Abstract: Systems and methods of detecting irregular events include the extraction of values for measure in each of a plurality of notifications. The extracted values are stored in a measures database and a distribution is calculated for the values of each of the measures. The extracted values are compared to the calculated distributions to determine if an irregular event has occurred. An irregularity alert is produced if an irregular event has occurred.

Abstract: A radio therapy apparatus (100) includes a tissue of interest tracker (124) that receives a first image of tissue of interest and a second later acquired spectral image of the tissue of interest and tracks a change in a geometry and/or location of the tissue of interest based at least on the first and second images and generates a signal indicative of the change. The second image is generated based on a first spectral signal corresponding to an output of an energy-resolving radiation sensitive detector array for a first predetermined energy range and a second spectral signal corresponding to an output of the energy-resolving radiation sensitive detector array for a second predetermined energy range and visually enhances scanned structure corresponding to the first or second signals while visually suppressing scanned structure corresponding to the other of the first or second signals. An adaptive planner (126) updates a radiotherapy treatment plan based on the signal.

Abstract: An apparatus and method for performing automatic 3D image segmentation and reconstruction of organ structures, which is particularly well-suited for use on cortical surfaces is presented. A brain extraction process removes non-brain image elements, then classifies brain tissue as to type in preparation for a cerebrum segmentation process that determines which portions of the image information belong to specific physiological structures. Ventricle filling is performed on the image data based on information from a ventricle extraction process. A reconstruction process follows in which specific surfaces, such as white matter (WM) and grey matter (GM), are reconstructed.

Abstract: Systems and methods may include receiving first and second motion data about first and second objects, respectively. The systems and methods may include applying an asymmetric correlation rule (ACR) to the first and second motion data. The ACR may define a baseline state of motion for the first object and a correlation relationship between the first and second objects. The systems and methods may include determining whether the first object is in the baseline state and, in response to determining that the first object is not in the baseline state, determining whether a first motion vector of the first object is sufficiently correlated with a second motion vector of the second object. The systems and methods may include, in response to determining both that the first object is not in the baseline state and that the first and second motion vectors are not sufficiently correlated, generating an anomalous behavior notification.

Abstract: Digital watermark encoding—and associated registry transactions—are made transparent to consumers—performed as built-in features of common image processing operations, such as taking a picture, or printing a picture. In one arrangement, a user particularly defines network experiences that a hardcopy image is to invoke. The user may interact with buttons and other controls of a graphical user interface on the touchscreen of a printer to author specific experiences that should be triggered by a hardcopy image—such as launching a related video, playing a recorded audio clip, displaying other images in a story narrative to which the hardcopy image relates, etc. These choices can be made at the time of printing, or the printer can be used as an interface to establish or adjust such network experiences after printing. The printer then attends to interactions with network infrastructure components needed to give the hardcopy print the user-desired functionality.

Abstract: Method and apparatus for detecting obstacle based on monocular camera are provided. The method includes: obtaining a target frame image and its adjacent frame image shot by the monocular camera; deleting an unstable feature point from an initial feature point set of the adjacent frame image to obtain a preferred feature point set; dividing a target feature point set to obtain several target feature point subsets; judging whether the target feature point subset corresponds to obstacle based on a change of a distance between points within a ground projection point set of the target feature point subset from adjacent frame time instant to target frame time instant; and determining a union of all the target feature point subsets which are judged as corresponding to obstacles as an obstacle point set of the target frame image.

Abstract: The invention relates to a method for non-invasive reproducible determination of a corrected surface on a 3D bone surface model constructed from 3D medical image of a bone having a deformation consisting in a bump overgrowth at the head-neck junction; wherein said corrected surface comprises: i) a 3D spherical corrected surface patch on the head portion of said 3D bone surface model, and ii) a 3D smooth transition corrected surface patch on the neck portion of said 3D bone surface model, contiguous to said 3D spherical corrected surface patch; Said corrected surface patches are defined by a set of parameters comprising: iii) at least one first parameter (a*) representing a spherical extent value of said 3D spherical corrected surface patch, iv) and a set of at least one second parameter, said set determining the 3D correction boundary of said corrected surface patches, such that said corrected surface patches are continuous with said 3D bone surface model along said boundary.

