Abstract: Implementations of the disclosure provide a method comprising generating, by a processing device, a group repository in view of a plurality of image repositories comprising image manifests. An image manifest comprising an application image and an image platform specifier specifying platform resources for executing the application image from the image repositories is identified. The image manifest is clustered into one or more group members of the group repository in view of the image platform specifier. Each group member references at least a key and a value associated with the key. The key references the image manifest and the value references a manifest list describing a plurality of platforms to execute the application image associated with the image manifest. Thereupon, a data object to redirect a client device to a location comprising the one or more group members of the group repository is published.

Abstract: An image processing apparatus (IP) comprising an input port (IN) for receiving projection data through respective 3D locations in an imaging region, said projection date collected in a scan operation by an imaging apparatus (IM). An image segment generator (IGS) of said apparatus (IP) is configured to generate, based on said projection data, a first image segment for said 3D locations. A visualizer (VIZ) configured to effect displaying said first image segment on a display device before or whilst the image apparatus collects projection data for a different 3D location.

Abstract: Fall detection and reporting technology, in which output from at least one sensor configured to sense, in a room of a building, activity associated with a patient falling is monitored and a determination is made to capture one or more images of the room based on the monitoring. An image of the room is captured with a camera positioned to include the patient within a field of view of the camera and the captured image of the room is analyzed to detect a state of the patient at a time of capturing the image. A potential fall event for the patient is determined based on the detected state of the patient and a message indicating the potential fall event for the patient is sent based on the determination of the potential fall event for the patient. Techniques are also described for fall detection and reporting using an on-body sensing device.

Abstract: In one embodiment, a method executed by a computing system, comprising: receiving pixel samples from three-dimensional (3D) data corresponding to one or more images comprising one or more animals; fitting curves for the received pixel samples; deriving parameters from the curves; determining measurements based on variations in the parameters; and estimating a weight of the one or more animals by applying one or more regression algorithms to the measurements.

Abstract: A method and system is provided for tracking one or more objects in a video which is computationally light so that it can run on a variety of computing devices, including mobile devices which typically have a limited computational power. The tracked objects can be selected, and can then be automatically tracked afterwards. The tracked objects can be deselected or have their bounding boxes moved or resized at any time. The tracking can be performed using online learning with a binary classifier to separate the target from the background.

Abstract: In one representative embodiment, an intraoral scanning device includes a scan head sized and shaped to be placed inside a patient's mouth. The scan head can include at least one ultrasonic transducer for generating ultrasonic images and at least one light-based sensor for generating optical images.

Abstract: A motion tracking system monitors the motions performed by a user based on motion data received from one or more sensors. The motion tracking system may include a motion tracking device with one or more sensors, a smart device with one or more sensors and/or a server. As the user interacts with the motion tracking system or smart device the motion data generated by one or more sensors is processed by a software application. The software application generates interpreted data based on the motion data and contextual data such as the equipment being used by the user. Feedback is then provided to the user during and/or after the user has performed a motion or a set of motions. The feedback provided to the user may be visual, audio or tactile. The application may be used to monitor a routine in a sporting, fitness, industrial or medical environment, for example.

Abstract: According to a first aspect, the invention relates to a method to support clinical decision by characterizing images acquired in sequence through a video medical device. The method comprises defining at least one image quantitative criterion, storing sequential images in a buffer, for each image (10) in the buffer, automatically determining, using a first algorithm, at least one output based on said image quantitative criterion and attaching said output to a timeline (11).

Abstract: A system and method of assisting a treatment procedure is provided, the method comprising the steps of determining a 3-D intervention vector in relation to an inner body structure of a body of interest based on a 3-D x-ray image, determining a 3-D position of an entry point on an outer surface of the body of interest based on the intervention vector, comparing the position and/or orientation of the inner body structure in the 3-D x-ray image with the position and/or orientation of the inner body structure in an additional 2-D x-ray image being generated transverse to the intervention vector, correcting the 3-D position of the entry point on the outer surface of the body of interest based on a deviation detected in the comparing step.

Abstract: A piece of medical information, e.g., a medical image of tissue, may be received for processing and analysis on a computing device or system. A region of the medical image may be analyzed to determine a presence of one or more contours in the region. One or more properties of the one or more contours may be extracted, where the one or more properties are inputted into a first algorithm to determine an indication of cancer for the region. The indication of cancer may be inputted into a second algorithm to generate a cancer score for the region.

