Vehicle image processing apparatus and vehicle image processing method

Patent metadata

Field	Value
Publication number	US-9840199-B2
Application number	US-201615188460-A
Country	US
Kind code	B2
Filing date	Jun 21, 2016
Priority date	May 29, 2008
Publication date	Dec 12, 2017
Grant date	Dec 12, 2017

Abstract

A vehicle image processing apparatus includes a group of cameras, a drawing unit that converts a captured image into an image viewed along a line of sight running from a predetermined position in a predetermined direction, a viewing-line-of-sight changing unit that detects whether a first line of sight is switched to a second line of sight, and a viewing-line-of-sight generation/updating unit that acquires parameters concerning the first and second lines of sight after detecting the switching and generates a parameter which is gradually changed from the parameter of the first line of sight to the parameter of the second line of sight. Moreover, the drawing unit generates, on the basis of the gradually changed parameter, an image which is gradually changed from an image viewed along the first line of sight to an image viewed along the second line of sight.

First claim

What is claimed is:

1. A vehicle image processing apparatus comprising:
a memory configured to store a captured image which is an image that has captured an area around a vehicle with use of at least one camera; and
a processor coupled to the memory, the processor configured to:
acquire the captured image;
convert, using at least one predetermined projection shape, the captured image into an image viewed along a virtual line of sight that is a line of sight running from a predetermined position in a predetermined direction;
detect whether a virtual line of sight is switched from a position of a first virtual line of sight to a position of a second virtual line of sight which is a different virtual line of sight, the position of the first virtual line of sight associated with a parameter value of at least one selected from a predetermined position and a direction of the virtual line of sight and the position of the second virtual line of sight being associated with a parameter value different from the parameter value associated with the position of the first virtual line of sight;
acquire at least one type of parameter value associated with a virtual line of sight for each position of the first virtual line of sight and the second virtual line of sight after detecting that the virtual line of sight is switched from the position of the first virtual line of sight to the position of the second virtual line of sight, and generate a parameter value of a position of a virtual line of sight that is gradually changed along a predetermined path connecting the position of the first virtual line of sight and the position of the second virtual line of sight;
convert the captured image to an image viewed along at least one virtual line of sight among the first virtual line of sight and the second virtual line of sight using a projection map which includes a relationship between a position of a pixel of the captured image and a position of a pixel of an image viewed along the first virtual line of sight or the second virtual line of sight, and generate the converted image to be viewed from the virtual line of sight included in the virtual line of sight group changing from the first virtual line of sight to the second virtual line of sight not using a projection map but using a predetermined projection shape with the linking of the position of pixels calculated by the positional relationship between the image-capturing camera and the projection shape, the linking indicating a relationship between positions on the projection shape and pixels in the captured image; and
detect that the position of the first virtual line of sight is switched to the position of the second virtual line of sight when a switching occurs of a pre-registered virtual line of sight or when a difference between unchanged and changed virtual lines of sight is greater than or equal to a specified value.

2. The vehicle image processing apparatus according to claim 1 , wherein the processor is configured to change the drawing part of the predetermined projection shape in the converted image based on the generated parameter value so that the converted image is a part of the converted image group which is gradually changed from a first image viewed along the position of the first virtual line of sight to a second image viewed along the position of the second virtual line of sight.

3. The vehicle image processing apparatus according to claim 1 , wherein
when the captured image is converted to the image viewed along at least one virtual line of sight among the first virtual line of sight and the second virtual line of sight, the conversion of the captured image is performed without using a predetermined projection shape, and
the virtual line of sight group does not include at least one selected from the first virtual line of sight and the second virtual line of sight.

4. A vehicle image processing method comprising:
acquiring a captured image which is an image that has captured an area around a vehicle with use of at least one camera;
using at least one predetermined projection shape to convert the captured image into an image viewed along a virtual line of sight that is a line of sight running from a predetermined position in a predetermined direction;
detecting whether a virtual line of sight is switched from a position of a first virtual line of sight to a position of a second virtual line of sight which is a different virtual line of sight, the position of the first virtual line of sight associated with a parameter value of at least one selected from a predetermined position and a direction of the virtual line of sight and the position of the second virtual line of sight being associated with a parameter value different from the parameter value associated with the position of the first virtual line of sight;
acquiring at least one type of parameter value associated with a virtual line of sight for each position of the first virtual line of sight and the second virtual line of sight after detecting that the virtual line of sight is switched from the position of the first virtual line of sight to the position of the second virtual line of sight, and generating a parameter value of a position of a virtual line of sight that is gradually changed along a predetermined path connecting the position of the first virtual line of sight and the position of the second virtual line of sight;
converting the captured image to an image viewed along at least one virtual line of sight among the first virtual line of sight and the second virtual line of sight using a projection map which includes a relationship between a position of a pixel of the captured image and a position of a pixel of an image viewed along the first virtual line of sight or the second virtual line of sight, and generating the converted image to be viewed from the virtual line of sight included in the virtual line of sight group changing from the first virtual line of sight to the second virtual line of sight not using a projection map but using a predetermined projection shape with the linking of the position of pixels calculated by the positional relationship between the image-capturing camera and the projection shape, the linking indicating a relationship between positions on the projection shape and pixels in the captured image; and
detecting that the position of the first virtual line of sight is switched to the position of the second virtual line of sight when a switching occurs of a pre-registered virtual line of sight or when a difference between unchanged and changed virtual lines of sight is greater than or equal to a specified value.

5. The vehicle image processing method according to claim 4 , further comprising changing the drawing part of the predetermined projection shape in the converted image based on the generated parameter value so that the converted image is a part of the converted image group which is gradually changed from a first image viewed along the position of the first virtual line of sight to a second image viewed along the position of the second virtual line of sight.

6. The vehicle image processing method according to claim 4 , wherein
when converting the captured image to the image viewed along at least one virtual line of sight among the first virtual line of sight and the second virtual line of sight, the conversion of the captured image is performed without using a predetermined projection shape, and
the virtual line of sight group does not include at least one selected from the first virtual line of sight and the second virtual line of sight.

Assignees

• Fujitsu Ltd

Inventors

• Kitaura Asako
• Shimizu Seiya
• Yamada Hiroshi

Classifications

• G06T2207/30252

  Vehicle exterior; Vicinity of vehicle · CPC title

• B60R2300/105

  using multiple cameras · CPC title

• G06T3/0056

  Physics · mapped topic

• G06T5/006

  Physics · mapped topic

• B60R1/00 Primary

  Optical viewing arrangements; Real-time viewing arrangements for drivers or passengers using optical image capturing systems, e.g. cameras or video systems specially adapted for use in or on vehicles · CPC title