Abstract: An eye-gaze-detection apparatus includes an image acquisition unit that acquires a face image of a user from an imaging apparatus, the face image being captured by the imaging apparatus; a feature-quantity extraction unit that extracts a feature quantity of the face image; an eye-gaze-calculation-determination unit that determines whether or not an eye-gaze calculation process is performed by referring to a rule database, based on the feature quantity extracted by the feature quantity extraction unit, the rule database storing a rule set associating a condition including the feature quantity of the face image with information indicating whether or not the eye gaze calculation process is performed; and an eye-gaze-calculation unit that performs the eye-gaze-calculation process for the user, based on the feature quantity of the face image acquired by the image acquisition unit, when the eye-gaze-calculation-determination unit determines that the eye-gaze-calculation process is performed.

Abstract: A radiation detection system includes a detector unit and at least one processor. The detector unit is configured to generate signals responsive to radiation events. The at least one processor receives the signals, and is configured to obtain a first count for at least one of the signals corresponding to a first energy window, the first energy window corresponding to values higher than a nominal peak value; obtain a second count for the at least one of the signals corresponding to a second energy window, the second energy window corresponding to values lower than the nominal peak value; obtain at least one auxiliary count for the at least one of the signals corresponding to at least one auxiliary energy window; and adjust a gain applied to the signals based on the first count, the second count, and the at least one auxiliary count.

Abstract: A non-transitory computer readable medium that stores instructions that once executed by a computer cause the computer to execute the stages of: calculating first curvature attributes of first areas of a first representation of a first three dimensional object; calculating second curvature attributes of second areas of a second representation of a second three dimensional object; selecting first points of interest of the first representation in response to the first curvature attributes; selecting second points of interest of the second representation in response to the second curvature attributes; classifying the first points of interest to first classes; classifying the second points of interest to second classes; calculating multiple sets of first vectors that are indicative of spatial relationships between first points of interest, wherein different sets out of the multiple sets of the first vectors are associated with different first classes; calculating multiple sets of second vectors that are indicativ

Abstract: Optimized blending mode for mineralogy images. A luminosity value is determined for a pixel in a base layer or top layer mineralogy image. An image weighting value is determined from the luminosity value and an optional mixing parameter. A multiply value is determined by multiplying the base and top layer pixel values. An overlay value is determined from twice the multiply value if the value of one of the base layer or top layer pixel values is over a threshold, otherwise it is determined by inverting twice the product of the inverted top layer pixel value with the inverted base layer pixel value. A blended image pixel value is determined by adding the multiply value weighted with the image weighting value and the overlay value weighted with the inverted image weighting value.

Abstract: A method for recognizing an object (120) in an image (100), in which the recognition of the object (120) comprises a first scaling stage of a scaling region of the image (100), and at least a further scaling stage of the scaling region of the image (100); and in which the image (100) is subdivided into at least one image segment (110); a first decision being taken for the at least one image segment (110) on the first scaling stage of the scaling region as to whether the at least one image segment (110) is considered on the at least one further scaling stage of the scaling region for the recognition of the object (120).

Abstract: Methods, systems and computer-readable storage media relate to image-guided treatment planning and treatment assessment. The methods, systems, and the computer-readable storage medias according to embodiments can analyze treatment response and can determine an accurate, outcome-based response assessment of treatment (e.g., radiation treatment). The methods may include a method for determining a treatment response. The method may include registering at least a first image data and a second image data of a subject, the first image data corresponding to a first time point, the second image data corresponding to a second time point, the first time point and the second time point being different with respect to a treatment session and/or treatment stage. The method may include processing the registered image to determine a treatment response. The registering may be based on deformable registration.

