Sampling method and image processing apparatus of CS-RANSAC for estimating homography

1. A sampling method for estimating a homography matrix that represents conversion correlations between pluralities of images by means of Constraint Satisfaction-Random Sample Consensus (CS-RANSAC), the method comprising:

sampling, to divide an input image into a form of grids (N by N), select features, which are used for calculating a homography matrix, from features, which are abstracted from the input image, by means of a random sampling, and inspect whether the features selected by the random sampling satisfy constraints, wherein the sampling is configured to dynamically apply grid sizes in accordance with a distribution pattern of the features abstracted from the input image;

executing model estimation to calculate the homography matrix from the features only if the selected features satisfy the constraints; and

determining a position of an object in the input image based on the executed model estimating locations of the selected features in the input image relative to the abstracted features in the input image.

2. The sampling method according to claim 1 , wherein the sampling is configured to dynamically apply grid sizes and constraints in accordance with a distribution pattern of the features abstracted from the input image.

3. The sampling method according to claim 1 , wherein the sampling is configured to calculate the homography matrix only if the constraints are satisfied by reapplying the random sampling to the features abstracted from the input image unless the features selected through the random sampling satisfy the constraints.

4. The sampling method according to claim 1 , wherein the sampling is configured to reselect features, which are used for calculating the homography matrix, with reference to the predetermined number of iteration times and the maximum number of sampling times unless the features selected through the random sampling satisfy the constraints.

5. The sampling method according to claim 4 , wherein a size of a grid area, in which the features are dispersedly classified, is dynamically determined by a distribution pattern of the features abstracted from the input image.

6. The sampling method according to claim 1 , wherein the sampling is configured to dispersedly classify features, which are distributed over the whole area of the input image, and select the features, which are used for calculating the homography matrix, by applying Constraint Satisfaction Problems (CSP).

7. The sampling method according to claim 6 , wherein the CSP is configured to include variables that represent the features, domains that represent positional correlations of the features, and the constraints.

8. The sampling method according to claim 1 , wherein the sampling is configured to execute a predisposing process that divides the input image of the plural images into pluralities of grid areas, and classifies the features, which are abstracted from the input image, into the grid areas.

9. The sampling method according to claim 8 , wherein the sampling is configured to classify the features, which correspond to each unit grid, with reference to coordinate values of the features.

10. The sampling method according to claim 1 , wherein the sampling is configured to apply at least one of linear and distance constraints, the linear constraint being configured to prevent other features from being selected at a position forming linearity with the selected features, and the distance constraint being configured to prevent other features from being selected in a distance from the selected features.

11. A computer readable hardware storage device including instructions to control a computer system to execute a Constraint Satisfaction-Random Sample Consensus (CS-RANSAC) algorithm,

wherein the CS-RANSAC algorithm is a method of a homography matrix that represents conversion correlations between pluralities of images,

wherein the instructions is configured to control the computer system through a method comprising:

sampling, to select features, which are used for calculating a homography matrix, from features, which are abstracted from an input image of the plural images, by means of a random sampling, and inspect whether the features selected by the random sampling satisfy constraints, wherein the sampling is configured to apply at least one of linear and distance constraints, the linear constraint being configured to prevent other features from being selected at a position forming linearity with the selected features, and the distance constraint being configured to prevent other features from being selected in a distance from the selected features;

executing model estimation to calculate the homography matrix from the features that satisfy the constraints; and

determining a position of an object in the input image based on the executed model estimating locations of the selected features in the input image relative to the abstracted features in the input image.

12. The computer readable hardware storage device according to claim 11 , wherein the sampling is configured to execute a predisposing process that divides the input image of the plural images into pluralities of grid areas, and classifies the features, which are abstracted from the input image, into the grid areas.

13. An image processing apparatus for estimating a homography matrix that represents conversion correlations between pluralities of images by means of Constraint Satisfaction-Random Sample Consensus (CS-RANSAC), comprising:

a processor, a memory, and a display; and

a set of instructions stored in the memory that cause the processor to perform the following:

to select features, which are used for calculating a homography matrix, from features, which are abstracted from the input image, by means of a random sampling, and inspect whether the features selected by the random sampling satisfy constraints;

calculate the homography matrix from the features that satisfy the constraints; and

determine a position of an object in the input image based on the executed model estimating locations of the selected features in the input image relative to the abstracted features in the input image,

wherein the image processing apparatus, as the features selected through the random sampling disagree with the constraints, is configured to reselect features, which are used for calculating the homography matrix, from features, which are abstracted from the input image, with reference to similarity of the abstracted features.

14. The image processing apparatus according to claim 13 , the set of instructions further causing the processor to: dynamically apply one of pluralities of predefined grid sizes in accordance with a distribution pattern of the feature abstracted from the input image.

15. The image processing apparatus according to claim 13 , the set of instructions, as the features selected through the random sampling disagree with the constraints, further causing the processor to: reapply the random sampling to the features abstracted from the input image, and reselect features for calculating the homography matrix.

16. The image processing apparatus according to claim 13 , the set of instructions further causing the processor to: execute a predisposing process that divides the input image of the plural images into pluralities of grid areas, and classifies the features, which are abstracted from the input image, into the grid areas.

17. The image processing apparatus according to claim 13 , the set of instructions further causing the processor to: apply at least one of linear and distance constraints, the linear constraint being configured to prevent other features from being selected at a position forming linearity with the selected features, the distance constraint being configured to prevent other features from being selected in a distance from the selected features.