Method of animating a graphics character using fuzzy processing layers

• US 7,697,004 B2
• Filed: 05/18/2009
• Issued: 04/13/2010
• Est. Priority Date: 08/10/2001
• Status: Expired due to Term

• Current Assignee: Stephen John Regelous, Stephen Noel Regelous
• Original Assignee: Stephen John Regelous, Stephen Noel Regelous
• Inventors: Regelous, Stephen John
• Primary Examiner(s): Repko; Jason M
• Application Number:
  US12/453,674
• Publication Number:
  US 20090284533A1
• Time in Patent Office: 330 Days
• Field of Search: 345/957, 345/958, 706/920
• US Class Current: 345/474
• CPC Class Codes: G06T 13/40 of characters, e.g. humans, animals or virtual beings

Abstract

A computer implemented method of generating behavior of a graphics character within an environment including a selected graphics character and one or more graphics elements, the method comprising: generating an image of the environment from a perspective of the selected graphics character; processing the image using an artificial intelligence engine with one or more layers to determine an activation value for the graphics character wherein at least one of the layers is a fuzzy processing layer, and generating the behavior of the graphics character based on the activation value.

Claims

1. A computer implemented method of generating behavior of a graphics character within an environment including a selected graphics character and one or more graphics elements, the method comprising:

generating pixel values to form an image of the environment from a perspective of the selected graphics character;

processing the image using artificial intelligence engine with one or more layers to determine an activation value for the graphics character wherein at least one of the layers is a fuzzy processing layer, directly applying pixel values to the fuzzy processing layer to generate the activation value, and generating the behavior of the graphics character based on the activation value, wherein the image comprises pixels and each pixel is processed by the fuzzy processing layer according to a fuzzy membership function to obtain fuzzy logic values to be used to determine the activation value, wherein the fuzzy processing layer applies fuzzy membership functions to each pixel value to obtain fuzzy weightings and the fuzzy weightings are according to one of the group consisting of;

the pixel'"'"'s leftness;

the pixel'"'"'s centreness;

the pixel'"'"'s rightness;

the pixel'"'"'s very nearness;

the pixel'"'"'s nearness;

the pixel'"'"'s farness.

2. A method as claimed in claim 1 wherein fuzzy rules are applied by a second fuzzy processing layer to the fuzzy logic values for each pixel to obtain output values.

3. A method as claimed in claim 1 wherein a neural network utilizes the fuzzy logic values to obtain output values.

4. A method as claimed in claim 1 wherein processing further comprises using middle layer to process input values to obtain activation values.

5. A method as claimed in claim 4 wherein the fuzzy logic values are the input values processed by the middle layer.

6. A method as claimed in claim 4 wherein the middle layer is a fuzzy logic network.

7. A method as claimed in claim 4 wherein the middle layer is a neural network.

8. A method as claimed in claim 4 wherein the middle layer is a binary logic network.

9. A method as claimed in claim 6 wherein a defuzzifying output layer is utilised to provide activation values.

10. A method as claimed in claim 1 wherein image and sound information is processed to determine the activation value for the graphics character.

11. A method as claimed in claim 1 wherein the image is rendered using a scanline rendering technique.

12. A method as claimed in claim 1 wherein the image is generated by rendering images for a plurality of adjacent sub space areas, wherein the images are rendered as viewed from a common viewpoint and different orientations.

13. The method of claim 1, wherein the pixel values are applied pixel by pixel.

14. The method of claim 1, wherein the fuzzy processing layer applies fuzzy membership functions to each pixel value in parallel.