Approaching object detection system

• US 8,712,097 B2
• Filed: 11/19/2009
• Issued: 04/29/2014
• Est. Priority Date: 11/19/2008
• Status: Active Grant

• Current Assignee: Clarion Co., Ltd. (Faurecia SA)
• Original Assignee: Clarion Co., Ltd. (Faurecia SA)
• Inventors: Uchida, Yoshitaka, Aoki, Toshiyuki
• Primary Examiner(s): Park, Chan
• Assistant Examiner(s): LE, HA N
• Application Number:
  US13/129,869
• Publication Number:
  US 20110228985A1
• Time in Patent Office: 1,622 Days
• Field of Search: None
• US Class Current: 382/103
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/20068 Projection on vertical or horizontal image axis
• CPC Class Codes: G06T 2207/20132 Image cropping
• CPC Class Codes: G06T 2207/30261 Obstacle
• CPC Class Codes: G06T 7/215 Motion-based segmentation

Abstract

An approaching object detection system, approaching object can be accurately detected while reducing the load on a calculation processing. A first moving region detection unit (30) detects (#3) only an optical flow substantially in horizontal direction in an image (P) captured by a camera (10) (#1) and sets (#4) a rectangular image portion (Q) containing a region moving in a substantially horizontal direction according to the detected optical flow. A second moving region detection unit (40) obtains a distribution (profile) of signal values of the set rectangular image portion (Q), (#5) in a vertical direction (longitudinal direction). Furthermore, the second moving region detection unit (40) correlates distributions of signal values of image portions (Q, Q) of two continuous images (P, P) in time series (#6) based on dynamic programming based processing to obtain an enlargement rate (#7). An approaching object determining unit (50) determines according to the enlargement rate whether the object is actually approaching.

Claims

1. An approaching object detection system comprising:

a camera which is mounted on a vehicle to capture an image in the vicinity of the vehicle;

a processor configured to;

perform, on a plurality of continuous images captured in time series by the camera, optical flow processing in which a velocity vector in a certain direction in the images in time series is detected, so that image portions of the images including an object moving in the certain direction is identified;

obtain a range of variation in luminance values of pixels of the identified image portions in a direction different from the certain direction and correlate the distributions of the continuous images in time series with each other to compute an enlargement rate of size of the image portions; and

determine, by calculating the enlargement rate as the reciprocal of tan(theta) where theta is based on the image portions of consecutive input images, that the object corresponding to the image portions is approaching the camera, when the enlargement rate is increasing.

2. An approaching object detection system according to claim 1, wherein the (theta) is an angle between a hypotenuse and a base of a right triangle in which edges of image portions Q(t+1), Q(t+2) in the direction different from the certain direction configure two sides of the triangle to define the right angle and Q(t+2) is the base.

3. The approaching object detection system according to claim 1, wherein:

the certain direction is a direction within a predetermined range including a horizontal direction; and

the direction different from the certain direction is a vertical direction.

4. The approaching object detection system according to claim 1, wherein the processor is further configured to exclude at least one of a sky region and a ground region from the image captured by the camera before extracting the image portion by the optical flow processing.

5. The approaching object detection system according to claim 1, wherein the processor is further configured to:

acquire vehicle information on a traveling condition of the vehicle including a vehicle speed; and

correct, when the vehicle information indicates a movement of the vehicle, a size of the image in the continuous images in time series in such a direction as to reduce a change in size of an image according to the movement of the vehicle.

6. The approaching object detection system according to claim 5, wherein

the processor is further configured to change an enlargement rate of the image in the size correction according to a vehicle moving distance in the continuous images in time series.

7. The approaching object detection system according to claim 1,

wherein the processor is further configured to:

obtain a variation in shape of a region occupied by the object moving in the certain direction between continuous images in time series; and

determine the object as a pedestrian when the variation in shape of the region is greater than a preset value.

8. The approaching object detection system according to claim 7, wherein the processor is further configured to obtain a difference in area of regions occupied by a moving object which has moved in the certain direction in the continuous images in time series and set a value resulting from accumulation of the differences over the continuous images in time series as the valuation.