System and method for detecting nuclear material in shipping containers

• US 7,813,540 B1
• Filed: 01/13/2005
• Issued: 10/12/2010
• Est. Priority Date: 01/13/2005
• Status: Expired due to Fees

• Current Assignee: Oro Grande Technology, LLC
• Original Assignee: Oro Grande Technologies LLC
• Inventors: Kraft, Clifford H.
• Primary Examiner(s): Bella; Matthew C
• Assistant Examiner(s): Newman; Michael A
• Application Number:
  US11/034,498
• Time in Patent Office: 2,098 Days
• Field of Search: 382/103, 382/141, 382/143, 382/155, 382/156, 382/159, 382/181, 382/191, 382/203, 382/204, 382/209, 382/224, 378/57
• US Class Current: 382/143
• CPC Class Codes: G01V 5/22 Active interrogation, i.e. by irradiating objects or goods using external radiation sources, e.g. using gamma rays or cosmic rays
• CPC Class Codes: G06F 18/00 Pattern recognition
• CPC Class Codes: G06V 2201/05 Recognition of patterns representing particular kinds of hidden objects, e.g. weapons, explosives, drugs

Abstract

A system and method for detecting metal contraband such as weapons related material in shipping containers where a container is scanned with at least one penetrating beam, preferably a tomographic x-ray beam, and at least one image is formed. The image can be analyzed by a pattern recognizer to find voids representing metal. The voids can be further classified with respect to their 2 or 3-dimensional geometric shapes. Container ID and contents or bill of lading information can be combined along with other parameters such as total container weight to allow a processor to generate a detection probability. The processor can use artificial intelligence methods to classify suspicious containers for manual inspection.

Claims

1. A method for scanning shipping containers for nuclear material comprising:

scanning a shipping container with a rotating CT-based x-ray device producing CT scan data as said shipping container moves through a scan area;

slicing said scan data into a sequence of 2-dimensional slices;

locating nuclear weapon component target shapes in said 2-dimensional slices including spheres, cylinders, cannon barrels or pellets, using pattern classification techniques;

re-slicing said scan data along at least two different axes to verify said possible shapes;

outputting scan recognition signals to an artificial intelligence processor relating to detection of any of said nuclear weapon component target shapes in a particular container;

comparing at said artificial intelligence processor said scan recognition signals with data such as a bill of lading container content lists, port of origin data or container weight to produce an event probability number;

quantifying a total metal content for said container;

raising said event probability number when a contents list for said container does not show a total metal content compatible with the total metal content for the container;

outputting a risk alarm from any container having an event probability greater than a predetermined value.

2. The method of claim 1 further comprising:

locating voids in said 2-dimensional slices;

examining said voids along different slice axes;

examining said voids with different x-ray energies.

3. The method of claim 1 further comprising raising said event probability number when a container is determined to contain a plurality of small metal parts.

4. The method of claim 1 further comprising raising said event probability when said container contains pipes-shaped objects.