L-3 Communications Security and Detection Systems Corporation

L-3 Security & Detection Systems, Inc.

Leidos Security Detection & Automation, Inc.

L-3 Communication Security and Detection Systems Corp.

Andrew Dean Foland

Boris Oreper

Richard Franklin Eilbert

Nikolay Rolshud

Vitaliy Ziskin

David Perticone

Michael R Gambini

Thomas David Plamondon

Michael H Schmitt

Brian Joel Baker

Andrew David Smith

Prabhav Morje

Kenneth E Prather

Justin L Wright

A computing-device implemented system and method for identifying an item in an x-ray image is described. The method includes training a machine learning algorithm with at least one training data set of x-ray images to generate at least one machine-learned model. The method further includes receiving at least one rendered x-ray image that includes an item, identifying the item using the at least one model, and generating an automated detection indication associated with the item.

Systems and methods for image processing

Systems, methods, and non-transitory computer-readable media taught herein process a subset of a three-dimensional array of voxels to form an image of a region of interest in an object. Images thus formed are clear, comprehensible, and contextual. The systems, methods, and non-transitory computer-readable media taught herein select the subset of voxels that represent the region of interest along a direction perpendicular to a view direction defined by the region of interest. The subset of voxels represents one or more portions of a plurality of image slices of the object.

Systems and methods for generating projection images

Methodologies, systems, apparatus, and non-transitory computer-readable media are described herein to facilitate acquisition of volumetric data and volumetric image reconstruction. An imaging system can be configured to transport an object at a speed relative to the scan path of an X-ray source such that insufficient measurement data is collected for classically complete geometrical coverage. Iterative image reconstruction techniques may be used to generate volumetric images based on measured volumetric data of at least a portion of the object.

Systems and methods for image reconstruction at high computed tomography pitch

A system and method for imaging objects with a sparse detector array that includes fewer detectors than conventional x-ray scanning systems. The sparse detector array is positioned to receive x-ray radiation from the at least one x-ray source after passing through an inspection area. The sparse detector array includes a plurality of rows of detector elements, wherein at least some of the plurality of rows are separated by gaps such that the at least some of the plurality of rows are non-contiguous. An iterative reconstruction process is used to determine a volumetric image of the object from the radiation measurements recorded by the detectors in the sparse detector array.

X-ray imager with sparse detector array

A volumetric image of a space is acquired from an imaging system. The space includes an object of interest and another object, and the volumetric image includes data representing the object of interest and the other object. A two-dimensional radiograph of the space is acquired from the imaging system. The two-dimensional radiograph of the space includes data representing the object of interest and the other object. The two-dimensional radiograph and the volumetric image are compared at the imaging system. A two-dimensional image is generated based on the comparison. The generated two-dimensional image includes the object of interest and excludes the other object.

Generating a representation of an object of interest

A system and method for forming volumetric images of an imaged object based on multiple radiation measurements of the object taken from different angles. A first volumetric image of the object may be calculated using a direct reconstruction method from a plurality of radiation measurements of the object. At least one iteration of an iterative reconstruction method may be performed to compute a second volumetric image of the object. The iterative reconstruction method may be initialized with the first volumetric image of the object.

Reconstruction method using direct and iterative techniques

A distribution of heavy particle stopping power is be determined. A distribution of effective atomic number of a three-dimensional space is accessed, and a distribution of an x-ray stopping power of the three-dimensional space is accessed. A conversion is applied to the distribution of the effective atomic number and the distribution of x-ray stopping power. A distribution of the heavy particle stopping power of the three-dimensional space is generated based on the conversion, the heavy particle stopping power being an indication of a depth of penetration for a heavy particle incident on the three-dimensional space.

Determination of heavy particle stopping power

X-ray radiation is generated at a target that emits x-ray radiation in response to being struck by accelerated electrons, the electrons being emitted by a cathode that emits electrons in response to being illuminated by electromagnetic radiation from a source, and the x-ray radiation is moved by orienting a surface that directs the electromagnetic radiation from the source toward the cathode.

Scanning X-ray radiation

An apparatus may comprise a frame supporting at least first and second skewed radiation sources and at least first and second radiation detectors. The first and second radiation detectors may be substantially non-contiguous such that a substantial gap exists between the first and second radiation detectors that is free of any radiation detectors. Each of the first and second radiation detectors may also configured and arranged to detect radiation emitted by each of the first and second skewed radiation sources.

Radiation scanning systems and methods

An imaging system that can form an image of an item under inspection using scattered radiation. A pencil beam of radiation is steered over the item under inspection and scattered radiation is detected. Regions of the item under inspection from which radiation is scattered are resolved in three dimensions using two-dimensional coordinates to which the pencil beam is steered. The third dimension is resolved using time of flight from the source. Because the inspection system can be located on one side of an item under inspection, an item may be imaged from a long distance and the imaging system may be mounted on a moving vehicle, making the imaging system well suited for use in many security inspection systems to detect explosives and other contraband items.

Imaging system with long-standoff capability

A system may comprise a cathode, a target, one or more switches, and a conductive element. The cathode may be configured and arranged to generate an electron beam, and the target may be configured and arranged to emit radiation when electrons in the electron beam impact the target after being accelerated by an energy source. The one or more switches may be configured and arranged to apply either a first voltage or a second voltage from a power supply between the cathode and the target. The conductive element may be disposed between the cathode and the target so as to inhibit the electron beam generated by the cathode from reaching the target when a signal is applied to the conductive element.

Selective generation of radiation at multiple energy levels

A method for operating an inspection system is disclosed in which an item under inspection may be moved between radiation sources and detectors illuminated by the sources. The radiation sources may be positioned such that radiation from at least some of the sources impinge on the radiation detectors, forming acute angles with respect to a plane having a normal direction coinciding with the first direction that are substantially in excess of three degrees. Data accumulated by the radiation detectors may be processed to form a three-dimensional tomographic data image of at least a portion of the item under inspection. The processing may be performed using an algebraic reconstruction technique using an inverse system matrix. The inverse matrix can be derived without first computing a transpose of the system matrix.

Growing community of inventors

Cambridge, MA, United States of America

Andrew Dean Foland