Abstract: System and methods for object segmentation include providing a pre-trained neural network model to segment object instances based on a first set of images and a first loss function. The neural network, for a pixel, can generate a gradient flow that points towards a center of an object structure and provides a probability score indicating a probability of the pixel belonging to the object structure. An adapted neural network model can be generated from the pre-trained neural network model to account for domain shifted new input images by training the pre-trained neural network model on a second set of images and a loss function that comprises a contrastive flow loss component and a contrastive mask loss component.

Abstract: A system and method to manage delivery of healthcare via a plurality of resources to a patient is provided. The system and method track and output a signal representative of a location of at least one of a series of resources relative to a control volume associated with the patient, acquire at least one signal representative of detecting ingress or egress of at least one of the plurality of resources relative to the control volume; and output a first signal representative of one of a series of milestones as defined in a predetermined protocol in response to detecting ingress or egress of at least one of the resources relative to the control volume.

Abstract: A system and method to manage delivery of healthcare via a plurality of resources to a patient is provided. The system and method track and output a signal representative of a location of at least one of a series of resources relative to a control volume associated with the patient, acquire at least one signal representative of detecting ingress or egress of at least one of the plurality of resources relative to the control volume; and output a first signal representative of one of a series of milestones as defined in a predetermined protocol in response to detecting ingress or egress of at least one of the resources relative to the control volume.

Abstract: A device and method for processing an image to create appearance and shape labeled images of a person or object captured within the image. The appearance and shape labeled images are unique properties of the person or object and can be used to re-identify the person or object in subsequent images. The appearance labeled image is an aggregate of pre-stored appearance labels that are assigned to image segments of the image based on calculated appearance attributes of each image segment. The shape labeled image is an aggregate of pre-stored shape labels that are assigned to image segments of the image based on calculated shape attributes of each image segment. An identifying descriptor of the person or object can be computed based on both the appearance labeled image and the shape labeled image. The descriptor can be compared with other descriptors of later captured images to re-identify a person or object.

Abstract: A device and method for processing an image to create appearance and shape labeled images of a person or object captured within the image. The appearance and shape labeled images are unique properties of the person or object and can be used to re-identify the person or object in subsequent images. The appearance labeled image is an aggregate of pre-stored appearance labels that are assigned to image segments of the image based on calculated appearance attributes of each image segment. The shape labeled image is an aggregate of pre-stored shape labels that are assigned to image segments of the image based on calculated shape attributes of each image segment. An identifying descriptor of the person or object can be computed based on both the appearance labeled image and the shape labeled image. The descriptor can be compared with other descriptors of later captured images to re-identify a person or object.

Abstract: Aspects of the disclosure provide a method for crowd segmentation that can globally optimize crowd segmentation of an input image based on local information of the input image. The method can include receiving an input image of a site, initializing a plurality of hypothesis based on the input image, dividing the input image into a plurality of patches, calculating an affinity measure of one or more patches to a hypothesis based on a partial response of the patches to a whole body classifier of the hypothesis that includes a combination of weak classifiers, and optimizing assignments of the plurality of patches to the plurality of hypothesis based on the affinity measures of the plurality of patches to the plurality of hypothesis.

Abstract: A system for detecting and tracking targets captured in images, such as people and object targets that are captured in video images from a surveillance network. Targets can be detected by an efficient, geometry-driven approach that determines likely target configuration of the foreground imagery based on estimated geometric information of possible targets. The detected targets can be tracked using a centralized tracking system.

Abstract: A device and method for detecting targets of interest in an image, such as people or objects of a certain type. Targets are detected based on an optimized strong classifier descriptor that can be based on a combination of weak classifier descriptors. The weak classifier descriptors can include a user-defined weak classifier descriptor that is defined by a user to represent a shape or appearance attribute that is characteristic of parts of the target of interest. The strong classifier descriptor can be optimized by selecting a subset of weak classifier descriptors that exhibit improved performance in detecting targets in training images.

Abstract: A device and method for processing an image to create appearance and shape labeled images of a person or object captured within the image. The appearance and shape labeled images are unique properties of the person or object and can be used to re-identify the person or object in subsequent images. The appearance labeled image is an aggregate of pre-stored appearance labels that are assigned to image segments of the image based on calculated appearance attributes of each image segment. The shape labeled image is an aggregate of pre-stored shape labels that are assigned to image segments of the image based on calculated shape attributes of each image segment. An identifying descriptor of the person or object can be computed based on both the appearance labeled image and the shape labeled image. The descriptor can be compared with other descriptors of later captured images to re-identify a person or object.

