Optical object recognition system

• US 6,853,738 B1
• Filed: 05/17/2000
• Issued: 02/08/2005
• Est. Priority Date: 06/16/1999
• 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: Nishigaki, Morimichi, Saka, Masakazu
• Primary Examiner(s): Chang, Jon
• Assistant Examiner(s): Kim, Charles
• Application Number:
  US09/572,249
• Time in Patent Office: 1,728 Days
• Field of Search: 382/103, 382/104, 382/106, 382/154, 382/180, 382/225, 356/3, 356 313- 314, 356/3.16, 348/139, 348/142, 340/901, 340/903, 701/300
• US Class Current: 382/106
• CPC Class Codes: G01C 3/085 with electronic parallax measurement
• CPC Class Codes: G01S 5/16 using electromagnetic waves other than radio waves
• CPC Class Codes: G06F 18/23 Clustering techniques
• CPC Class Codes: G06V 10/255 Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
• CPC Class Codes: G06V 10/267 by performing operations on regions, e.g. growing, shrinking or watersheds
• CPC Class Codes: G06V 10/762 using clustering, e.g. of similar faces in social networks
• 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 20/582 of traffic signs
• CPC Class Codes: G06V 20/64 Three-dimensional objects
• CPC Class Codes: G06V 2201/08 Detecting or categorising vehicles

Abstract

An object recognition system comprises a memory for storing a plurality of distance ranges with different distance labels associated with respective distance ranges. The controller converts measured distance values into distance labels according to distance ranges to which the distance values belong. The controller groups the sections or windows of a captured image based on assigned distance labels. Detection area or viewing area of the sensors is divided into a plurality of distance ranges according to tolerance of the measured distance such that broader distance range is defined as the distance from the system is larger. The controller scans the windows with distance labels using a template that defines a joining relationship for the windows and assigns each window with a cluster label that is a combination of the distance label and a occurrence indicia, which is the same for the windows that satisfy the joining relationship. The controller unites the windows having the same cluster labels into a cluster, generates three dimensional data of each of said clusters and combines the clusters that are positioned close to each other based on the three dimensional data to form a candidate of a physical object. The system includes a memory for storing three dimensional data of one or more physical objects that were recognized in previous recognition cycle. The controller infers a physical object which would be recognized in the current cycle based on the stored data and a speed of the vehicle relative to the physical object. The controller compares the inferred physical object with said candidate of a physical object to recognize a physical object.

Claims

1. An object recognition system having one or more image sensors and a controller that is adapted for measuring the distance from the system to objects with respect to respective sections of an image captured by the sensors, comprising:

a memory for storing a plurality of distance ranges, each distance range given a distance label,

wherein said controller assigns said distance labels to said sections respectively according to the distance ranges to which the measured distance values belong, and

wherein the system is adapted for being carried on a vehicle and the viewing area of said sensors is divided into the plurality of distance ranges according to a tolerance of the measured distance such that the distance ranges become wider as the distance from the system increases.

2. The system of claim 1, wherein the sections having the same distance label are grouped into a same cluster.

3. The system of claim 1, wherein said controller scans said sections having distance labels using a template that defines a joining relationship for the sections and assigns each section with a cluster label that is a combination of the distance label and a occurrence indicia, the occurrence indicia being the same for the sections that satisfies said joining relationship.

4. The system of claim 3, wherein the sections having the same distance label and the same occurrence indicia are united into a cluster.

5. The system of claim 4, wherein said controller generates three dimensional information of each of said clusters based on distance, height and width if the integral clusters.

6. The system of claim 5, wherein said controller groups and clusters into one or more cluster groups based on said three dimensional information such that each cluster group represents a possible physical object.

7. The system of claim 6, wherein said controller stores in a memory three dimensional information of one or more physical objects that were recognized in previous recognition cycle and infers a physical object which would be recognized in the current cycle based on the stored information and a speed of the vehicle mounting said system relative to the physical object.

8. A method for recognizing a physical object from a vehicle, comprising the steps of:

defining a plurality of distance ranges each associated with a distance label;

capturing an image in the traveling direction and measuring distance from the vehicle to objects with respect to a plurality of windows of the image;

assigning said distance labels to said windows respectively according to the distance ranges to which the measured distance values belong; and

wherein said distance ranges are defined according to a tolerance of the measured distance such that the distance ranges become larger as the distance from the vehicle increases.

9. The method of claim 8, further comprising the step of:

scanning said windows having distance labels using a template that defines a joining relationship for the windows; and

assigning each window with a cluster label that is a combination of the distance label and a occurrence indicia, the occurrence indicia being the same for the windows that satisfy said joining relationship.

10. The method of claim 9, further comprising:

uniting the windows having the same cluster labels into a cluster.

11. The method of claim 10, further comprising:

generating three dimensional data of each of said clusters based on distance from the vehicle, height and width of said clusters.

12. The method of claim 11, further comprising:

combining the clusters that are positioned close to each other based on the three dimensional data to form a candidate of a physical object.

13. The method of claim 12, further comprising:

storing in a memory three dimensional data of one or more physical objects that were recognized in previous recognition cycle; and

inferring a physical object which would be recognized in the current cycle based on the stored data and a speed of the vehicle relative to a physical object.

14. The method of claim 11, wherein said distance from the vehicle is determined by averaging distance from the vehicle of the windows constituting the cluster.

15. The method of claim 11, wherein the height of a cluster is determined by the difference between a position of the window at the top of the cluster and a position of the window at the bottom of the cluster.

16. The method of claim 11, wherein the width of a cluster is determined by the difference between a position of the window at the right end of the cluster and a position of the window at the left end of the cluster.

17. The method of claim 13, further comprising:

comparing the inferred physical object with said candidate of a physical object to recognize a physical object.

18. An object recognition system having one or more image sensors and a controller that is adapted for measuring the distance from the system to objects with respect to respective windows of an image captured by the sensors, comprising:

a memory for storing a plurality of distance ranges, each distance range given a distance label;

means for assigning said distance labels to said windows respectively according to the distance ranges to which the measured distance values belong;

means for grouping the windows into clusters according to said distance labels; and

means for recognizing a physical object based on said clusters;

wherein the system is adapted for being carried on a vehicle and the viewing area of said sensors is divided into the plurality of distance ranges according to a tolerance of the measured distance such that the distance ranges become broader as the distance from the system increase.