Object recognition system

• US 6,792,147 B1
• Filed: 10/18/2000
• Issued: 09/14/2004
• Est. Priority Date: 11/04/1999
• Status: Expired due to Fees

• Current Assignee: Honda Giken Kogyo Kabushiki Kaisha (Honda Motor Company)
• Original Assignee: Honda Giken Kogyo Kabushiki Kaisha (Honda Motor Company)
• Inventors: Saka, Masakazu, Yuhara, Hiromitsu, Aoki, Tomoyoshi, Nishigaki, Morimichi
• Primary Examiner(s): MARIAM, DANIEL G
• Application Number:
  US09/691,124
• Time in Patent Office: 1,427 Days
• Field of Search: 382/103, 382/104, 382/106, 382/151, 382/190, 382/199, 382/291, 340/933, 340/937, 340/903, 348/169
• US Class Current: 382/199
• CPC Class Codes: G06T 2207/10028 Range image; Depth image; 3D point clouds
• CPC Class Codes: G06T 2207/10048 Infrared image
• CPC Class Codes: G06T 2207/20132 Image cropping
• CPC Class Codes: G06T 2207/30256 Lane; Road marking
• CPC Class Codes: G06T 2207/30261 Obstacle
• CPC Class Codes: G06T 7/12 Edge-based segmentation
• CPC Class Codes: G06T 7/74 involving reference images or patches
• CPC Class Codes: G06V 10/255 Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
• 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 2201/08 Detecting or categorising vehicles

Abstract

An object recognition system including a position sensor, an image sensor and a controller is provided. The position sensor determines the position of an object, and the image sensor captures an image of the object. The controller sets a processing area within the image captured by the image sensor based on the position of the object determined by the position sensor and a predetermined size for the object to be recognized. The controller extracts horizontal edges from the processing area, and judges whether each of the extracted edges belongs to the object based on characteristics of the object to be recognized. More practically, the controller can check if each of the extracted edges contains a pixel on a boundary of the processing area. If so, the controller judges to the edge to belong to an object other than the object. The controller can also examine the linearity of each of the extracted edges. If the linearity is larger than a predetermined value, the controller judges the edge to belong to an object other than the object. The controller can also examine the slope of each of the extracted edges. If the slope is larger than a predetermined value, the controller judges the edge to belong to an object other than the object. Thus, the edges judged to belong to an object other than the object are removed. The controller recognizes the outline of the object based on the edges judged to belong to the object.

Claims

1. An object recognition system, comprising:

a position sensor for determining a position of an object;

an image sensor for capturing an image of the object; and

a controller programmed to;

set a processing area within the image captured by the image sensor based on the position of the object determined by the position sensor and a predetermined size for the object to be recognized, to extract edges from the processing area, and to judge whether each of the extracted edges belongs to the object based on characteristics of the object to be recognized; and

to examine a slope of each of the extracted edges;

wherein said controller recognizes an outline of the object according to the edges judged to belong to the object; and

wherein an edge is judged to belong to an object other than the object to be recognized if the edge has a large slope.

2. The system of claim 1, wherein the edges include horizontal edges and vertical edges.

3. The system of claim 2, wherein said controller is further programmed to determine upper and lower ends of the object from the horizontal edges, and to determine left and right ends of the object from the vertical edges;

and

wherein the outline of the object is recognized by the determined upper, lower, left, and right ends.

4. The system of claim 3, wherein said controller is further programmed to identify an upper horizontal edge whose length is larger than a first predetermined value and which is closest to an upper boundary of the processing area, and to identify a lower horizontal edge whose length is larger than the first predetermined value and which is closest to a lower boundary of the processing area;

wherein said controller is further programmed to identify a left vertical edge whose length is larger than a second predetermined value and which is located near a left boundary of the processing area, and to identify a right vertical edge whose length is larger than the second predetermined value and which is located near a right boundary of the processing area;

wherein the upper end of the object is determined by the position in the vertical direction that corresponds to the identified upper horizontal edge, and the lower end of the object is determined by the position in vertical direction that corresponds to the identified lower horizontal edge; and

wherein the left end of the object is determined by the position in the horizontal direction that corresponds to the identified left vertical edge, and the right end of the object is determined by the position in the horizontal direction that corresponds to the identified right vertical edge.

