APPARATUS FOR MONITORING SURROUNDINGS OF A VEHICLE

• US 20130070098A1
• Filed: 05/30/2011
• Published: 03/21/2013
• Est. Priority Date: 06/07/2010
• Status: Active Grant

• Current Assignee: Arriver Software AB (Qualcomm, Inc.)
• Original Assignee: Honda Motor Co., Ltd. (Honda Motor Company)
• Inventors: Aimura, Makoto, Nagaoka, Nobuharu
• Granted Patent: US 9,030,560 B2
• Time in Patent Office: Days
• US Class Current: 348/148
• CPC Class Codes: G06T 2207/10048 Infrared image
• CPC Class Codes: G06T 2207/30261 Obstacle
• CPC Class Codes: G06T 7/12 Edge-based segmentation
• CPC Class Codes: G06T 7/73 using feature-based methods
• CPC Class Codes: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
• CPC Class Codes: G08G 1/166 for active traffic, e.g. moving vehicles, pedestrians, bikes

Abstract

The vehicle surroundings monitoring apparatus is provided with an imaging device and a device that transforms captured image to digital image. A first edge extraction mask is applied to detect multiple horizontal edges. The apparatus further includes a detector that detects upper end of the head of the object by detecting a horizontal edge having a highest edge intensity out of the multiple horizontal edges. A second edge extraction mask is used to detect the lower end of the head of the physical object by detecting multiple vertical edges and matching the positional variation of the multiple vertical edges with predetermined patterns.

Claims

1. An apparatus for monitoring surroundings of a vehicle, comprising:

an imaging device that is mounted on a vehicle and captures an image around the vehicle; and

an image processing unit having a processor and a memory;

wherein the image processing unit is configured to;

transform a grayscale image acquired by the imaging device to a multi-value image;

detect an upper end of the head of the physical object in the multi-value image by determining a horizontal edge having a maximum edge intensity region of a first edge extraction mask applied to the multi-value image;

detect multiple vertical edges in the multi-value image by applying a second edge extraction mask extending downwards from the detected upper end of the head of the physical object;

detect a lower end of the head of the physical object based on a positional variation of the detected multiple vertical edges; and

to

identify a head region of the physical object based on the space between the upper end of the head and the lower end of the head of the physical object.

2. The apparatus according to claim 1, wherein the imaging device is a single infrared camera, and the monitoring device the image processing unit is further configured to:

calculate a distance between the vehicle and the physical object in a real space based on the size of the head of the physical object in the multi-value image and a focal length of the infrared camera.

3. The apparatus according to claim 2, wherein the image processing unit is further configured to:

determine a possibility that the vehicle contacts the physical object based on at least one of the calculated distance, a vehicle speed, and a yaw rate of the vehicle.

4. The apparatus according to claim 1, wherein the image processing unit is further configured to:

apply an intensity profile to a grayscale image of the detected head region to produce information about the head; and

to

determine reliability of the detection of the head in the light of the information produced from the intensity profile.

5. The apparatus according to claim 1, wherein the lower end of the head is detected when the positional variation of the pixels of the detected vertical edges matches a predetermined pattern.

6. An apparatus for monitoring surroundings of a vehicle, comprising:

an imaging means mounted on a vehicle for capturing an image around the vehicle;

means for transforming a grayscale image acquired by the imaging device to a multi-value image;

means for detecting an upper end of the head of the physical object in the multi-value image by determining a horizontal edge having a maximum edge intensity in the region of a first edge extraction mask applied to the multi-value image;

means for detecting multiple vertical edges in the multi-value image by applying a second edge extraction mask extending downwards from the detected upper end of the head of the physical object in the multi-value image;

means for detecting a lower end of the head of the physical object based on a positional variation of the detected multiple vertical edges in the multi-value image; and

means for identifying a head region of the physical object in the multi-value image based on the space between the detected upper end of the head and the detected lower end of the head of the physical object.

7. The apparatus according to claim 6, wherein the imaging means is a single infrared camera, and the apparatus further comprising:

means for calculating a distance between the vehicle and the physical object in a real space based on the size of the head of the physical object in the multi-value image and a focal length of the infrared camera.

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

means for determining a possibility that the vehicle contacts the physical object based on at least one of the calculated distance, a used brake magnitude, a vehicle speed, and a yaw rate of the vehicle.

9. The apparatus according to claim 6, wherein the lower end of the head is detected when the positional variation of the pixels of the detected vertical edges matches a predetermined pattern.

10. A method of monitoring surroundings of a vehicle, comprising:

capturing an image around the vehicle with an imaging device mounted on the vehicle;

transforming a grayscale image acquired by the imaging device to a multi-value image;

detecting an upper end of the head of the physical object in the multi-value image by determining a horizontal edge having a maximum edge intensity in the region of a first edge extraction mask applied to the multi-value image;

detecting multiple vertical edges in the multi-value image by applying a second edge extraction mask extending downwards from the detected upper end of the head of the physical object in the multi-value image;

detecting a lower end of the head of the physical object based on a positional variation of the detected multiple vertical edges in the multi-value image; and

identifying a head region of the physical object in the multi-value image based on the space between the upper end of the head and the lower end of the head of the physical object.

11. The method according to claim 10, wherein the imaging device is a single infrared camera, and the method further comprises:

calculating a distance between the vehicle and the physical object in a real space based on the size of the head of the physical object in the multi-value image and a focal length of the infrared camera.

12. The method according to claim 11, further comprising:

determining a possibility that the vehicle contacts the physical object based on at least one of the calculated distance, a used brake magnitude, a vehicle speed, and a yaw rate of the vehicle.

13. The method according to claim 10, wherein the lower end of the head is detected when the positional variation of the pixels of the detected vertical edges matches a predetermined pattern.