Abstract: A device and method for processing an image to create appearance and shape labeled images of a person or object captured within the image. The appearance and shape labeled images are unique properties of the person or object and can be used to re-identify the person or object in subsequent images. The appearance labeled image is an aggregate of pre-stored appearance labels that are assigned to image segments of the image based on calculated appearance attributes of each image segment. The shape labeled image is an aggregate of pre-stored shape labels that are assigned to image segments of the image based on calculated shape attributes of each image segment. An identifying descriptor of the person or object can be computed based on both the appearance labeled image and the shape labeled image. The descriptor can be compared with other descriptors of later captured images to re-identify a person or object.

Abstract: A device and method for efficient computation of statistical information, such as a mean, co-variance, or histogram of the image pixels, over discrete image regions. The computation employs integral computations to determine the statistical information over image regions of arbitrary shape, including irregular polygonal shaped regions. The integral computations are simplified by categorizing corner points of boundaries of image regions. The computation can be applied to calculate descriptors or signatures of persons or objects within an image. The computation also has a low computational cost enabling fast calculation of image statistics.

Abstract: A device and method for processing an image to create appearance and shape labeled images of a person or object captured within the image. The appearance and shape labeled images are unique properties of the person or object and can be used to re-identify the person or object in subsequent images. The appearance labeled image is an aggregate of pre-stored appearance labels that are assigned to image segments of the image based on calculated appearance attributes of each image segment. The shape labeled image is an aggregate of pre-stored shape labels that are assigned to image segments of the image based on calculated shape attributes of each image segment. An identifying descriptor of the person or object can be computed based on both the appearance labeled image and the shape labeled image. The descriptor can be compared with other descriptors of later captured images to re-identify a person or object.

Abstract: A system, method and program product for camera-based object analyses including object recognition, object detection, and/or object categorization. An exemplary embodiment of the computerized method for analyzing objects in images obtained from a camera system includes receiving image(s) having pixels from the camera system; calculating a pool of features for each pixel; then deriving either a pool of radial moment of features from the pool of features and a geometric center of the image(s) or a pool of central moments of features from the pool of features; then calculating a normalized descriptor, based on an area of the image(s) and either of the derived pool of moments of features; and then based on the normalized descriptor, a computer then either recognizes, detects, and/or categorizes an object(s) in the image(s).

Abstract: A device and method for detecting targets of interest in an image, such as people or objects of a certain type. Targets are detected based on an optimized strong classifier descriptor that can be based on a combination of weak classifier descriptors. The weak classifier descriptors can include a user-defined weak classifier descriptor that is defined by a user to represent a shape or appearance attribute that is characteristic of parts of the target of interest. The strong classifier descriptor can be optimized by selecting a subset of weak classifier descriptors that exhibit improved performance in detecting targets in training images.

Abstract: A system, method and program product for camera-based object analyses including object recognition, object detection, and/or object categorization. An exemplary embodiment of the computerized method for analyzing objects in images obtained from a camera system includes receiving image(s) having pixels from the camera system; calculating a pool of features for each pixel; then deriving either a pool of radial moment of features from the pool of features and a geometric center of the image(s) or a pool of central moments of features from the pool of features; then calculating a normalized descriptor, based on an area of the image(s) and either of the derived pool of moments of features; and then based on the normalized descriptor, a computer then either recognizes, detects, and/or categorizes an object(s) in the image(s).

Abstract: Embodiments of the invention include a system and a method for determining whether a person is carrying concealed contraband, such as an improvised explosives device or other weapon. The system includes a people tracking video subsystem, a people tracking decisioning subsystem, a concealed contraband detection aiming subsystem, and a concealed contraband detection decisioning subsystem.

Abstract: A method for re-identifying an image is provided. The method comprises obtaining a plurality of images and generating a correspondence map between the plurality of images. The method further comprises defining a plurality of region signatures for one or more regions comprising the plurality of images and comparing the plurality of images based on the correspondence map and the plurality of region signatures to perform image re-identification.

Abstract: Aspects of the disclosure provide a method for crowd segmentation that can globally optimize crowd segmentation of an input image based on local information of the input image. The method can include receiving an input image of a site, initializing a plurality of hypothesis based on the input image, dividing the input image into a plurality of patches, calculating an affinity measure of one or more patches to a hypothesis based on a partial response of the patches to a whole body classifier of the hypothesis that includes a combination of weak classifiers, and optimizing assignments of the plurality of patches to the plurality of hypothesis based on the affinity measures of the plurality of patches to the plurality of hypothesis.

Abstract: A system for detecting and tracking targets captured in images, such as people and object targets that are captured in video images from a surveillance network. Targets can be detected by an efficient, geometry-driven approach that determines likely target configuration of the foreground imagery based on estimated geometric information of possible targets. The detected targets can be tracked using a centralized tracking system.

Abstract: A gaze estimation method and system, the method including capturing a video sequence of images with an image capturing system, designating at least one landmark in a head portion of the captured video sequence, fitting a virtual model of the head portion to the actual head portion in the captured video sequence, and determining the gaze estimation.