Obstacle detection apparatus and method

• US 20050018043A1
• Filed: 08/17/2004
• Published: 01/27/2005
• Est. Priority Date: 02/29/2000
• Status: Active Grant

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: Hattori, Hiroshi, Onoguchi, Kazunori, Takeda, Nobuyuki
• Granted Patent: US 7,317,474 B2
• Time in Patent Office: Days
• US Class Current: 348/119
• CPC Class Codes: H04N 7/181 for receiving images from a plurality of remote sources

Abstract

A plurality of cameras respectively input an image from different camera positions. The plurality of cameras is on a moving object. An image memory stores a plurality of images input by the plurality of cameras. An image transformation unit transforms one image input by a first camera using each of a plurality of transformation parameters each representing a geometrical relationship among a predetermined plane, the first camera, and a second camera, and generates a plurality of transformed images from a view position of the second camera. A matching processing unit compares each of the plurality of transformed images with another image input by the second camera for each area consisting of pixels, and calculates a coincidence degree of each area between each transformed image and another image. An obstacle detection unit detects an obstacle area consisting of areas each having a coincidence degree below a threshold from another image.

Claims

1-21. -21 (Canceled).

22. :

A computer-implemented obstacle detection system, comprising;

a first camera and a second camera each configured to input images, the first camera and the second camera being disposed on a moving object on a road plane, a view position of the first camera being different from a view position of the second camera on the moving object;

an image memory configured to store a plurality of images input through the first camera and the second camera;

an image transformation unit configured to transform an image input through the first camera into a plurality of transformed images using each transformation parameter previously calculated based on different geometrical relationships among the road plane, the first camera and the second camera, wherein each transformation parameter differently represents a transformation from the view position of the second camera;

a matching processing unit configured to compare each area of the same position in each of the plurality of transformed images with a corresponding area of the same position in another image input through the second camera, to calculate coincidence degrees of compared areas of the same position between each transformed image and another image, and to select a maximum coincidence degree from the coincidence degrees of the compared areas of the same position; and

an obstacle detection unit configured to detect an obstacle area based on areas having the maximum coincidence degree in which the maximum coincidence degree is below a threshold.

23. :

The computer-implemented system according to claim 22,

wherein the first camera is one of a left camera and a right camera on a vehicle, and the second camera is the other of the left camera and the right camera, and

wherein the left camera and the right camera respectively take a left image and a right image of front area along an advance direction of the vehicle.

24. :

The computer-implemented system according to claim 23,

wherein an optical axis of the left camera and an optical axis of the right camera are parallel along the advance direction of the vehicle.

25. :

The computer-implemented system according to claim 23,

wherein the plurality of transformation parameters respectively represents a different transformation from the view position of the second camera based on a different posture of the vehicle on the road plane, and each transformation parameter is previously calculated based on a geometrical relationship among the road plane, the left camera, and the right camera in correspondence with each posture of the vehicle.

26. :

The computer-implemented system according to claim 23,

wherein said image transformation unit transforms one of the left image and the right image into a plurality of images by using each transformation parameter from the view position of the other of the left camera and the right camera.

27. :

The computer-implemented system according to claim 22,

wherein said image transformation unit transforms the one image by using a standard transformation parameter, and generates one transformed image from the view position of the second camera.

28. :

The computer-implemented system according to claim 22,

wherein said matching processing unit divides each transformed image into a plurality of areas, compares each area with a search area including a correspondence area of the same position on another image by shifting the correspondence area in the search area, calculates coincidence degrees between the area and the correspondence area for each shift position, and selects a maximum value from the coincidence degrees between the area and the correspondence area for all shift positions.

29. :

The computer-implemented system according to claim 28,

wherein said matching processing unit selects a maximum coincidence degree from maximum values of each area of the same position of all transformed images, and creates a coincidence degree image consisting of maximum coincidence degrees of each area.

30. :

The computer-implemented system according to claim 28,

wherein, if a coincidence degree of one shift position for an area of one transformed image is above a threshold, said matching processing unit selects the coincidence degree as the maximum coincidence degree of the area and completes the matching processing for the area of the same position of all transformed images.

31. :

The computer-implemented system according to claim 28,

wherein at least one of a size of the search area, a shift pitch of pixels in the search area, and a number of the plurality of transformation parameters, is changed according to a position of the area on the transformed image.