Automotive environment monitoring device, vehicle with the automotive environment monitoring device, and automotive environment monitoring program

• US 7,885,430 B2
• Filed: 04/07/2008
• Issued: 02/08/2011
• Est. Priority Date: 04/20/2007
• Status: Active Grant

• Current Assignee: Arriver Software AB (Qualcomm, Inc.)
• Original Assignee: Honda Motor Co., Ltd. (Honda Motor Company)
• Inventors: Saka, Masakazu, Tsuji, Takayuki, Aimura, Makoto, Nagaoka, Nobuharu
• Primary Examiner(s): Chen; Wenpeng
• Application Number:
  US12/080,906
• Publication Number:
  US 20080260208A1
• Time in Patent Office: 1,037 Days
• Field of Search: 382/104, 382/190, 382/103, 701/301
• US Class Current: 382/104
• CPC Class Codes: G06T 2207/10012 Stereo images
• CPC Class Codes: G06T 2207/10048 Infrared image
• CPC Class Codes: G06T 2207/30261 Obstacle
• CPC Class Codes: G06T 7/13 Edge detection
• CPC Class Codes: G06T 7/73 using feature-based methods
• CPC Class Codes: G06V 10/44 Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
• 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 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands

Abstract

The present invention provides an automotive environment monitoring device to detect the existence of an object, a pedestrian or the like, with high accuracy even if one part of the object is overlapped with the background of an image obtained from an imaging unit mounted on the vehicle. An area where the object exists in the image obtained from an infrared camera (102) is set as a first area (A_1i) and a lower portion of the first area (A_1i) is set as a second area (A_2i). A feature of the object is extracted with respect to the second area (A_2i) and the object is identified based on the extracted feature. Thereby, even in the case where the first area (A_1i) has been set but the feature of an upper part of the object can not be extracted due to the upper part of the object being overlapped with the background of the image, the object can still be identified with high accuracy by extracting the feature of a lower part of the object in the second area (A_2i).

Claims

1. An automotive environment monitoring device which monitors environment of a vehicle by using an image obtained from an imaging unit mounted on the vehicle, comprising:

a first processing unit which sets an area where an object exists in the image obtained from the imaging unit as a first area and a lower portion of the first area as a second area;

a second processing unit which extracts a positive or negative edge line, and a length of each of the positive or negative edge line of the object in the second area set by the first processing unit as a feature of the object in the second area set by the first processing unit; and

a third processing unit which identifies the object as a human on a condition that at least three positive or negative edge lines with the length in a first length range are extracted by the second processing unit on the basis of an extraction result by the second processing unit.

2. The automotive environment monitoring device according to claim 1, wherein the first processing unit determines a distance from the vehicle to the object;

and the second processing unit extracts the feature of the object on a condition that the determined distance by the first processing unit is in a given distance range.

3. The automotive environment monitoring device according to claim 1, wherein the first processing unit determines a height from a road surface to the lower end of the first area or the second area set by the first processing unit where the object exists;

and the second processing unit extracts the feature of the object on a condition that the determined height by the first processing unit is in a given height range.

4. An automotive environment monitoring program stored on a non-transitory computer readable medium which causes a computer mounted on a vehicle to serve as the automotive environment monitoring device according to claim 1.

5. An automotive environment monitoring device which monitors environment of a vehicle by using an image obtained from an imaging unit mounted on the vehicle, comprising:

a first processing unit which sets an area where an object exists in the image obtained from the imaging unit as a first area and a lower portion of the first area as a second area;

a second processing unit which extracts an edge line, a length of the edge line, and an upper horizontal interval and a lower horizontal interval between two edge lines of the object in the second area set by the first processing unit as the feature of the object in the second area set by the first processing unit; and

a third processing unit which identifies the object as a human on a condition that two edge lines with the length in a second length range and with a deviation between the upper horizontal interval and the lower horizontal interval in a given deviation range with a positive lower limit are extracted by the second processing unit on the basis of an extraction result by the second processing unit.

6. An automotive environment monitoring device according to claim 5, wherein the second processing unit determines a total number of edge points constituting the two edge lines as the length of the two edge lines, respectively;

and an average horizontal interval between edge points of the same height constituting the two edge lines in the upper and lower portion of the second area are determined as the upper horizontal interval and the lower horizontal interval of the two edge lines, respectively.

7. An automotive environment monitoring program causing a computer mounted on a vehicle to serve as the automotive environment monitoring device according to claim 5.

8. An automotive environment monitoring method which monitors environment of a vehicle by using an image obtained from an imaging unit mounted on the vehicle, comprising:

a first processing which sets an area where an object exists in the image obtained from the imaging unit as a first area and a lower portion of the first area as a second area;

a second processing which extracts a positive or negative edge line, and a length of each of the positive or negative edge line of the object in the second area set by the first processing as a feature of the object in the second area set by the first processing; and

a third processing which identifies the object as a human on a condition that at least three positive or negative edge lines with the length in a first length range are extracted by the second processing on the basis of an extraction result by the second processing.

9. An automotive environment monitoring method which monitors environment of a vehicle by using an image obtained from an imaging unit mounted on the vehicle, comprising:

a first processing which sets an area where an object exists in the image obtained from the imaging unit as a first area and a lower portion of the first area as a second area;

a second processing which extracts an edge line, a length of the edge line, and an upper horizontal interval and a lower horizontal interval between two edge lines of the object in the second area set by the first processing as the feature of the object in the second area set by the first processing; and

a third processing which identifies the object as a human on a condition that two edge lines with the length in a second length range and with a deviation between the upper horizontal interval and the lower horizontal interval in a given deviation range with a positive lower limit are extracted by the second processing on the basis of an extraction result by the second processing.