IMAGE PROCESSING APPARATUS AND IMAGE PROCESSING METHOD

• US 20150269448A1
• Filed: 12/16/2014
• Published: 09/24/2015
• Est. Priority Date: 03/24/2014
• Status: Active Grant

• Current Assignee: Alpine Electronics Incorporated (Alps Alpine Co., Ltd.)
• Original Assignee: Toshiba Corporation
• Inventors: KOSAKI, Masanori
• Granted Patent: US 9,305,222 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: B60R 11/04 Mounting of cameras operative during drive; Arrangement of controls thereof relative to the vehicle
• CPC Class Codes: G06F 18/28 Determining representative reference patterns, e.g. by averaging or distorting; Generating dictionaries
• CPC Class Codes: G06V 10/247 by affine transforms, e.g. correction due to perspective effects; Quadrilaterals, e.g. trapezoids
• 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 2201/07 Target detection
• CPC Class Codes: H04N 5/28 Mobile studios

Abstract

According to one embodiment, an image processing apparatus and an image processing method includes a dictionary generation unit, a processed image generation unit, and a detection unit. The dictionary generation unit generates a single dictionary using a plurality of images of a detection target object picked up by a camera. The plurality of images is obtained by arranging the detection target object at a corresponding plurality of positions in a predetermined range such that a predetermined visual axis of the camera is parallel with a normal-line direction of a detection target surface of the detection target object. The processed image generation unit generates a processed image having the predetermined visual axis as a normal-line direction, based on an image picked up by the camera after generation of the dictionary. The detection unit detects the detection target object included in the processed image by determining a feature value using the dictionary.

Claims

1. An image processing apparatus comprising:

a dictionary generation unit configured to generate a dictionary as a single dictionary in advance using a plurality of images of a detection target object picked up in advance by a camera, the camera being provided on a vehicle and picking up an image around the vehicle with a wide viewing angle, the plurality of images being obtained by arranging the detection target object at a corresponding plurality of positions in a predetermined range within an image-pickup range of the camera so as to make a predetermined visual axis of the camera and a normal-line direction of a detection target surface of the detection target object parallel to each other, and the plurality of images being obtained by picking up each of the plurality of images by the camera at the corresponding plurality of positions;

a processed image generation unit configured to generate a processed image having the predetermined visual axis as a normal-line direction, based on an image picked up by the camera after generation of the dictionary; and

a detection unit configured to detect the detection target object included in the processed image by determining a feature value using the dictionary.

2. The apparatus according to claim 1, wherein:

the detection unit detects the detection target object included in the processed image using the dictionary, based on a HOG feature value.

3. The apparatus according to claim 2, wherein:

the processed image generation unit generates a plurality of processed images by scaling the image picked up the camera so as to cause the plurality of processed images to have a different scaling factor to each other while each of the plurality of processed images having the predetermined visual axis as a normal-line direction.

4. The apparatus according to claim 1, wherein:

the dictionary generation unit previously generates a plurality of dictionaries for a corresponding plurality of visual axes of the camera;

the processed image generation unit generates a plurality of processed images in which the corresponding plurality of visual axes is taken as a normal-line direction, based on the image picked up by the camera; and

the detection unit detects the detection target object included in each of the plurality of processed images by determining a predetermined feature value using a dictionary corresponding to the each of the plurality of processed images.

5. The apparatus according to claim 3, wherein:

a fish-eye lens is mounted on the camera; and

the processed image generation unit generates the plurality of processed images such that the plurality of processed images curve in a progressively increasing manner in accordance with an extent to which the processed image has a large scaling factor and with respect to which a distance from the own vehicle is far.

6. The apparatus according to claim 1, wherein:

the processed image generation unit curves each of the plurality of processed images according to a shape of the detection target surface of the detection target object.

7. The apparatus according to claim 1, further comprising:

a warning unit configured to, upon detection of the detection target object from the processed image by the detection unit, notify a driver of the vehicle of information regarding the detection target object that is detected by the detection unit using at least one of an audio output through a speaker of the vehicle, a buzzer output through the speaker of the vehicle, and a warning display on a display apparatus provided at a position recognizable to the driver.

8. An image processing method comprising:

generating a dictionary as a single dictionary in advance using a plurality of images of a detection target object picked up in advance by a camera, the camera being provided on a vehicle and picking up an image around the vehicle with a wide viewing angle, the plurality of images being obtained by arranging the detection target object at a corresponding plurality of positions in a predetermined range within an image-pickup range of the camera so as to make a predetermined visual axis of the camera and a normal-line direction of a detection target surface of the detection target object parallel to each other, and the plurality of images being obtained by picking up each of the plurality of images by the camera at the corresponding plurality of positions;

generating a processed image having the predetermined visual axis as a normal-line direction, based on an image picked up by the camera after generation of the dictionary; and

detecting the detection target object included in the processed image by determining a feature value using the dictionary.

9. A non-transitory computer readable medium having instructions stored therein causes, when executed by a computer, to execute the steps of the method according to claim 8.