Method for three dimensional image reconstruction
View Patent ↗A method for three-dimensional (3D) image reconstruction includes the steps of registering an orthographic image of a scene, combining a photogrammetric image and a technical drawing of the scene to form a co-registered orthographic and perspective (COP) image, and reconstructing a 3D image from the COP image.
1. A method for three-dimensional (3D) image reconstruction comprising the steps of:
registering drawings with a calibrated image database for creating a set of calibrated images;
generating a co-registered orthographic and perspective (COP) image from said set of calibrated images;
repeating said step of generating a COP image utilizing different ones from said set of calibrated images, thereby generating at least one further COP image; and
combining said first and at least one further COP image and thereby refining a resulting reconstructed image.
2. A method for three-dimensional (3D) image reconstruction as recited in claim 1 , wherein said step of registering drawings comprises the steps of:
estimating a metric planar transformation between a drawing in space relative to said set of calibrated images; and
utilizing said metric planar transformation to register drawings.
3. A method for three-dimensional (3D) image reconstruction as recited in claim 1 , wherein said step of registering drawings comprises the steps of:
estimating a homography between each image of said set and said drawing; and
blending said drawing into each image of said set.
4. A method for three-dimensional (3D) image reconstruction as recited in claim 1 , wherein said step of reconstructing a 3D image from said COP image comprises:
a step of utilizing user identification of corresponding features within said COP image for said reconstructing.
5. A method for three-dimensional (3D) image reconstruction as recited in claim 1 , including a step of including user input data in said step of blending.