5. The system of claim 3, wherein the controller is further programmed to reduce the processing area in the vertical direction to the area defined by the determined upper and lower ends;

and

wherein the vertical edges are extracted from the reduced process area.

6. The system of claim 1, wherein the predetermined size is defined to surround the object to be recognized.

7. An object recognition system, comprising:

a position sensor for determining a position of an object;

an image sensor for capturing an image of the object;

a controller programmed to;

set a processing area within the image captured by the image sensor based on the position of the object determined by the position sensor and a predetermined size for the object to be recognized, to extract edges from the processing area, and to judge whether each of the extracted edges belongs to the object based on characteristics of the object to be recognized; and

check if each of the extracted edges contains a pixel located on a boundary of the processing area;

wherein said controller recognizes an outline of the object according to the edges judged to belong to the object; and

wherein an edge is judged to belong to an object other than the object if the edge contains pixels located on a boundary of the processing area.

8. The system of claim 7, wherein the edges include horizontal edges and vertical edges.

9. The system of claim 8, wherein said controller is further programmed to determine upper and lower ends of the object from the horizontal edges, and to determine left and right ends of the object from the vertical edges;

and

wherein the outline of the object is recognized by the determined upper, lower, left, and right ends.

10. The system of claim 9, wherein said controller is further programmed to identify an upper horizontal edge whose length is larger than a first predetermined value and which is closest to an upper boundary of the processing area, and to identify a lower horizontal edge whose length is larger than the first predetermined value and which is closest to a lower boundary of the processing area;

wherein said controller is further programmed to identify a left vertical edge whose length is larger than a second predetermined value and which is located near a left boundary of the processing area, and to identify a right vertical edge whose length is larger than the second predetermined value and which is located near a right boundary of the processing area;

wherein the upper end of the object is determined by the position in the vertical direction that corresponds to the identified upper horizontal edge, and the lower end of the object is determined by the position in vertical direction that corresponds to the identified lower horizontal edge; and

wherein the left end of the object is determined by the position in the horizontal direction that corresponds to the identified left vertical edge, and the right end of the object is determined by the position in the horizontal direction that corresponds to the identified right vertical edge.

11. The system of claim 9, wherein the controller is further programmed to reduce the processing area in the vertical direction to the area defined by the determined upper and lower ends;

and

wherein the vertical edges are extracted from the reduced process area.

12. The system of claim 7, wherein the predetermined size is defined to surround the object to be recognized.

13. An object recognition system, comprising:

a position sensor for determining a position of an object;

an image sensor for capturing an image of the object; and

a controller programmed to;

set a processing area within the image captured by the image sensor based on the position of the object determined by the position sensor and a predetermined size for the object to be recognized, to extract edges from the processing area, and to judge whether each of the extracted edges belongs to the object based on characteristics of the object to be recognized; and

examine a linearity of each of the extracted edges;

wherein said controller recognizes an outline of the object according to the edges judged to belong to the object; and

wherein an edge is judged to belong to an object other than the object to be recognized if the edge has a poor linearity.

14. The system of claim 13, wherein the edges include horizontal edges and vertical edges.

15. The system of claim 14, wherein said controller is further programmed to determine upper and lower ends of the object from the horizontal edges, and to determine left and right ends of the object from the vertical edges;

and

wherein the outline of the object is recognized by the determined upper, lower, left, and right ends.

16. The system of claim 15, wherein said controller is further programmed to identify an upper horizontal edge whose length is larger than a first predetermined value and which is closest to an upper boundary of the processing area, and to identify a lower horizontal edge whose length is larger than the first predetermined value and which is closest to a lower boundary of the processing area;

wherein said controller is further programmed to identify a left vertical edge whose length is larger than a second predetermined value and which is located near a left boundary of the processing area, and to identify a right vertical edge whose length is larger than the second predetermined value and which is located near a right boundary of the processing area;

wherein the upper end of the object is determined by the position in the vertical direction that corresponds to the identified upper horizontal edge, and the lower end of the object is determined by the position in vertical direction that corresponds to the identified lower horizontal edge; and

wherein the left end of the object is determined by the position in the horizontal direction that corresponds to the identified left vertical edge, and the right end of the object is determined by the position in the horizontal direction that corresponds to the identified right vertical edge.

