vehicles
• CPC Class Codes: G01S 15/58 Velocity or trajectory determination systems; Sense-of-movement determination systems velocity measurement in imaging systems G01S15/8979
• CPC Class Codes: G01S 15/931 of land vehicles
• CPC Class Codes: G01S 2013/932 using own vehicle data, e.g. ground speed, steering wheel direction

Abstract

An image generator is provided which generates a monitor display image that facilitates easy recognition of a three-dimensional object in an overhead view image. An image generator includes: an overhead view image generation section for generating an overhead view image by performing a projective transformation, with a virtual viewpoint above a vehicle, of an image captured by an on-board camera for capturing an image of a surrounding region of the vehicle; a three-dimensional object detection section for recognizing a three-dimensional object present in the surrounding region and outputting three-dimensional object attribute information showing an attribute of the three-dimensional object; and an image composition section for generating a monitor display image for vehicle driving assistance by performing image composition of a grounding plane mark showing a grounding location of the three-dimensional object with a portion at the grounding location in the overhead view image, based on the three-dimensional object attribute information.

Claims

1. An image generator comprising:

an overhead view image generation section for generating an overhead view image by performing a projective transformation, with a virtual viewpoint above a vehicle, of an image captured by an on-board camera for capturing an image of a surrounding region of the vehicle;

a three-dimensional object detection section for recognizing a three-dimensional object present in the surrounding region and outputting three-dimensional object attribute information showing an attribute of the three-dimensional object; and

an image composition section for generating a monitor display image for vehicle driving assistance by performing image composition of a grounding plane mark showing a grounding location of the three-dimensional object with a portion at the grounding location in the overhead view image, based on the three-dimensional object attribute information.

2. The image generator according to claim 1, wherein the grounding plane mark is in a flattened shape, and an inclined posture of the grounding plane mark is determined so that a line of direction from the vehicle to the three-dimensional object becomes orthogonal to a major axis of the grounding plane mark.

3. The image generator according to claim 1, wherein the grounding plane mark is in a shape of an ellipse.

4. The image generator according to claim 1, wherein a size of the grounding plane mark is determined in accordance with the three-dimensional object attribute information.

5. The image generator according to claim 1, wherein a size of the grounding plane mark is set larger than a width of the three-dimensional object in the overhead view image, based on a width of the three-dimensional object contained in the three-dimensional object attribute information.

6. The image generator according to claim 1, wherein in the image composition performed by the image composition section, a three-dimensional object image layer containing the three-dimensional object alone is generated from a basic image layer containing the overhead view image, the grounding plane mark is placed between the basic image layer and the three-dimensional object image layer, and at the same time, positioned at the grounding location of the three-dimensional object in the overhead view image.

7. The image generator according to claim 1, wherein in the image composition performed by the image composition section, the grounding plane mark is superimposed on the grounding location of the three-dimensional object in the overhead view image.

8. The image generator according to claim 1, wherein the overhead view image generation section includes:

a grounding plane mark storing section for storing a plurality of the grounding plane marks; and

a grounding plane mark output section for extracting an appropriate grounding plane mark from the grounding plane mark storing section based on the three-dimensional object attribute information, and sending the selected grounding plane mark to the image composition section.

9. The image generator according to claim 1, wherein an indication of a distance from the grounding location of the three-dimensional object to the vehicle is added in the vicinity of the grounding plane mark.