Confirmed boundary pattern matching

• US 5,168,530 A
• Filed: 08/29/1988
• Issued: 12/01/1992
• Est. Priority Date: 08/29/1988
• Status: Expired due to Fees

• Current Assignee: Raytheon Company Lexington Massachusetts 02173
• Original Assignee: Raytheon Company (Rtx Corporation)
• Inventors: Geller, Harold J., Peregrim, Theodore J., Richter, Stephen L.
• Primary Examiner(s): CAIN, DAVID C
• Application Number:
  US07/237,934
• Time in Patent Office: 1,555 Days
• Field of Search: 382/22, 382/34, 382/41, 382/48, 382/49, 382/50, 382/27, 382/56, 364/135
• US Class Current: 382/199
• CPC Class Codes: G06T 2207/10044 Radar image
• CPC Class Codes: G06T 2207/20016 Hierarchical, coarse-to-fine, multiscale or multiresolution image processing; Pyramid transform
• CPC Class Codes: G06T 2207/30212 Military
• CPC Class Codes: G06T 7/12 Edge-based segmentation
• CPC Class Codes: G06T 7/33 using feature-based methods
• CPC Class Codes: G06T 7/70 Determining position or orientation of objects or cameras camera calibration G06T7/80
• CPC Class Codes: G06V 10/36 Applying a local operator, i.e. means to operate on image points situated in the vicinity of a given point; Non-linear local filtering operations, e.g. median filtering
• CPC Class Codes: G06V 10/757 Matching configurations of points or features

Abstract

A method of aligning two images of the same scene by matching features in a first image to features in a second image is disclosed. The method comprises identifying edges of objects in the first image using two different processes. The edges identified using both processes are compared and combined into one image representing confirmed edges which are readily identified in other images of the same scene. A template is then formed from the confirmed edges which is matched to a subregion of the second image.

Claims

1. In an imaging system representing an image by an array of pixels, a method of selecting pixels in the image representing edges of objects in the image, comprising the steps of:

(a) forming a local window around each pixel in the image;

(b) computing a ratio corresponding to the center pixel in each local window, said ratio being the larger of;

(i) the ratio of the value of the center pixel to the value of the pixel in the local window having a value greater than all other pixels in the local window except a predetermined number; and

(ii) the ratio of the value of the center pixel to the value of the pixel in the local window having a value less than all other pixels in the local window except a predetermined number;

(c) forming an upper mean of the values of a first set of pixels;

(d) forming a lower means of the values of a second set of pixels;

(e) computing a threshold equal to the mean of the upper mean and lower mean; and

(f) selecting pixels to represent edges wherein the selected pixels comprise;

(i) pixels having values above the threshold and adjacent to pixels having values below the threshold; and

(ii) pixels having values below the threshold adjacent to pixels having a value above the threshold.

2. The method of selecting pixels in the image representing edges of the objects as in claim 1 wherein the step of forming an upper mean comprises:

(a) selecting pixels with intensities in a first range;

(b) selecting as a temporary group in a first fraction of the selected pixels having the highest corresponding ratios;

(c) removing pixels from the temporary group having ratios substantially lower and substantially higher than the mean of the ratios corresponding to all pixels in the temporary group and replacing the removed pixels with pixels not previously selected to lower the standard deviation of the ratios of the pixels in the temporary group below a second fraction of the mean of the ratios of the pixels in the temporary group; and

(d) forming the upper mean by averaging the values of the pixels in the temporary group.

3. The method of selecting pixels in the image representing edges of the objects as in claim 2 wherein the pixels selected in the first range having values in the 35th to 90th percentile in comparison to the values of all of the pixels in the image.

4. The method of selecting pixels in the image representing edges of the objects as in claim 1 wherein the step of forming a lower mean comprises:

(a) selecting pixels with intensities in a first range;

(b) selecting as a temporary group in a first fraction of the selected pixels having the lowest corresponding ratios;

(c) removing pixels from the temporary group having ratios substantially lower and substantially higher than the mean of the ratios corresponding to all pixels in the temporary group and replacing the removed pixels with pixels not previously selected to lower the standard deviation of the ratios of the pixels in the temporary group below a second fraction of the mean of the ratios of the pixels in the temporary group; and

(d) forming the lower mean by averaging the values of the pixels in the temporary group.

5. The method of selecting pixels in the image representing edges of the objects as in claim 2 wherein the pixels selected in the first range having values in the 10th to 65th percentile in comparison to the values of all of the pixels in the image.