Systems and methods for detecting luggage in an imaging system
Inventors
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Abstract
A luggage detection device is configured to detect luggage by generating computed tomography (CT) imaging slices. For each of the CT imaging slices, the luggage detection device is configured to identify at least one region within the CT imaging slice for removal based on at least one predefined rule, to remove pixel data associated with the at least one identified region within the CT imaging slice, to generate a pixel count representing a number of pixels in the modified CT imaging slice that include a value above a threshold pixel value, and to generate an object indicator based on a determination that the generated pixel count is above a threshold pixel count. The luggage detection device is further configured to display at least one of the plurality of CT image slices based on the presence of the corresponding baggage indicator.
Core Innovation
The invention relates to detecting luggage in a computed tomography (CT) imaging system using a luggage detection device that includes a processor coupled to a memory device and to the CT imaging system. The device receives CT imaging data generated by detecting an x-ray beam projected across a gantry, and filters detected edges of the luggage by rebinning the CT imaging data into an intermediate format, performing at least one statistical measure on the CT imaging data in the intermediate format, and determining that the statistical measure satisfies a predefined statistical threshold.
The device generates a plurality of CT imaging slices from the CT imaging data by applying a reconstruction transformation to the CT imaging data. For each CT imaging slice, the device identifies at least one region within the CT imaging slice for removal based on at least one predefined rule, and modifies the CT imaging slice by removing pixel data associated with the identified region.
The device generates a pixel count representing a number of pixels in the modified CT imaging slice wherein each pixel has a pixel value above a predefined threshold pixel value. Based on a determination that the generated pixel count is above a predefined threshold pixel count, the device generates an object indicator representing whether luggage is detected in the CT imaging system.
The device displays to a user a three-dimensional representation based on only the CT image slices that include an object indicator, enabling the user to easily visually identify false positives and false negatives.
Claims Coverage
The independent claims are clm-00001, clm-00008, and clm-00014. They share six inventive features.
CT-based luggage detection device with intermediate-format edge filtering
A luggage detection device receives CT imaging data generated by detecting an x-ray beam projected across a gantry and filters detected edges by rebinning into an intermediate format, performing at least one statistical measure, and satisfying a predefined statistical threshold.
Reconstruction of CT imaging slices
A plurality of CT imaging slices is generated from the CT imaging data by applying a reconstruction transformation.
Removal of pixel data in predefined regions
For each CT imaging slice, at least one region is identified for removal based on at least one predefined rule, and pixel data associated with the identified region is removed.
Threshold-based pixel count
A pixel count is generated representing a number of pixels in the modified CT imaging slice wherein each pixel has a pixel value above a predefined threshold pixel value.
Object indicator
An object indicator is generated based on a determination that the pixel count is above a predefined threshold pixel count.
Three-dimensional representation using only slices with an object indicator
A three-dimensional representation is displayed based on only the CT image slices that include the object indicator, to visually identify false positives and false negatives.
Across clm-00001, clm-00008, and clm-00014, the claims converge on intermediate-format rebinning with a predefined statistical threshold, reconstruction of multiple CT slices, removal of pixel data in regions selected by predefined rules, threshold-based generation of an object indicator, and display of a three-dimensional representation using only slices that include the object indicator.
Stated Advantages
Enables the user to easily visually identify false positives and false negatives.
Documented Applications
Displaying a three-dimensional representation for luggage detection in a CT imaging system based only on CT image slices that include an object indicator.
Interested in licensing this patent?