SYSTEM AND METHOD FOR REGION CLASSIFICATION OF 2D IMAGES FOR 2D-TO-3D CONVERSION

• US 20110043540A1
• Filed: 03/23/2007
• Published: 02/24/2011
• Est. Priority Date: 03/23/2007
• Status: Abandoned Application

• Current Assignee: Thomson Licensing LLC (The Woodbridge Co. Ltd.)
• Original Assignee: Thomson Licensing LLC (The Woodbridge Co. Ltd.)
• Inventors: Benitez, Ana Belen, Fancher, James Arthur, Zhang, Dong-Qing
• Application Number:
  US12/531,906
• Publication Number:
  US 20110043540A1
• Time in Patent Office: Days
• US Class Current: 345/672
• CPC Class Codes: G06T 7/50 Depth or shape recovery
• CPC Class Codes: H04N 13/261 with monoscopic-to-stereoscopic image conversion

Abstract

A system and method for region classification of two-dimensional images for 2D-to-3D conversion of images to create stereoscopic images are provided. The system and method of the present disclosure provides for acquiring a two-dimensional image, identifying a region of the 2D image, extracting features from the region, classifying the extracted features of the region, selecting a conversion mode based on the classification of the identified region, converting the region into a 3D model based on the selected conversion mode, and creating a complementary image by projecting the 3D model onto an image plane different than an image plane of the 2D image. A learning component optimizes the classification parameters to achieve minimum classification error of the region using a set of training images and corresponding user annotations.

Claims

1. A three-dimensional conversion method for creating stereoscopic images comprising:

acquiring a two-dimensional image;

identifying a region in the two-dimensional image;

classifying the identified region;

selecting a conversion mode based on the classification of the identified region;

converting the region into a three-dimensional model based on the selected conversion mode; and

creating a complementary image by projecting the three-dimensional model onto an image plane different than an image plane of the acquired two-dimensional image.

2. The method as in claim 1, further comprising:

extracting features from the region;

classifying the extracted features; and

selecting the conversion mode based on the classification of the extracted features.

3. The method as in claim 2, wherein the extracting step further comprises determining a feature vector from the extracted features.

4. The method as in claim 3, wherein the feature vector is employed in the classifying step to classify the identified region.

5. The method as in claim 2, wherein the extracted features are texture and edge direction.

6. The method as in claim 5, further comprising:

determining a feature vector from the texture features and the edge direction features; and

classifying the feature vector to select the conversion mode.

7. The method as in claim 1, wherein the conversion mode is a fuzzy object conversion mode or a solid object conversion mode.

8. The method as in claim 1, wherein the classifying step further comprises:

acquiring a plurality of two-dimensional images;

selecting a region in each of the plurality of two-dimensional images;

annotating the selected region with an optimal conversion mode based on a type of the selected region; and

optimizing the classifying step based on the annotated two-dimensional images.

9. The method as in claim 8, wherein the type of selected region corresponds to a fuzzy object.

10. The method as in claim 8, wherein the type of selected region corresponds to a solid object.

11. A system for three-dimensional conversion of objects from two-dimensional images, the system comprising:

a post-processing device configured for creating a complementary image from a two-dimensional image;

the post-processing device including;

a region detector configured for detecting a region in at least one two-dimensional image;

a region classifier configured for classifying a detected region to determine an identifier of at least one converter;

the at least one converter configured for converting a detected region into a three-dimensional model; and

a reconstruction module configured for creating a complementary image by projecting the selected three-dimensional model onto an image plane different than an image plane of the one two-dimensional image.

12. The system as in claim 11, further comprising a feature extractor configured to extract features from the detected region.

13. The system as in claim 12, wherein the feature extractor is further configured to determine a feature vector for inputting into the region classifier.

14. The system as in claim 12, wherein the extracted features are texture and edge direction.

15. The system as in claim 11, wherein the region detector is a segmentation function.

16. The system as in claim 11, wherein the at least one converter is a fuzzy object converter or a solid object converter.

17. The system as in claim 11, further comprising a classifier learner configured to acquire a plurality of two-dimensional images, select at least one region in each of the plurality of two-dimensional images and annotate the selected at least one region with the identifier of an optimal converter based on a type of the selected at least one region, wherein the region classifier is optimized based on the annotated two-dimensional images.

18. The system as in claim 17, wherein the type of selected at least one region corresponds to a fuzzy object.

19. The system as in claim 17, wherein the type of selected at least one region corresponds to a solid object.

20. A program storage device readable by a machine, tangibly embodying a program of instructions executable by the machine to perform method steps for creating stereoscopic images from a two-dimensional image, the method comprising;

acquiring a two-dimensional image;

identifying a region of the two dimensional image;

classifying the identified region;

selecting a conversion mode based on the classification of the identified region;

converting the region into a three-dimensional model based on the selected conversion mode; and

creating a complementary image by projecting the three-dimensional model onto an image plane different than an image plane of the two-dimensional image.