Hierarchical system for object recognition in images

• US 20070179918A1
• Filed: 02/02/2006
• Published: 08/02/2007
• Est. Priority Date: 02/02/2006
• Status: Active Grant

• Current Assignee: Honda Motor Co., Ltd. (Honda Motor Company)
• Original Assignee: Honda Motor Co., Ltd. (Honda Motor Company)
• Inventors: Heisele, Bernd, Sharon, Yoav
• Granted Patent: US 7,680,748 B2
• Time in Patent Office: Days
• US Class Current: 706/13
• CPC Class Codes: G06F 18/231 Hierarchical techniques, i.e. dividing or merging pattern sets so as to obtain a dendrogram

Abstract

Object recognition techniques are disclosed that provide both accuracy and speed. One embodiment of the present invention is an identification system. The system is capable of locating objects in images by searching for local features of an object. The system can operate in real-time. The system is trained from a set of images of an object or objects. The system computes interest points in the training images, and then extracts local image features (tokens) around these interest points. The set of tokens from the training images is then used to build a hierarchical model structure. During identification/detection, the system, computes interest points from incoming target images. The system matches tokens around these interest points with the tokens in the hierarchical model. Each successfully matched image token votes for an object hypothesis at a certain scale, location, and orientation in the target image. Object hypotheses that receive insufficient votes are rejected.

Claims

1. A method for identifying objects in images, comprising:

computing one or more interest points in each of a plurality of training images including one or more objects;

extracting tokens associated with the interest points;

comparing tokens of training image pairs to find matched tokens, and grouping the matched tokens into groups;

computing a group token to represent each group; and

building a model tree using the group tokens, where each node of the tree represents an object model.

2. The method of claim 1 wherein the method further includes the preliminary step of receiving the plurality of training images including one or more objects, and formatting those images so that they can be processed according to the method.

3. The method of claim 1 further comprising:

identifying objects in a target image using the model tree.

4. The method of claim 3 wherein identifying objects in target images using the model tree comprises:

computing one or more interest points in the target image;

extracting tokens associated with the target image interest points; and

comparing tokens of the target image with tokens in the model tree to identify matches.

5. The method of claim 4 further comprising:

in response to determining a token match threshold is satisfied, outputting an object hypothesis; and

in response to determining a token match threshold is satisfied, rejecting the object hypothesis.

6. The method of claim 5 further comprising:

repeating the computing, extracting, comparing, and determining are repeated for a plurality of target images.

7. The method of claim 3 wherein the method further includes the preliminary step of receiving the target images, and formatting those images so that they can be processed according to the method.

8. A machine-readable medium encoded with instructions, that when executed by a processor, cause the processor to carry out a process for identifying objects in images, comprising:

computing one or more interest points in each of a plurality of training images including one or more objects;

extracting tokens associated with the interest points;

comparing tokens of training image pairs to find matched tokens, and grouping the matched tokens into groups;

computing a group token to represent each group; and

building a model tree using the group tokens, where each node of the tree represents an object model.

9. The machine-readable medium of claim 8 wherein the process further includes receiving the plurality of training images including one or more objects, and formatting those images so that they can be processed according to the process.

10. The machine-readable medium of claim 8, the process further comprising:

identifying objects in a target image using the model tree.

11. The machine-readable medium of claim 10 wherein identifying objects in target images using the model tree comprises:

computing one or more interest points in the target image;

extracting tokens associated with the target image interest points; and

comparing tokens of the target image with tokens in the model tree to identify matches.

12. The machine-readable medium of claim 11, the process further comprising:

in response to determining a token match threshold is satisfied, outputting an object hypothesis; and

in response to determining a token match threshold is satisfied, rejecting the object hypothesis.

13. The machine-readable medium of claim 12, the process further comprising:

repeating the computing, extracting, comparing, and determining are repeated for a plurality of target images.

14. The machine-readable medium of claim 10 wherein the process further includes the preliminary step of receiving the target images, and formatting those images so that they can be processed according to the process.

15. A system for identifying objects in images, comprising:

an interest point locator module for computing one or more interest points in each of a plurality of training images including one or more objects;

a token extraction module for extracting tokens associated with the interest points;

a token grouping module for comparing tokens of training image pairs to find matched tokens, grouping the matched tokens into groups, and computing a group token to represent each group; and

a model tree builder module for building a model tree using the group tokens, where each node of the tree represents an object model.

16. The system of claim 15 further comprising:

a run-time recognition module for identifying objects in a target image using the model tree.

17. The system of claim 16 wherein the run-time recognition module further comprises:

an interest point locator module for computing one or more interest points in the target image;

a token extraction module for extracting tokens associated with the target image interest points; and

a token matching module for comparing tokens of the target image with tokens in the model tree to identify matches.

18. The system of claim 17 further comprising:

a hypothesis verification module for determining if a token match threshold is satisfied, and outputting or rejecting an object hypothesis based on that determination.

19. A system for identifying objects in images, comprising:

a means for computing one or more interest points in each of a plurality of training images including one or more objects;

a means for extracting tokens associated with the interest points;

a means for comparing tokens of training image pairs to find matched tokens, grouping the matched tokens into groups, and computing a group token to represent each group; and

a means for building a model tree using the group tokens, where each node of the tree represents an object model.

20. The system of claim 19 further comprising:

a means for computing one or more interest points in the target image;

a means for extracting tokens associated with the target image interest points; and

a means for comparing tokens of the target image with tokens in the model tree to identify matches; and

a means for determining if a token match threshold is satisfied, and outputting or rejecting an object hypothesis based on that determination.