Object image search using sub-models

• US 6,324,299 B1
• Filed: 04/03/1998
• Issued: 11/27/2001
• Est. Priority Date: 04/03/1998
• Status: Expired due to Term

• Current Assignee: Cognex Corporation
• Original Assignee: Cognex Corporation
• Inventors: Marrion, Cyril C., Chang, Yian Leng, Bachelder, Ivan A., Sarachik, Karen B.
• Primary Examiner(s): Boudreau, Leo
• Assistant Examiner(s): Mariam, Daniel G.
• Application Number:
  US09/054,968
• Time in Patent Office: 1,334 Days
• Field of Search: 382/151, 382/154, 382/103, 382/181, 382/209, 382/219, 382/291, 382/177, 382/203, 382/216, 382/287, 382/289, 382/296, 348/169, 358/488
• US Class Current: 382/151
• CPC Class Codes: G06V 10/7515 Shifting the patterns to accommodate for positional errors

Abstract

The invention provides a method of locating an object within a client region, where the object has a plurality of portions. The method includes defining a full geometric model of the object; defining a plurality of geometric sub-models of the object; determining coarse candidate poses of the object within the region using an image of the region and the full geometric model of the object; determining the fine pose of each of a plurality of portions of the object using the coarse candidate poses of the object within the region, and at least some of said geometric sub-models, to provide a plurality of object portion fine poses within the region; and then determining the fine poses of the object within the region using said plurality of object portion fine poses of a plurality of portions of the object includes determining the coarse poses of each of a plurality of portions of the object, and using each coarse pose, determining the fine pose of each of the plurality of portions of the object. The invention allows geometric descriptions of objects (such as resistor chips, ball grid array packages, flip chips, etc.) to be specified in an arbitrary coordinate system, such as a physical (real world) coordinate system. This allows the same model to be used when locating the object within the physical world over a wide range of imaging conditions. The invention provides a powerful method for finding objects in images that is efficient in both memory space and computational time.

Claims

1. A method of locating an object within a client region, the object having a plurality of portions, the method comprising:

defining a full geometric model of the object;

defining a plurality of geometric sub-models of the object;

determining coarse candidate poses of the object within the region using an image of the region and the full geometric model of the object;

determining the fine pose of each of a plurality of portions of the object using the coarse candidate poses of the object within the region, and at least some of said geometric sub-models, to provide a plurality of object portion fine poses within the region;

determining the fine poses of the object within the region using said plurality of object portion fine poses.

2. The method of claim 1, wherein defining a plurality of sub-models of the object includes defining the pose of each sub-model within the reference frame of the full model.

3. The method of claim 1, wherein determining the fine pose of each of a plurality of portions of the object includes:

determining the coarse poses of each of a plurality of portions of the object, and

using each coarse pose, determining the fine pose of each of the plurality of portions of the object.

4. The method of claim 3, wherein determining the fine pose of each of a plurality of portions of the object occurs locally and independently for each portion of the object.

5. The method of claim 1, wherein using a full geometric model of the object to determine the coarse candidate poses of the object includes creating an image search model in an image frame of reference.

6. The method of claim 5, wherein creating an image search model in an image frame of reference includes creating a template matching model of the object.

7. The method of claim 5, wherein creating an image search model in an image frame of reference includes creating a normalized correlation search model of the object.

8. The method of claim 5, wherein creating an image search model in an image frame of reference includes creating a generalized Hough transform model of the object.

9. The method of claim 1, wherein using a geometric sub-model to determine the fine pose of a portion of the object includes:

creating an image search model in an image frame of reference for that sub-model.