METHODS AND SYSTEMS FOR OBJECT BASED GEOMETRIC FITTING
First Claim
Patent Images
1. An automated process for geometric data fitting, the process comprising:
- (a) obtaining a raster image having a spatial resolution and comprising a plurality of image-objects representing real-world objects;
(b) obtaining a mask dataset comprising a plurality of mask-objects, each mask-object having a center, and each mask-object spatially corresponding to one of the image-objects in the raster image at the same spatial resolution;
(c) defining (i) a distance threshold and (ii) a pseudo-rotation angle applicable to a shift function;
(d) spatially superimposing the mask dataset and the raster image in such a manner that the locations of the plurality of mask-objects approximately corresponds to the locations of the plurality of corresponding image-objects;
(e) locally superimposing a plurality of mask-objects by incrementally moving the plurality of mask-objects over the spatially corresponding image-objects using a shift function including the defined (i) distance threshold and (ii) pseudo-rotation angle until an optimal homogeneity is attained for a plurality of mask-objects; and
(f) generating an optimally fitted dataset comprising a plurality of mask-objects which are individually geometrically fitted.
2 Assignments
0 Petitions
Accused Products
Abstract
Described herein are various implementations of a process and a system for automatically performing object based geometric fitting. The process may include spatially superimposing a mask dataset comprising mask-objects on a raster image comprising image-objects, and locally superimposing individual mask-objects on individual image-objects, until a dataset is obtained wherein mask-objects are geometrically fitted to image-objects.
-
Citations
8 Claims
-
1. An automated process for geometric data fitting, the process comprising:
-
(a) obtaining a raster image having a spatial resolution and comprising a plurality of image-objects representing real-world objects; (b) obtaining a mask dataset comprising a plurality of mask-objects, each mask-object having a center, and each mask-object spatially corresponding to one of the image-objects in the raster image at the same spatial resolution; (c) defining (i) a distance threshold and (ii) a pseudo-rotation angle applicable to a shift function; (d) spatially superimposing the mask dataset and the raster image in such a manner that the locations of the plurality of mask-objects approximately corresponds to the locations of the plurality of corresponding image-objects; (e) locally superimposing a plurality of mask-objects by incrementally moving the plurality of mask-objects over the spatially corresponding image-objects using a shift function including the defined (i) distance threshold and (ii) pseudo-rotation angle until an optimal homogeneity is attained for a plurality of mask-objects; and (f) generating an optimally fitted dataset comprising a plurality of mask-objects which are individually geometrically fitted. - View Dependent Claims (3)
-
-
2. An automated process for geometric data fitting, the process comprising:
-
(a) obtaining a raster image having a spatial resolution and comprising a plurality of image-objects representing real-world objects; (b) obtaining a mask dataset comprising a plurality of mask-objects, each mask-object having a center, and each mask-object spatially corresponding to one of the image-objects in the raster image at the same spatial resolution; (c) defining (I) a distance threshold and (ii) a pseudo-rotation angle applicable to a shift function; (d) spatially superimposing the mask dataset and the raster image in such a manner that the locations of the plurality of mask-objects approximately corresponds to the locations of the plurality of corresponding image-objects; (e) locally superimposing a plurality of mask-objects by incrementally moving the plurality of mask-objects over the spatially corresponding image-objects using a shift function by, for each mask-object (i) determining the homogeneity based on digital numbers in the corresponding raster image that fall within the area of the mask-object; (ii) incrementally shifting the mask-object around its center based on a pseudo-rotation angle projected in the x and y direction; (iii) at each shift increment, calculating and saving the homogeneity of the digital numbers in the raster image that fall within the overlapping area of the mask-objects; (iv) iterating (e)(i) to (e)(iii) until the distance threshold is reached or until an optimal homogeneity is attained; and (v) defining the location and boundary of the mask-object at the optimal homogeneity; and (f) generating a fitted dataset comprising a plurality of mask-objects which are individually geometrically fitted.
-
-
4. A system for providing automated process for geometric data fitting, wherein the system comprises:
-
an input interface for receiving a raster image having a spatial resolution and comprising a plurality of image-objects representing real-world objects; an output interface for providing an indication of geometrically fitted mask-objects corresponding to the image-objects; and a processing unit coupled to the input and the output interfaces, the processing unit being configured to generate a mask dataset comprising a plurality of mask-objects that each have a center and spatially correspond to one of the image-objects in the raster image at the same spatial resolution;
to spatially superimpose the mask dataset and the raster image in such a manner that the locations of the plurality of mask-objects approximately corresponds to the locations of the plurality of corresponding image-objects;
to locally superimpose the plurality of mask-objects by incrementally moving the plurality of mask-objects over the spatially corresponding image-objects using a shift function operating under a defined distance threshold and using a pseudo-rotation angle until an optimal homogeneity is attained for the plurality of mask-objects; and
to define a geometrically fitted dataset comprising the plurality of geometrically shifted mask-objects which are individually optimally and geometrically fitted to the corresponding image-objects. - View Dependent Claims (5, 6, 7, 8)
-
Specification