Abstract: A network of apparatuses that characterizes items is presented. A self-updating apparatus includes a processing unit that has a memory storing parameters that are useful for characterizing different items, and a processing module configured to automatically select sources from which to receive data, modify the parameters based on the data that is received, and to select recipients of modified parameters. Selection of sources and recipients is based on comparison of parameters between the processing module and the sources, and between the processing module and the recipients, respectively. The processing unit may include an artificial intelligence program (e.g., a neural network such as a machine learning program). When used in a network, the processing units may “train” other processing units in the network such that the characterization accuracy and range of each processing unit improves over time.

Abstract: A method of decomposing a set of scans of different views of overlapping objects into constituent objects is presented. The method involves an initialization process whereby keypoints in two views are determined and matched, disparity between keypoint pairs are computed, and the keypoints are grouped into clusters based on their disparities. Following the initialization process is an iterative optimization process whereby a cost function is calculated and minimized assuming a fixed composition matrix and re-solved assuming a fixed attenuation coefficient. Then, the composition matrix and the attenuation coefficient are updated simultaneously, and the solving, the re-solving, and the updating steps are repeated until there is no significant improvement in the result.

Abstract: A method and an apparatus for efficient resource sharing are presented. The apparatus includes a central unit having a plurality of surfaces on the outside, the central unit holding a resource. Compartments are coupled to the central unit, each of the compartments being placed adjacent to one of the surfaces of the central unit. Each compartment has a platform to support an object, and has a sensor that reads an output signal indicating that the object in the compartment has finished accessing the resource from the central unit. A computation unit receives and processes the output signal from each of the compartments. The sensor in the apparatus may be located in the central unit instead of in the compartments.

Abstract: A method and system for efficiently screening for threatening items are presented. The system includes a test unit configured to subject the object to a combination of two or more different types of tests, sensors configured to receive test outcome from the object and generate corresponding output signals, and a computation unit receiving and processing the output signals to generate parameter values. The computation unit combines the parameter values from the different types of tests to determine a set of risk factors that indicate a likelihood that the threatening item is present in the object, wherein the parameter values include visualization data obtained from different measurement angles.

Abstract: A method and a system for efficiently screening for dangerous threatening items in or on an animate subject (e.g., a person) are presented. The system includes a portal that accommodates an animate subject and a test unit that includes equipment for subjecting the animate subject to a combination of two or more tests. There are sensors located in the portal, wherein each of the sensors reads data resulting from testing the animate subject and generates an output signal. A computation unit receives the output signal from each of the sensors and processes the output signals in parallel to determine a risk factor based on parameters resulting from the two or more tests. The test unit may be coupled to a portal and an object unit, wherein the object unit is for screening inanimate subjects (e.g., bags, coats). The parallel acquisition and processing of the output signals enhances accuracy.

Abstract: A method and system for efficiently screening for dangerous threatening items are presented. The system includes an object unit designed to hold the object and a test unit including equipment for subjecting the object to a combination of two or more tests. There are sensors located in the object unit, wherein each of the sensors reads data resulting from testing the object and generates an output signal. A computation unit receives the output signal from each of the sensors and processes the output signals in parallel to determine a risk factor based on parameters resulting from the two or more tests. The parallel acquisition and processing of the output signals enhances accuracy. By testing a “batch” of objects at once, the system improves throughput.