Abstract: A device, system, and method of assistance for visually impaired users. The system comprises a plurality of video cameras, often head mounted, computer processors and associated support devices and algorithms configured for computer vision, and a user worn haptic band comprising a plurality (two or more) of distantly spaced haptic transducers. This haptic band is worn such that user's hands are free for other tasks. The system uses its video camera, depth processing algorithms, and object recognition algorithms (hardware and/or software based) to identify a limited number of navigationally important objects. The spatial locations of each object deemed important is output to the user by varying output to the haptic transducers accordingly. The system is configured to identify and report objects as generic objects, identified objects, and potential obstacle objects. The system can also optionally provide audio information pertaining to these objects as well.

Abstract: In an object recognition device, a reliability setting unit sets object presence reliability indicating the reliability of whether or not an object is present with respect to the surrounding area of a host vehicle. Then, a grouping unit groups the reflection points based on the object presence reliability in the area between the reflection points. For this reason, for example, even though two objects are adjacent to each other, in a case where the object presence reliability in the area between the reflection points of one object and the reflection points of the other object is low, the reflection points of the two objects can be separately grouped without being grouped into a single group. As a result, since it is possible to avoid mistakenly recognizing a plurality of objects in a single object, recognition accuracy of the object can be improved.

Abstract: The present disclosure provides methods, systems, and computer-readable storage media that can be used to image an unstained sample. The disclosed methods can include obtaining a spectroscopic image (e.g., infrared (IR) imaging data) of the sample, analyzing the resulting spectroscopic image to reduce the dimensionality of the spectroscopic image, comparing the reduced spectroscopic image compared to a control (e.g., by using an appropriately trained algorithm) and generating an output computed stain image from the reduced IR spectra, thereby imaging the sample without the use of stains or dyes.

Abstract: A voxel-based technique is provided for performing quantitative imaging and analysis of tissue image data. Serial image data is collected for tissue of interest at different states of the issue. The collected image data may be deformably registered, after which the registered image data is analyzed on a voxel-by-voxel basis, thereby retaining spatial information for the analysis. Various thresholds are applied to the registered tissue data to identify a tissue condition or state, such as classifying chronic obstructive pulmonary disease by disease phenotype in lung tissue, for example.

Abstract: Concepts herein relate to processing urine sediment images. An example method comprises: approximating the color of a pixel in a block to be processed to one of the kc colors in a code book, wherein the code book is a set of the kc colors generated in a set of urine sample blocks; obtaining a distribution histogram of the number of pixels the color approximation results of which fall on each color of the kc colors; using an occurrence frequency correction factor to correct the number of pixels the color approximation results; standardizing the corrected number of pixels the color approximation results; and processing the block to be processed.

Abstract: In a method and apparatus for generating an enhanced image for display from medical imaging data of a subject, a feature of interest in the imaging data elongated in at least one dimension is determined. A location of a line through the imaging data along the feature of interest is obtained, and a projection image along the line is generated from the imaging data.

Abstract: A method includes: collecting projection data and recording electrocardiogram data when computed tomographic scanning is performed on a patient, selecting, from the projection data and based on the electrocardiogram data, first projection data related to each cardiac pixel in a same phase, and reconstructing, based on the first projection data, an image of the related cardiac pixel, to obtain a cardiac image; determining, based on the electrocardiogram data, a reconstruction phase of each reconstruction pixel in a first reconstruction region, where the first reconstruction region is an image region selected along the patient's head-to-foot direction from the cardiac image; and selecting, based on the reconstruction phase of each reconstruction pixel and from the projection data, second projection data related to the reconstruction pixel in the reconstruction phase, and reconstructing, based on the second projection data, an image of the reconstruction pixel.

Abstract: A method for video object tracking using stereoscopic images with depth maps. The method comprises calculating a first axis histogram for each depth map and applying: a first object detection method to track objects based on at least one of: the contents of the images and the depth maps; and a second object detection method to track objects based on the contents of the histograms of the depth maps. The locations of tracked objects are determined based on comparison of the results of the first object detection method and the second object detection method.

Abstract: A system, apparatus, method, computer program product, and computer readable storage medium provide the ability to reconstruct a surface mesh. Photo image data is obtained from a set of overlapping photographic images. Scan data is obtained from a scanner. A point cloud is generated from a combination of the photo image data and the scan data. An initial rough mesh is estimated from the point cloud data. The initial rough mesh is iteratively refined into a refined mesh.

Abstract: The present invention relates to a method for identifying calcification portions in a dual energy CT contrast agent enhanced scanning image, the method including: filtering the pixels in the dual energy CT contrast agent enhanced scanning image to acquire pixels to be grouped; grouping the pixels to be grouped in a plurality of pixel groups according to the positions of the pixels to be grouped in the dual energy CT contrast agent enhanced scanning image; material-decomposing the pixels in each pixel group; and determining the pixels corresponding to the calcification portions in the plurality of pixel groups according to the result of the material-decomposing. Therefore, the calcification portions can be identified accurately.

Abstract: In an imaging device in a display system, a control unit recognizes human traits from an image of a human being that is an object to be displayed, which is obtained by photography. The image of the human being is correlated to information indicating the recognized traits and then transmitted to a digital signage device by a communication unit. In the digital signage device, the display area on an image display unit is determined in accordance with this information indicating the human traits that have been correlated to the image of the human being that is the object to be displayed, and the image of the human being that is the object to be displayed is modified so to be displayed in the determined display area, after which the modified image is displayed on the determined display area of the image display unit.