Abstract: A computer-implemented method includes receiving a reference image of an outdoor area, identifying that a portion of the outdoor area shown in the reference image corresponds to living vegetation, determining, from multiple images of the outdoor area, a reference color that corresponds to a dry condition in the portion of the outdoor area, receiving a sample image of the portion of the outdoor area, determining that a sample color of the portion of the outdoor area shown in the sample image corresponds to the reference color, and based on a determination that the sample color of the portion of the outdoor area shown in the sample image corresponds to the reference color, triggering a watering device to provide water to the portion of the outdoor area.

Abstract: An image display apparatus 120 for imaging and displaying a test substance contained in a sample 111 includes an imaging unit 200 for imaging a test substance, an image processing unit 121 for generating an image 61 for display including an additional image 11c in which the pixel value of each pixel is set in uneven distribution added to at least part of the captured image 11 obtained by the imaging unit 200 and a region 21 of the test substance, and a display unit 123 for displaying the image 61 generated by the image processing unit 121.

Abstract: A representative image generation device includes circuitry that identifies a selected image from a plurality of recorded images of an object. The plurality of recorded images are captured as the object traverses a predetermined area. The device prepares the selected image for display on a display device, wherein the selected image provides a visual recognizability of the object greater than a predetermined threshold.

Abstract: A computer-implemented method, system, and computer program product are provided for facial recognition. The method includes receiving, by a processor device, a plurality of images. The method also includes extracting, by the processor device with a feature extractor utilizing a convolutional neural network (CNN) with an enlarged intra-class variance of long-tail classes, feature vectors for each of the plurality of images. The method additionally includes generating, by the processor device with a feature generator, discriminative feature vectors for each of the feature vectors. The method further includes classifying, by the processor device utilizing a fully connected classifier, an identity from the discriminative feature vector. The method also includes control an operation of a processor-based machine to react in accordance with the identity.

Abstract: In a diagnostic imaging device, such as an MRI device, correction processing improves an image to be a high-quality image and an imaging time is shortened. In the diagnostic imaging device, a noise reduction unit 201 reduces a noise in observation data acquired with an observation unit 100 and converted into an image, and the image correction unit 202 corrects the noise reduced data by correction processing that uses visual characteristics of human. The image correction unit 202 separates the noise reduced data into a broad luminance component and a local variation component, and generates a correction level map using the broad luminance component. Correcting the noise reduced data using this correction level map and the local variation component acquires a high-quality image that is competent in the clinical field.

Abstract: A method for recognizing an action captured on an event-based camera includes the steps of receiving asynchronously transmitted pixel locations which have changed intensity via an address-event bus; stacking a plurality of frames of received pixel location to form a surrogate RGB image where the channels represent individual frames; inputting the surrogate RGB image into a first convolutional neural network; and extracting feature f1 from a last fully connected layer of the convolutional neural network to obtain an action classification of the action, thereby recognizing the action.

Abstract: Disclosed is a system which uses one or more camera units with embedded processors to measure the relative translation and/or rotation between different members on an aerial device. Image data from each unit is processed and transmitted processing to the position control system of the aerial device, and used to determine the position of an aerial element of the device.

Abstract: A radiography support device that supports imaging of an object with a radiation detection panel in which a plurality of pixels are two-dimensionally arranged and which detects radiation emitted from a radiation source, includes: a first reading control unit that reads first pixel signals from at least some of the plurality of pixels in a state in which the radiation is not emitted from the radiation source and a state in which the object is placed on the radiation detection panel; a first arithmetic unit that calculates a position of the object with respect to the radiation detection panel based on the first pixel signals; and a notification processing unit that performs a notification process in a case in which the position of the object is out of a predetermined range.

Abstract: A tomographic imaging apparatus includes an X-ray detector comprising a plurality of dual mode pixels and configured to detect radiation that has passed through an object, and at least one processor configured to obtain scan data from the X-ray detector, and control each pixel of the plurality of dual mode pixels to operate in one of a first mode and a second mode, wherein each pixel of the plurality of dual mode pixels includes a sensor configured to generate a scan signal by converting incident radiation into an electric signal, a first signal path circuit configured to transmit the scan signal in the first mode, a second signal path circuit configured to transmit the scan signal in the second mode, and a photon counter configured to count photons from the scan signal transmitted through one of the first and second signal path circuits.

Abstract: A method of blink detection in a laser eye surgical system includes providing a topography measurement structure having a geometric marker. The method includes bringing the topography measurement structure into a position proximal to an eye such that light traveling from the geometric marker is capable of reflecting off a refractive structure of the eye of the patient, and also detecting the light reflected from the structure of the eye for a predetermined time period while the topography measurement structure is at the proximal position. The method further includes converting the light reflected from the surface of the eye into image data and analyzing the image data to determine whether light reflected from the geometric marker is present is in the reflected light, wherein if the geometric marker is determined not to be present, the patient is identified as having blinked during the predetermined time.