Automatic annotation generation

• US 8,462,176 B1
• Filed: 10/21/2009
• Issued: 06/11/2013
• Est. Priority Date: 12/01/2008
• Status: Active Grant

• Current Assignee: Autodesk, Inc.
• Original Assignee: Autodesk, Inc.
• Inventors: Stubbs, Cameron M., Cole, Brandon Willets
• Primary Examiner(s): HARRISON, CHANTE E
• Application Number:
  US12/603,219
• Time in Patent Office: 1,329 Days
• Field of Search: 345/619, 345/419, 345/617, 382/128
• US Class Current: 345/619
• CPC Class Codes: G06T 19/00 Manipulating 3D models or images for computer graphics
• CPC Class Codes: G06T 2207/20041 Distance transform
• CPC Class Codes: G06T 2219/004 Annotating, labelling
• CPC Class Codes: G06T 7/60 Analysis of geometric attributes

Abstract

Systems, methods, and computer program products automatically generate and place annotations on an image (e.g., a rendering of a computer aided design model). Regions within an image are identified, and a representation of the image is generated, where the representation characterizes each of the image regions. Annotation leader locations are determined based on the representation of the image. Thereafter, annotation leaders are automatically generated and displayed using at the annotation leader locations.

Claims

1. A computer-implemented method comprising:

identifying image regions within an image, wherein each of the image regions is associated with a region identifier, the region identifier corresponding to a rendered color for that image region, and wherein the image region comprises image pixels and a region boundary, the region boundary defining a boundary of the image region based on the rendered color for the image region;

generating a representation of the image using a Gaussian blur filter, wherein the representation of the image characterizes each of the image regions and wherein, for each image region, the representation of the image indicates weighted values of the image pixels of the image region according to a distance between the image pixels of the image region and the region boundary;

determining annotation leader locations for the image based on, at least, the weighted values of the image pixels in the representation of the image;

generating annotation leaders at the annotation leader locations; and

providing the annotation leaders and the image.

2. The method of claim 1, wherein the image defines an assembly model having assembly components and the image regions correspond to the assembly components, the assembly model and the assembly components generated by use of a computer aided design program.

3. The method of claim 1 wherein generating the representation of the image, further comprises:

for each of the image regions, determining one or more respective region centers based on a distance to the image region boundary.

4. The method of claim 3, wherein determining the annotation leader locations further comprises:

determining the annotation leader locations based on the one or more respective region centers.

5. The method of claim 3, wherein each of the image regions has respective contour edges defining an outline of the image region, and wherein determining the one or more region centers based on the distance to the image region boundary comprises:

determining a distance to one or more of the contour edges of the image region.

6. The method of claim 5, wherein the contour edges define a three-dimension outline of the corresponding image region.

7. The method of claim 1, further comprising:

for each of the annotation leader locations, generating an annotation leader description site; and

associating each annotation leader description site with a corresponding annotation leader location.

8. A system comprising:

a computer-readable medium having instructions stored thereon; and

data processing apparatus programmed to perform operations comprising;

identifying image regions within an image, wherein each of the image regions is associated with a region identifier, the region identifier corresponding to a rendered color for that image region, and wherein the image region comprises image pixels and a region boundary, the region boundary defining a boundary of the image region based on the rendered color for the image region;

generating a representation of the image using a Gaussian blur filter, wherein the representation of the image characterizes each of the image regions and wherein, for each image region, the representation of the image indicates weighted values of the image pixels of the image region according to a distance between the image pixels of the image region and the region boundary;

determining annotation leader locations for the image based on, at least, the weighted values of the image pixels in the representation of the image;

generating annotation leaders at the annotation leader locations; and

providing the annotation leaders and the image.

9. The system of claim 8 wherein the image defines an assembly model having assembly components and the image regions correspond to the assembly components, the assembly model and the assembly components generated by use of a computer aided design program.

10. The system of claim 8 wherein generating the representation of the image, further comprises:

for each of the image regions, determining one or more respective region centers based on a distance to the image region boundary.

11. The system of claim 10 wherein determining the annotation leader locations further comprises:

determining the annotation leader locations based on the one or more respective region centers.

12. The system of claim 10 wherein each of the image regions has respective contour edges defining an outline of the image region, and wherein determining the one or more region centers based on the distance to the image region boundary comprises:

determining a distance to one or more of the contour edges of the image region.

13. The system of claim 12 wherein the contour edges define a three-dimension outline of the corresponding image region.

14. The system of claim 8 wherein the operations further comprise:

for each of the annotation leader locations, generating an annotation leader description site; and

associating each annotation leader description site with a corresponding annotation leader location.

15. A computer-readable medium having instructions stored thereon that, when executed by data processing apparatus, cause the data processing apparatus to perform operations comprising:

identifying image regions within an image, wherein each of the image regions is associated with a region identifier, the region identifier corresponding to a rendered color for that image region, and wherein the image region comprises image pixels and a region boundary, the region boundary defining a boundary of the image region based on the rendered color for the image region;

generating a representation of the image using a Gaussian blur filter, wherein the representation of the image characterizes each of the image regions and wherein, for each image region, the representation of the image indicates weighted values of the image pixels of the image region according to a distance between the image pixels of the image region and the region boundary;

determining annotation leader locations for the image based on, at least, the weighted values of the image pixels in the representation of the image;

generating annotation leaders at the annotation leader locations; and

providing the annotation leaders and the image.

16. The computer-readable medium of claim 15 wherein the image defines an assembly model having assembly components and the image regions correspond to the assembly components, the assembly model and the assembly components generated by use of a computer aided design program.

17. The computer-readable medium of claim 15 wherein generating the representation of the image, further comprises:

for each of the image regions, determining one or more respective region centers based on a distance to the image region boundary.

18. The computer-readable medium of claim 17 wherein determining the annotation leader locations further comprises:

determining the annotation leader locations based on the one or more respective region centers.

19. The computer-readable medium of claim 17 wherein each of the image regions has respective contour edges defining an outline of the image region, and wherein determining the one or more region centers based on the distance to the image region boundary comprises:

determining a distance to one or more of the contour edges of the image region.

20. The computer-readable medium of claim 19 wherein the contour edges define a three-dimension outline of the corresponding image region.

21. The computer-readable medium of claim 15 wherein the operations further comprise:

for each of the annotation leader locations, generating an annotation leader description site; and

associating each annotation leader description site with a corresponding annotation leader location.