Abstract: A processor implemented system and method for identification of an activity performed by a subject based on sensor data analysis is described herein. In an implementation, the method includes capturing movements of the subject in real-time using a sensing device. At least one action associated with the subject is ascertained from a predefined set of actions. From the predefined set of actions, a plurality of actions can collectively form at least one activity. The ascertaining is based on captured movements of the subject and at least one predefined action rule. The at least one action rule is based on context-free grammar (CFG) and is indicative of a sequence of actions for occurrence of the at least one activity. Further, a current activity performed by the subject is dynamically determined, based on the at least one action and an immediately preceding activity, using a non-deterministic push-down automata (NPDA) state machine.

Abstract: A projection image of a three dimensional image is generated and displayed and a three dimensional target point corresponding to a designated two-dimensional target point is set to the three dimensional image. A reference cross-section is set to the three dimensional image by using the three dimensional target point. A cross-sectional two-dimensional image of the reference cross-section in which an object close to a point of view that faces the reference cross-section is not displayed is generated. An instruction to change the position of the point of view, using the three dimensional target point based on the cross-sectional two-dimensional image as a reference point, in order to align an observation direction of a structure to which the three dimensional target point is set with a target three dimensional direction is received. A new reference cross-section is set. A new cross-sectional two-dimensional image of the new reference cross-section is generated.

Abstract: A method and an apparatus for detecting change in retinal oxygen saturation over time are provided. The method includes the steps of capturing a first group of images of two or more wavelengths, calculating oxygen saturation of a vessel in the first group of images, storing the first group of images on a data storage device, capturing a second group of images of two or more wavelengths, calculating the oxygen saturation of a vessels in the second group of images, storing the second group of images on a data storage device, spatially registering the pair of the group of images, captured at different time and calculate the change in oxygen saturation. The method also includes means to validate whether an observed change in oxygen saturation is a real physiological change or artificial.

Abstract: A zonal underground structure detection method based on sun shadow compensation is provided, which belongs to the crossing field of remote sensing technology, physical geography and pattern recognition, and is used to carry out compensation processing after a shadow is detected, to improve the identification rate of zonal underground structure detection and reduce the false alarm rate. The present invention comprises steps of acquiring DEM terrain data of a designated area, acquiring an image shadow position by using DEM, a solar altitude angle and a solar azimuth angle, processing and compensating a shadow area, and detecting a zonal underground structure after the shadow area is corrected.

Abstract: An apparatus reconstructs an image using high energy-based data regarding a scene provides access to first image-capture data regarding the scene that is formed using a first image-capture modality and to second image-capture data that is formed using a second (different) image-capture modality. A control circuit executes an iterative image reconstruction process that establishes a first and a second image-representation channel, a fidelity error measure that measures inconsistency of the image as compared to first image-capture data and second image-capture data, and a prior-penalty term that scores the image based on a priori likelihood or desirability using, at least in part, for each of a plurality of pixels, a non-separable matrix-penalty of a Jacobian-matrix of the image at that pixel, such as nuclear norm.

Abstract: In a first exemplary embodiment of the present invention, an automated, computerized method is provided for processing an image. According to a feature of the present invention, the method comprises the steps of, at a computer system, receiving an image recorded at and transmitted from a remote source, at the computer system, processing the transmitted image, for segregation of the transmitted image into a corresponding intrinsic image and, at the computer system, processing the corresponding intrinsic image to perform a preselected task, for a result. As a further feature of the first exemplary embodiment of the present invention, the remote source comprises a cell phone or remote computer system.

Abstract: A candidate-region for an object-region is set in an image. In a graph including point-S corresponding the object-region, point-T corresponding to a background-region, a point corresponding to each pixel in the image, S-link connecting each pixel and point-S, T-link connecting each pixel and point-T, and N-link connecting each pair of adjacent pixels, a cost is set for each link, graph-cut is performed. Whether a pixel connected to point-S by a link is present in the graph is judged. If no pixel is present, graph-cut is performed at each stage while costs set for all the S-links connecting each pixel in the candidate-region and point-S are increased stepwise in an increment of a predetermined threshold or less until a pixel connected to point-S by a link appears. Whether each pixel in the image belongs to the object-region or the background-region is determined based on a result of graph-cut performed last.

Abstract: A local feature descriptor for a point in an image is generated over multiple levels of an image scale space. The image is gradually smoothened to obtain a plurality of scale spaces. A point may be identified as the point of interest within a first scale space from the plurality of scale spaces. A plurality of image derivatives is obtained for each of the plurality of scale spaces. A plurality of orientation maps is obtained (from the plurality of image derivatives) for each scale space in the plurality of scale spaces. Each of the plurality of orientation maps is then smoothened (e.g., convolved) to obtain a corresponding plurality of smoothed orientation maps. Therefore, a local feature descriptor for the point may be generated by sparsely sampling a plurality of smoothed orientation maps corresponding to two or more scale spaces from the plurality of scale spaces.

Abstract: A position and orientation measurement device includes a grayscale image input unit that inputs a grayscale image of an object, a distance image input unit that inputs a distance image of the object, an approximate position and orientation input unit that inputs an approximate position and orientation of the object with respect to the position and orientation measurement device, and a position and orientation calculator that updates the approximate position and orientation. The position and orientation calculator calculates a first position and orientation so that an object image on an image plane and a projection image of the three-dimensional shape model overlap each other, associates the three-dimensional shape model with the image features of the grayscale image and the distance image, and calculates a second position and orientation on the basis of a result of the association.