System and method for video object identification

• US 8,005,262 B2
• Filed: 07/16/2007
• Issued: 08/23/2011
• Est. Priority Date: 07/16/2007
• Status: Expired due to Fees

• Current Assignee: Hugh Griffin
• Original Assignee: Hugh Griffin
• Inventors: Griffin, Hugh
• Primary Examiner(s): Desire; Gregory M
• Application Number:
  US11/778,394
• Publication Number:
  US 20090022405A1
• Time in Patent Office: 1,499 Days
• Field of Search: 382/103, 382/107, 382/109
• US Class Current: 382/103
• CPC Class Codes: G06V 10/242 by image rotation, e.g. by 90 degrees
• CPC Class Codes: G06V 10/46 Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features colour feature extraction G06V10/56
• CPC Class Codes: G06V 10/752 Contour matching

Abstract

A video object identification system used to identify an object, to locate its position in the view, and to determine its angular orientation. It digitizes a field of image view and subdivides the viewed area into a grid pattern of small cells. It then encodes the angle of a tangent line segment within each cell (when present) at the boundary of objects in the view. It determines rate-of-curvature of the boundary to develop a linear signature for the object. The system breaks the linear signature into segments that can be normalized to be constant regardless of the scale of the image. It then generates identification numbers to identify the object through a mathematics process. The system utilizes pipeline processing to the point where the results are applied to a microprocessor. The microprocessor analyzes a stored image field of view in encoded format to determine object perimeter cell locations (a chaining process).

Claims

1. A method for identification of a video image object comprising the steps of:

receiving a first video image from a video device;

digitizing said first video image to generate a second video image;

calculating encoded object edge data segments based on said second video image including the angle tangent to the object edge segments using a digital video processor, wherein said object edge segments makeup an object perimeter;

calculating angular rate of change data based on said object perimeter;

matching said angular rate of change data to one of a plurality of known object templates to identify an object.

2. The method of claim 1, wherein angular rate of change data is a recognizable linear signature of an object when its perimeter is traced.