Abstract: What is disclosed is a system and method for detecting cancerous tissue in breast tissue using a thermal image. In one embodiment, the present tumor detection method involves selecting a region of interest in the thermal image to be processed for breast cancer screening. Thereafter, a percentage of pixels p1 in the selected region having a temperature Tpixel1, where T1?Tpixel1?T2, is determined. A percentage of pixels p2 in the selected region having a temperature Tpixel2, where T3?Tpixel2, is determined. A ratio p 3 = P edge / P block is also determined, where Pedge is a number of pixels around a border of a suspected tumor within the selected region, and Pblock is a number of pixels in a perimeter of the selected region. A decision fusion rule R, as more fully disclosed herein, is utilized to determine, based on these determination whether tissue within that region is cancerous, or non-cancerous, or is suspicious of being cancerous.

Abstract: A trajectory analyzing apparatus includes a matching unit that calculates the correlation between a forward trajectory obtained by tracking a moving object over pictures along the forward direction of the time axis and a backward trajectory obtained by tracking a moving object over the pictures along the backward direction of the time axis and a result output unit that outputs trajectory information indicating at least one of the forward trajectory, the backward trajectory, and an integrated trajectory obtained by integrating the forward trajectory and backward trajectory and indicating the degree of reliability of the at least one trajectory based on the calculated correlation.

Abstract: An industrial safety system is provided that integrates optical safety monitoring with machine control. The safety system includes an imaging sensor device supporting pixel array processing functions that allow time-of-flight (TOF) analysis to be performed on selected portions of the pixel array, while two-dimensional imaging analysis is performed on the remaining portions of the array, reducing processing load and response time relative to performing TOF analysis for all pixels of the array. The portion of the pixel array designated for TOF analysis can be pre-defined through configuration of the imaging sensor device, or can be dynamically selected based on object detection and classification by the two-dimensional imaging analysis. The imaging sensor device can also implement a number of safety and redundancy functions to achieve a high degree of safety integrity.

Abstract: Accelerating object detection techniques are described. In one or more implementations, adaptive sampling techniques are used to extract features from an image. Coarse features are extracted from the image and used to generate an object probability map. Then, dense features are extracted from high-probability object regions of the image identified in the object probability map to enable detection of an object in the image. In one or more implementations, cascade object detection techniques are used to detect an object in an image. In a first stage, exemplars in a first subset of exemplars are applied to features extracted from the multiple regions of the image to detect object candidate regions. Then, in one or more validation stages, the object candidate regions are validated by applying exemplars from the first subset of exemplars and one or more additional subsets of exemplars.

Abstract: A system for capturing image data for gestures from a passenger or a driver in a vehicle with a dynamic illumination level comprises a low-lux sensor equipped to capture image data in an environment with an illumination level below an illumination threshold, a high-lux sensor equipped to capture image data in the environment with the illumination level above the illumination threshold, and an object recognition module for activating the sensors. The object recognition module determines the illumination level of the environment and activates the low-lux sensor if the illumination level is below the illumination threshold. If the illumination level is above the threshold, the object recognition module activates the high-lux sensor.

Abstract: The embodiments relate to a method and device for determining plaque deposits in coronary arteries. According to the method, a coronary angiography radiography image of a subject is obtained using an imaging modality. The obtained radiography image is calibrated for further analysis of the radiography image. Image processing techniques such as thresholding and histogram equalization are applied on the radiography image to extract vessel tree structure for analysis. Further, an inner lumen width and an outer vessel width are computed based on the processed radiography image. Further, a level of plaque deposition is determined based on the inner lumen and outer vessel dimensions. Further, the result based on the analysis is displayed to the user. The result includes the level of plaque deposits within the lumen on the vascular structure and possible risks posed by the plaque deposits to a subject.

Abstract: In an image processing device (1), the motion detection unit (43) extracts an outline indicating a body from an image of each frame in moving image data of a player and sets a motion reference axis(line) to each part of the body. Then, the motion comparison unit (44) compares a moving image of the player and a moving image of a professional golfer based on a motion of a main motion reference axis(line) and generates moving image data for comparison to which comparison result data is added. Based on this moving image data for comparison, the comparison result display control unit (45) distinguishably displays a difference between the moving image of the player and the moving image of the professional golfer.