Object recognition system

• US 6,788,817 B1
• Filed: 10/18/2000
• Issued: 09/07/2004
• 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:
  US09/691,545
• Time in Patent Office: 1,420 Days
• Field of Search: 382/103-104, 382/106, 382/181, 382/190, 382/199, 382/291, 340/903, 340/933, 340/937, 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 identifies horizontal edges belonging to the outline of the object from the extracted edges. Thus, the object can be recognized based on the horizontal edges only. Similarly, the controller can extract vertical edges from the processing area and identify vertical edges belonging to the outline of the object. Preferably, the controller selects upper, lower, left, and right horizontal and vertical candidate ends of the object from the identified horizontal and vertical edges respectively, from which upper, lower, left, and right ends of the object are determined. If either one or both of the left and right horizontal candidate ends cannot be selected, candidate ends can be estimated based on the position of the object recognized in a previous recognition cycle, and the estimated candidate ends can be used in lieu of the candidate ends selected from the horizontal edges.

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,

extract horizontal edges vertical edges from the processing area,

identify horizontal edges vertical edges belonging to an outline of the object from the extracted horizontal edges and vertical edges;

select left and right candidate ends from the identified horizontal edges;

select left and right candidate ends from the identified vertical edges;

determine left and right ends of the object based on the left and right candidate ends selected from the horizontal edges and the left and right candidate ends selected from the vertical edges; and

recognize the outline of the object according to the determined left and right ends,

wherein the left and right candidate ends selected from the vertical edges are chosen as the left and right ends of the object respectively; and

wherein if said controller cannot select either one or both of the left and right candidate ends from the vertical edges, then the left or right end of the object is determined by the left or right candidate end selected from the horizontal edges in lieu of the left or right candidate end selection from the vertical edges.

2. The system of claim 1, said controller is programmed to select upper and lower candidate ends from the identified horizontal edges, and to select upper and lower candidate ends from the identified vertical edges;

and

wherein upper and lower ends of the object are determined based on the upper and lower candidate ends selected from the horizontal edges and the upper and lower candidate ends selcted from the vertical edges.

3. The system of claim 2, wherein the higher one of the upper candidate end selected from the horizontal edges and the upper candidate end selected from the vertical edges is chosen as the upper end of the object, and the lower one of the lower candidate end selected from the horizontal edges and the lower candidate end selected from the vertical edges is chosen as the lower end of the object.

4. The system of claim 1, if said controller cannot select either one or both of the left and right candidate ends from the horizontal edges, then the left and right ends of the object are determined by estimated left and right candidate ends in lieu of the left and right candidate ends selected from the horizontal edges, the estimated left and right candidate ends being determined based on the position of the object recognized in a previous recognition cycle.

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

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

determining a position of the object;

capturing an image of the object;

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;

extracting horizontal edges vertical edges from the processing area;

judging whether each of the extracted horizontal edges vertical edges belongs to the object based on characteristics of the object to be recognized;

identifying horizontal edges vertical edges belonging to an outline of the object from the horizontal edges vertical edges judged to belong to the object;

selecting left and right candidate ends from the identified horizontal edges;

selecting left and right candidate ends from the identified vertical edges;

determining left and right ends of the object based on the left and right candidate ends selected from the horizontal edges and the left and right candidate ends selected from the vertical edges; and

recognizing the outline of the object according to the determined left and right ends,

wherein the left and right candidate ends selected from the vertical edges are chosen as the left and right ends of the object respectively; and

wherein if either one or both of the left and right candidate ends cannot be selected from the vertical edges, then the left or right end of the object is determined by the left or right candidate end selected from the horizontal edges in lieu of the left or right candidate end selected from the vertical edges.

7. The method of claim 6, further comprising:

selecting upper and lower candidate ends from the identified horizontal edges;

selecting upper and lower candidate ends from the identified vertical edges; and

determining upper and lower ends of the object based on the upper and lower candidate ends selected from the horizontal edges and the upper and lower candidate ends selected from the vertical edges;

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

8. The method of claim 6, further comprising a step of determining estimated left and right candidate ends based on the position of the object recognized in a previous recognition cycle;

and

wherein if either one or both of the left and right candidate ends cannot be selected from the horizontal edges, then the left and right ends of the object are determined by the estimated left and right candidate ends in lieu of the left and right candidate ends selected from the horizontal edges.

9. 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 positioning sensor and a predetermined size for the object to be recognized;

means for extracting horizontal edges vertical edges from the processing area;

means for judging whether each of the extracted horizontal edges vertical edges belongs to the object based on characteristics of the object to be recognized; and

means for identifying horizontal edges vertical edges belonging to an outline of the object from the horizontal edges vertical edges judged to belong to the object;

means for selecting left and right candidate ends from the identified horizontal edges;

means for selecting left and right candidate ends from the identified vertical edges;

means for determining left and right ends of the object based on the left and right candidate ends selected from the horizontal edges and the left and right candidate ends selected from the vertical edges; and

means for recognizing the outline of the object according to the and right ends,

wherein the left and right candidate ends selected from the vertical edges chosen as the left and right ends of the object respectively; and

wherein if either one or both of the left and right candidate ends cannot be selected from the vertical edges, then the left or right end of the object is determined by the left or right candidate end selected from the horizontal edges in lieu of the left or right candidate end selected from the vertical edges.

10. The system of claim 9, further comprising:

means for selecting upper and lower candidate ends from the identified horizontal edges; and

means for selecting upper and lower candidate ends from the identified vertical edges;

wherein upper and lower ends of the object are determined based on the upper and lower candidate ends selected from the horizontal edges and the upper and lower candidate ends selected from the vertical edges; and

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

11. The system of claim 9, if either one or both of the left and right candidate ends cannot be selected from the horizontal edges, then the left and right ends of the object are determined by estimated left and right candidate ends in lieu of the left and right candidate ends selected from the horizontal edges, the estimated left and right candidate ends being determined based on the position of the object recognized in a previcous recognition cycle.