Confirmed boundary pattern matching

• US 5,173,949 A
• Filed: 08/29/1988
• Issued: 12/22/1992
• 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: Richter, Stephen L., Peregrim, Theodore J., Long, Albert H.
• Primary Examiner(s): CAIN, DAVID C
• Application Number:
  US07/237,933
• Time in Patent Office: 1,576 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: 382/294
• CPC Class Codes: G01S 13/9027 Pattern recognition for feature extraction
• 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 7/74 involving reference images or patches
• 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 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 a system for aligning two images of the same scene, each of such images comprising an array of pixels, a method of forming a template of a portion of the first image for comparison to the second image, said method comprising the steps of:

(a) forming a first map from a portion of the first image, the first map comprising an array of pixels, each pixel in the first map having a value indicating whether the corresponding pixel in the first image represents the edge of an object in the range; and

(b) assigning a first value to each pixel in a template map corresponding to pixels on the first map having values indicating an edge and corresponding to pixels in the image having values above a predetermined threshold, and assigning a second value to each pixel in the template corresponding to pixels in the first map having values indicating an edge and corresponding to pixels in the image having values below a predetermined threshold; and

(c) computing a correlation threshold according to the formula;

space="preserve" listing-type="equation">CR (ln CR)/(CR-1)

where CR represents the ratio of the average value of the pixels in the first image corresponding to pixels in the template map with the first value to the average value of the pixels in the first image corresponding to pixels in the template map with the second value.

2. The method of forming a template as in claim 1 wherein:

(a) the pixels in the template map in a local window around a pixel set to the first value are also set to the first value when the corresponding pixels in the first image are above the predetermined threshold; and

(b) the pixels in the template map in a local window around a pixel set to the second value are also set to the second value when the corresponding pixels in the first image are below the predetermined threshold.