Vehicle surroundings monitoring apparatus

• US 9,165,197 B2
• Filed: 02/04/2013
• Issued: 10/20/2015
• Est. Priority Date: 03/05/2012
• Status: Active Grant

• Current Assignee: Arriver Software AB (Qualcomm, Inc.)
• Original Assignee: Honda Motor Co., Ltd. (Honda Motor Company)
• Inventors: Aimura, Makoto
• Primary Examiner(s): YENKE, BRIAN P
• Application Number:
  US13/758,503
• Publication Number:
  US 20130229520A1
• Time in Patent Office: 988 Days
• US Class Current: 1/1
• 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 20/584 of vehicle lights or traffic lights

Abstract

In an image captured by an infrared camera mounted in a vehicle, a featured image portion group including first and second high luminance image portions lined up side by side vertically or horizontally and a third high luminance image portion located below the first and second high luminance image portions is defined. The featured image portion group has a feature indicating that a similarity of one of a luminance distribution and a shape between the first high luminance image portion and the second high luminance image portion is higher than between the third high luminance image portion and at least one of the first and second high luminance image portions. If the featured image portion group is found in the captured image, it is determined that at least the third high luminance image portion is the image of a component of a traffic signal structure.

Claims

1. A vehicle surroundings monitoring apparatus for performing an object recognition on an object located in the vicinity of a vehicle on the basis of an image captured by an infrared camera mounted in the vehicle, comprising:

a structure recognition unit that detects whether a featured image portion group is included in the captured image, the featured image portion group including;

i) first and second high luminance image portions lined up side by side vertically or horizontally and a third high luminance image portion located below the first and second high luminance image portions, and

ii) a feature indicating that a similarity of one of a luminance distribution and a shape between the first high luminance image portion and the second high luminance image portion is higher than between the third high luminance image portion and at least one of the first and second high luminance image portions,

wherein upon detecting the featured image portion group in the captured image, the structure recognition unit determines that at least the third high luminance image portion is an image of a component of a traffic signal structure.

2. The vehicle surroundings monitoring apparatus according to claim 1, wherein the featured image portion group includes the first and second high luminance image portions lined up side by side vertically and the third high luminance image portion located below the first and second high luminance image portions, and

wherein upon detecting the featured image portion group in the captured image, the structure recognition unit determines that at least the third high luminance image portion is an image of a component of a traffic signal structure installed on a road in the United States.

3. The vehicle surroundings monitoring apparatus according to claim 1, wherein the featured image portion group includes the first and second high luminance image portions lined up side by side horizontally and the third high luminance image portion located below the first and second high luminance image portions, and

wherein upon detecting the featured image portion group in the captured image, the structure recognition unit determines that at least the third high luminance image portion is an image of a component of a traffic signal structure installed in a railway crossing in Japan.

4. The vehicle surroundings monitoring apparatus according to claim 2, wherein the structure recognition unit determines whether the vehicle is located in the vicinity of an intersection, and if so, the structure recognition unit detects whether the featured image portion group is included in the captured image.

5. The vehicle surroundings monitoring apparatus according to claim 3, wherein the structure recognition unit determines whether the vehicle is located in the vicinity of a railway crossing, and if so, the structure recognition unit detects whether the featured image portion group is included in the captured image.

6. The vehicle surroundings monitoring apparatus according to claim 1, further comprising:

an attention needed object detecting unit that detects, from the captured image, an image of an attention needed object of predetermined types including at least a human being; and

an alerting unit that performs a process for alerting a driver of the vehicle to the attention needed object when the attention needed object is detected,

wherein if the structure recognition unit determines that the third high luminance image portion is the image of one of the components of the traffic signal structure, the attention needed object detecting unit determines that at least the third high luminance image portion is not the image of the attention needed object.

7. The vehicle surroundings monitoring apparatus according to claim 6, wherein if the structure recognition unit determines that the third high luminance image portion is the image of one of the components of the traffic signal structure, the attention needed object detecting unit continues to determine that at least the third high luminance image portion is not the image of the attention needed object for at least a predetermined period of time.

8. The vehicle surroundings monitoring apparatus according to claim 6, wherein if the structure recognition unit determines that the third high luminance image portion is the image of one of the components of the traffic signal structure, the attention needed object detecting unit determines that an image of an object located above the third high luminance image portion in the captured image is not the image of the attention needed object.

9. The vehicle surroundings monitoring apparatus according to claim 1, further comprising the infrared camera capturing an infrared image.

10. The vehicle surroundings monitoring apparatus according to claim 9, wherein the infrared camera includes a semiconductor image sensor.

11. A vehicle surroundings monitoring apparatus for performing an object recognition on an object located in the vicinity of a vehicle on the basis of an image captured by an infrared camera mounted in the vehicle, comprising:

a structure recognition means for detecting whether a featured image portion group is included in the captured image, the featured image portion group including;

i) first and second high luminance image portions lined up side by side vertically or horizontally and a third high luminance image portion located below the first and second high luminance image portions, and

ii) a feature indicating that a similarity of one of a luminance distribution and a shape between the first high luminance image portion and the second high luminance image portion is higher than between the third high luminance image portion and at least one of the first and second high luminance image portions,

wherein upon detecting the featured image portion group in the captured image, the structure recognition means determines that at least the third high luminance image portion is an image of a component of a traffic signal structure.

12. A vehicle surroundings monitoring method for performing an object recognition on an object located in the vicinity of a vehicle, the method comprising:

capturing an image by an infrared camera mounted in the vehicle;

detecting, using a processor, whether a featured image portion group is included in the captured image, the featured image portion group including;

i) first and second high luminance image portions lined up side by side vertically or horizontally and a third high luminance image portion located below the first and second high luminance image portions, and

ii) a feature indicating that a similarity of one of a luminance distribution and a shape between the first high luminance image portion and the second high luminance image portion is higher than between the third high luminance image portion and at least one of the first and second high luminance image portions; and

upon detecting the featured image portion group in the captured image, determining, using a processor, that at least the third high luminance image portion is an image of a component of a traffic signal structure.