Systems and methods for the automatic detection of lithium batteries in cargo, baggage, parcels, and other containers

Patent metadata

Field	Value
Publication number	US-9733385-B2
Application number	US-201514800595-A
Country	US
Kind code	B2
Filing date	Jul 15, 2015
Priority date	Jul 15, 2014
Publication date	Aug 15, 2017
Grant date	Aug 15, 2017

Abstract

The present specification discloses methods for scanning objects for the presence of lithium batteries. Normalized transmission X-ray data is used to generate organic, effective Z, and attenuation-based images. These images are then segmented using a combination of thresholding and region growing techniques to identify regions of interest. The regions are classified as lithium batteries or other objects, based on characteristics such as area of the region, its organic intensity, Z eff number, shape, spatial arrangement and texture.

First claim

We claim:

1. An inspection system for detecting the presence of lithium batteries, comprising:
at least one radiation source;
at least one detector array corresponding to the at least one radiation source; and,
a processing unit comprising at least one processor, memory, and programmatic instructions, wherein, through the operation of the at least one processor, the memory, and the programmatic instructions, said processing unit:
obtains transmission X-ray data representative of a generated radiographic image;
normalizes said X-ray data to remove effects of dark current and to remove effects of pixel-to-pixel variations;
generates at least one of organic image data and effective Z image data from said normalized data;
segments said at least one of organic image data and effective Z image data based on an organic density of materials and a threshold effective atomic number (Z eff ), respectively;
identifies at least one region of interest in said at least one of organic image data and effective Z image data based on said segmentation, wherein said at least one region of interest comprises a plurality of characteristics; and
classifies said at least one region of interest as containing at least one lithium battery based on the plurality of characteristics of said at least one region of interest.

2. The inspection system of claim 1 , wherein said at least one region of interest is identified in segmented images based on properties such as area, shape, organic thickness, and Z eff number.

3. The inspection system of claim 1 , wherein the plurality of characteristics used by said processing unit to classify the at least one region of interest as containing at least one lithium battery include area, organic intensity, Z eff number, shape, X-ray attenuation level, spatial arrangement and texture of said region.

4. The inspection system of claim 1 , wherein the processing unit classifies said at least one region of interest as containing at least two lithium batteries based on the plurality of characteristics of said at least one region of interest and wherein said plurality of characteristics include a spatial arrangement defined by a first rectangular portion having a Z eff in a range of 14 to 20 and an organic density represented by a pixel map of at least 4000 pixels, a second rectangular portion having a Z eff in a range of 14 to 20 and an organic density represented by a pixel map of at least 4000 pixels, and a gap separating the first rectangular portion and second rectangular portion, said gap having a Z eff of less than 14.

5. The inspection system of claim 1 , wherein the system uses one X-ray source operating at a single voltage.

6. The inspection system of claim 1 , wherein the system uses two X-ray sources, each operating at a single voltage.

7. The inspection system of claim 6 , wherein the two X-ray sources switch between two operating voltages in an interlaced fashion.

8. The inspection system of claim 6 , wherein a first X-ray source is approximately perpendicular to a second X-ray source.

9. The inspection system of claim 6 wherein, the inspection system produces two substantially simultaneous images from the two X-ray sources.

10. The inspection system of claim 9 wherein, the two simultaneous images provide a horizontal view and a vertical view of cargo being scanned.

11. The inspection system of claim 1 , wherein the system uses from three to five X-ray sources, each operating at a single voltage.

12. The inspection system of claim 1 , wherein the detector array comprises dual-energy detectors.

13. The inspection system of claim 1 , wherein said threshold effective atomic number separates low-Z and high-Z materials in the effective Z image data.

14. The inspection system of claim 1 , wherein during the segmentation of organic images, the processing unit applies region growing techniques.

15. The inspection system of claim 14 , wherein said processing unit is configured to apply the region growing techniques when scanning cargo, baggage, or parcels with high clutter.

16. The inspection system of claim 1 , wherein results of a scan are manually verified to fine-tune identification criteria for lithium batteries.

17. A method for detecting the presence of at least one lithium battery in a target in an inspection system comrising a processing unit, said method comprising:
obtaining transmission X-ray data representative of a generated radiographic image of the target;
normalizing said X-ray data to remove effects of at least one of dark current or pixel-to-pixel variation;
generating effective Z images from said normalized data;
segmenting said effective Z images based on a threshold effective atomic number (Z eff );
identifying at least one region of interest in said effective Z images based on said segmentation; and
classifying said at least one region of interest as containing said at least one lithium battery based on characteristics of said at least one region of interest, said characteristics include a first substantially rectangular portion having a Z eff in a range of 14 to 20.

18. The method of claim 17 wherein the processing unit is configured to identify said at least one region of interest in segmented images based on properties such as area, shape, organic thickness, and Z eff number.

19. The method of claim 17 wherein the characteristics used for classifying at least one region of interest as containing at least one lithium battery further includes area, organic intensity, X-ray attenuation level, spatial arrangement and texture of said region.

20. The method of claim 17 wherein the characteristics used for classifying at least one region of interest as containing at least one lithium battery further includes a first substantially rectangular portion having a Z eff in a range of 14 to 20, a second substantially rectangular portion having a Z eff in a range of 14 to 20 and a gap separating the first substantially rectangular portion and second substantially rectangular portion, said gap having a Z eff of less than 14.

21. The method of claim 20 wherein an organic density of the first substantially rectangular portion is at least 4000 pixels and an organic density of the second substantially rectangular portion is at least 4000 pixels.

22. The method of claim 17 , wherein the processing unit is adapted to use the threshold effective atomic number to separate low-Z and high-Z materials in the effective Z images.

23. The method of claim 17 , wherein the processing unit is configured to apply region growing techniques when scanning cargo, baggage, or parcels with high clutter.

Assignees

• Rapiscan Systems Inc

Inventors

• Franco Ed
• Tang Ling
• Shea Jing Ye
• Huang Minyang
• Browne Jolyon

Classifications

• G01T1/36

  Measuring spectral distribution of X-rays or of nuclear radiation {spectrometry (pulse selection circuits per se H03K; investigation of materials by radiation diffraction G01N23/20; spectrometer tubes H01J49/00)} · CPC title

• G01T1/17

  Circuit arrangements not adapted to a particular type of detector {(pulse-selection circuits H03K, G01R)} · CPC title

• G01N23/04

  and forming images of the material · CPC title

• G01V5/0041 Primary

  Physics · mapped topic

• G01V5/224 Primary

  Multiple energy techniques using one type of radiation, e.g. X-rays of different energies · CPC title