System and method for mosaicing digital ortho-images

• US 7,925,114 B2
• Filed: 08/05/2009
• Issued: 04/12/2011
• Est. Priority Date: 09/19/2002
• Status: Expired due to Fees

• Current Assignee: VI Technologies, LLC (VI GP LLC (f/k/a M7 Visual Intelligence GP LLC))
• Original Assignee: Visual Intelligence LP (f/k/a M7 Visual Intelligence LP) (VI GP LLC (f/k/a M7 Visual Intelligence GP LLC))
• Inventors: Mai, Tuy Vu, Smitherman, Chester L.
• Primary Examiner(s): Carter; Aaron W
• Application Number:
  US12/462,563
• Publication Number:
  US 20100020097A1
• Time in Patent Office: 615 Days
• Field of Search: 382/284, 345629-641, 348584-588, 348143-147
• US Class Current: 382/284
• CPC Class Codes: G06T 3/4038 Image mosaicing, e.g. composing plane images from plane sub-images

Abstract

The present invention provides a system and method for mosaicing multiple input images, captured by one or more remote sensors, into a seamless mosaic of an area of interest. Each set of input images captured by the remote sensors within a capture interval are ortho-rectified and mosaiced together into a composite image. Successive composite images, along a given flight path, are then mosaiced together to form a strip. Adjacent strips are then mosaiced together to form a final image of the area of interest.

Claims

1. A method of mosaicing two overlapping digital input images together to form an output image, comprising the steps of:

providing a reference image, comprising a number of green-dominant pixels having certain average color intensity and average elevation;

providing a secondary image, comprising a number of green-dominant pixels having certain average color intensity and average elevation, that overlaps the reference image in an overlap area;

scaling pixel values of the secondary image within the overlap area such that the color intensity of the secondary image green-dominant pixels within the overlap area is equivalent to the average color intensity of the reference image green-dominant pixels within the overlap area;

selecting an initial seam line within the overlap area;

determining a position of an elevated feature in a small segment of the overlapping area from a digital elevation model; and

establishing the seam line within the overlap area, wherein the route of the seam line is altered based upon the position of an elevated feature.

2. The method of claim 1, further comprising a blending process for smoothing image transition within the overlap area.

3. The method of claim 2, wherein the blending process assigns a relative weight, determinative of inclusion in the output image, to the pixels of the secondary image.

4. The method of claim 3, wherein the relative weight ranges between zero, indicating no inclusion, and unity, indicating full inclusion.