17. The system of claim 15, wherein the controller is further programmed to reduce the processing area in the vertical direction to the area defined by the determined upper and lower ends;

and

wherein the vertical edges are extracted from the reduced process area.

18. The system of claim 13, wherein the predetermined size is defined to surround the object to be recognized.

19. A method for recognizing an object comprising the steps of:

a) determining a position of the object;

b) capturing an image of the object;

c) setting a processing area within the image based on the determined position of the object and a predetermined size for the object to be recognized;

d) extracting edges from the processing area;

e) judging whether each of the extracted edges belongs to the object based on characteristics of the object to be recognized by,

i) examining a slope of each of the extracted edges; and

ii) judging that an edge belongs to an object other than the object to be recognized if the edge has a slope greater than a predetermined value; and

f) recognizing an outline of the object according to the edges judged to belong to the object.

20. The method of claim 19, wherein the step e) further comprises a step of approximating each of the extracted edges by straight lines;

and

wherein the step ii) further comprises a step of judging that an edge belongs to an object other than the object to be recognized if the slope of the edge approximated by straight lines is greater than a predetermined value.

21. A method for recognizing an object comprising the steps of:

a) determining a position of the object;

b) capturing an image of the object;

c) setting a processing area within the image based on the determined position of the object and a predetermined size for the object to be recognized;

d) extracting edges from the processing area;

e) judging whether each of the extracted edges belongs to the object based on characteristics of the object to be recognized by,

i) checking if each of the extracted edges contains a pixel located on a boundary of the processing area; and

ii) judging that an edge belongs to an object other than the object to be recognized if the edge contains a pixel located on a boundary of the processing area; and

f) recognizing an outline of the object according to the edges judged to belong to the object.

22. A method for recognizing an object comprising the steps of:

a) determining a position of the object;

b) capturing an image of the object;

c) setting a processing area within the image based on the determined position of the object and a predetermined size for the object to be recognized;

d) extracting edges from the processing area;

e) judging whether each of the extracted edges belongs to the object based on characteristics of the object to be recognized by,

i) examining a linearity of each of the extracted edges; and

ii) judging that an edge belongs to an object other than the object to be recognized if the edge has a poor linearity; and

f) recognizing an outline of the object according to the edges judged to belong to the object.

23. The method of claim 22, wherein the step i) further comprises a step of calculating a variance of the positions in vertical direction of the points forming each of the extracted edges;

and

wherein the step j) further comprises a step of judging that an edge belongs to an object other than the object to be recognized if the variance calculated for the edge is greater than a predetermined value.

24. An object recognition system, comprising:

a position sensor for determining a position of an object;

an image sensor for capturing an image of the object;

means for setting a processing area within the image captured by the image sensor based on the position of the object determined by the position sensor and a predetermined size for the object to be recognized;

means for extracting edges from the processing area; and

means for judging whether each of the extracted edges belongs to the object based on characteristics of the object to be recognized, said means for judging comprises,

a means for examining a slope of each of the extracted edges;

wherein an outline of the object is recognized according to the edges judged to belong to the object; and

wherein an edge is judged to belong to an object other than the object to be recognized if the edge has a large slope.

25. An object recognition system, comprising:

a position sensor for determining a position of an object;

an image sensor for capturing an image of the object;

means for setting a processing area within the image captured by the image sensor based on the position of the object determined by the position sensor and a predetermined size for the object to be recognized;

means for extracting edges from the processing area; and

means for judging whether each of the extracted edges belongs to the object based on characteristics of the object to be recognized, said means for judging comprises,

a means for checking if each of the extracted edges contains a pixel located on a boundary of the processing area;

wherein an outline of the object is recognized according to the edges judged to belong to the object;

wherein an edge is judged to belong to an object other than the object if the edge contains a pixel located on a boundary of the processing area.

26. An object recognition system, comprising:

a position sensor for determining a position of an object;

an image sensor for capturing an image of the object;

means for setting a processing area within the image captured by the image sensor based on the position of the object determined by the position sensor and a predetermined size for the object to be recognized;

means for extracting edges from the processing area; and

means for judging whether each of the extracted edges belongs to the object based on characteristics of the object to be recognized, said means for judging comprises,

a means for examining a linearity of each of the extracted edges;

wherein an outline of the object is recognized according to the edges judged to belong to the object; and

wherein an edge is judged to belong to an object other than the object to be recognized if the edge has a poor linearity.