Method, medium, and system implementing 3D model generation based on 2D photographic images
A modeling method, medium, and system. The modeling method identifies a object within an image by detecting edges within the image, determines a complexity of the identified object based upon detected surface orientations of the identified object relative to a defined surface of the image, selectively, based upon the determined complexity, generates one or more surfaces for a 3D model by identifying one or more vanishing points for one or more corresponding surfaces, respectively, of the identified object and respectively analyzing the identified one or more vanishing points relative to respective determined points of the one or more corresponding surfaces of the image, and generates the 3D model by combining the one or more surfaces in a 3D space.
1. A method of generating a 3-dimensional (3D) model comprising:
detecting edges corresponding to points where changes in image information are equal to or greater than a threshold in an object of a 2D image;
by using geometric information of an extended edge line determined to be positioned closest to a center of the object, from among extended lines of the detected edges converging at at least one vanishing point that is a point at which the extended edge lines intersect each other, calculating a plane equation of a surface of the object corresponding to the at least one vanishing point; and
by using 2D image data and the calculated surface plane equation, generating a 3D model of the object.
2. The method of claim 1 , wherein the geometric information of the extended edge line is a straight line equation of the extended edge line.
3. The method of claim 2 , wherein in the calculating of the plane equation of the surface of the object, the plane equation of the surface is calculated by using the straight line equation of the extended edge line and the coordinates of one point on the surface.
4. The method of claim 1 , wherein if a plurality of vanishing points exist, in the calculating of the plane equation of the surface of the object, the plane equation of a first surface of the object corresponding to a first vanishing point is calculated by using the geometric information of an extended edge line converging at the first vanishing point from among the plurality of vanishing points, and the plane equation of a second surface of the object corresponding to a second vanishing point is calculated by using the geometric information of an extended edge line converging at the second vanishing point from among the plurality of vanishing points.
5. The method of claim 1 , further comprising identifying at least one object forming the 2D image, based on at least one of changes in image characteristics in the 2D image and user input information,
wherein in the detecting of the edges, edges corresponding to points where changes in the image information are equal to or greater than the threshold are detected in any one object among the identified objects.
6. The method of claim 1 , wherein the 2D image data is 2D coordinates and textures of pixels forming the 2D image, and
in the generating of the 3D model of the object, 3D coordinates of the pixels forming the surface are calculated by substituting the 2D coordinates in the plane equation of the surface, and a texture corresponding to each pixel is mapped onto the calculated 3D coordinates of the pixel.
7. The method of claim 6 , wherein in the generating of the 3D model of the object, a texture photographed by a camera facing each surface of the current object is mapped onto the 3D coordinates of the pixels forming each surface of the object.
8. A method of generating a 3-dimensional (3D) model comprising:
detecting edges corresponding to points where changes in image information are equal to or greater than a threshold in an object of a 2D image;
by using geometric information of extended lines of the detected edges converging at at least one vanishing point that is a point at which the extended edge lines intersect each other, calculating a plane equation of a surface of the object corresponding to the at least one vanishing point; and
by using 2D image data and the calculated surface plane equation, generating a 3D model of the object,
further comprising determining the complexity of the object based on the shapes of the detected edges, wherein according to the determined complexity of the object, the plane equation of the surface is selectively calculated.
9. A navigation method in a navigation system comprising:
based on a point at which extended lines of edges corresponding to points where changes in image information are equal to or greater than a threshold in an object of a 2D image, intersect each other, calculating a plane equation of a surface of the object, thereby generating a 3D model in relation to the object; and
extracting a 3D model corresponding to the current position information of the navigation system, from among 3D models, including the generated 3D model, and rendering the extracted 3D model on a 2D plane corresponding to the moving direction of a mobile body on which the navigation system is mounted,
wherein the plane equation of the surface of the object is calculated by using the geometric information of an extended edge line determined to be positioned closest to a center of the object, from among the extended edge lines converging at the vanishing point.
10. A modeling method, comprising:
identifying a object within an image by detecting edges within the image;
determining a complexity of the identified object based upon detected surface orientations of the identified object relative to a defined surface of the image;
selectively, based upon the determined complexity, generating a plane equation of one or more surfaces for a 3D model by identifying one or more vanishing points for one or more corresponding surfaces, respectively, of the identified object and respectively analyzing the identified one or more vanishing points relative to respective determined points of the one or more corresponding surfaces of the image; and
generating the 3D model by combining the one or more surfaces in a 3D space.
11. A modeling method, comprising:
identifying a object within an image by detecting edges within the image;
generating a plane equation of one or more surfaces for a 3D model by identifying one or more vanishing points for one or more corresponding surfaces, respectively, of the identified object and respectively analyzing the identified one or more vanishing points relative to respective determined points of the one or more corresponding surfaces of the image and a corresponding determined line within each of the one or more corresponding surfaces, with each corresponding determined line within each respective surface being a mid-line across the respective surface between two edge lines substantially perpendicular to a line substantially parallel with an identified bottom surface of the image; and
generating the 3D model by combining the one or more surfaces in a 3D space.