Abstract: A system and related method for hybrid headtracking receives head-referenced pose data from a head-mounted IMU and platform-referenced or georeferenced position and orientation (pose) data from a platform-mounted IMU, determines error models corresponding to uncertainties associated with both IMUs, and performs an initial estimate of head pose relative to the platform reference frame based on the head-referenced and platform-referenced pose data. A numerically stable UD factorization of the Kalman filter propagates the estimated head pose data forward in time and corrects the initial head pose estimate (and may correct the error models associated with the head-mounted and platform-mounted IMUs) based on secondary head pose estimates, and corresponding error models, received from an optical or magnetic aiding device. The corrected head pose data is forward to a head-worn display to ensure high accuracy of displayed imagery and symbology.

Abstract: A computer implemented method of diagnosing whether a human subject is infected with Zika virus, includes: determining a correlation between a fundus test image of an eye of the human subject for presence of gross macular pigment mottling with a known set of Zika virus infected fundus images and with a known set of healthy fundus images, wherein a high correlation/low correlation between the fundus test image and the known set of Zika virus infected fundus images indicates that there is a high probability/low probability that the human subject is infected with Zika virus, wherein a high correlation/low correlation between the fundus test image and the known set of healthy fundus images indicates that there is a low probability/high probability that the human subject is infected with Zika virus.

Abstract: A method and system for detecting actions of an object in a scene from a video of the scene. The video is a video sequence partitioned into chunks, and each chunk includes consecutive video frames. The method including the following elements. Acquiring the video of the scene, wherein the video includes a sequence of images. Tracking the object in the video, and for each object and each chunk of the video, further comprising: determining a sequence of contour images from video frames of the video sequence to represent motion data within a bounding box located around the object. Using the bounding box to produce cropped contour images and cropped images for one or more images in each chunk. Passing the cropped contour images and the cropped images to a recurrent neural network (RNN) that outputs a relative score for each action of interest.

Abstract: The present disclosure relates to agriculture. The teachings thereof may be embodied in methods to determine a percentage of weeds and/or control device. For example, a method for determining a weed percentage in an observation section of a field may include: acquiring actual spectral information using an optical observation section sensor aimed at the observation section; acquiring reference spectral information using an optical reference sensor aimed at a reference section of the same ground area; determining a difference between the actual spectral information and the reference spectral information; and mapping the difference to the weed percentage using predefined mapping.

Abstract: A computer includes a processor that is programmed to activate a vehicle exterior light, and measure a luminance in a predetermined region outside the vehicle based on vehicle camera data. The processor is programmed to determine whether the vehicle exterior light is operational based the measured luminance.

Abstract: Systems and methods for processing electronic imaging data obtained from medical imaging procedures are disclosed herein. Some embodiments relate to data processing mechanisms for medical imaging and diagnostic workflows involving the use of machine learning techniques such as deep learning, artificial neural networks, and related algorithms that perform machine recognition of specific features and conditions in imaging data. In an example, a deep learning model is selected for automated image recognition of a particular medical condition on image data, and applied to the image data to recognize characteristics of the particular medical condition. Based on the characteristics recognized by the automated image recognition on the image data, an electronic workflow for performing a diagnostic evaluation of the medical imaging study may be modified, updated, or prioritized.

Abstract: Improvements are disclosed for detecting counterfeit objects, based on comparison to digital fingerprints that describe features found in images of objects known to be counterfeit.

Abstract: A method for displaying at least two medical images, each medical image highlighting at least one feature, including steps of obtaining a 2D medical image, identifying at least two features on the obtained medical image, generating masks showing the identified features, each mask highlighting at least one of the identified features, generating a set of at least two medical images, each medical image highlighting at least one of the identified features by superimposing at least one of the masks on the obtained medical image, and displaying the set of at least two generated medical images, one after the other. The invention also relates to a microprocessor comprising a computer algorithm to perform the method of the invention and to a system comprising said microprocessor and a visualizing means.

Abstract: A video encoder may use an adaptive Wiener filter inside the core video encoding loop to improve coding efficiency. In one embodiment, the Wiener filter may be on the input to a motion estimation unit and, in another embodiment, it may be on the output of a motion compensation unit. The taps for the Wiener filter may be determined based on characteristics of at least a region of pixel intensities within a picture. Thus, the filtering may be adaptive in that it varies based on the type of video being processed.

Abstract: For an image processing concept, a database including data derived from a plurality of frames of a video is provided in a device. A live video feed is obtained from a camera of the device. Information is extracted from an image of the video feed. A search is performed in the database using the extracted information to retrieve a list of potential frames out of the plurality of frames. An initial pose of the selected image is estimated with respect to one frame of the list as a function of the extracted information and the data derived from the one frame. Respective subsequent poses for subsequent images from the live video feed are iteratively estimated, wherein the associated subsequent pose is estimated based on said subsequent image and a respective previously estimated pose. The video feed is augmented on the device with virtual information based on the estimated initial pose and the subsequent poses.

Abstract: An X-ray CT apparatus according to an embodiment includes processing circuitry. The processing circuitry collects pieces of image data in a plurality of time phases that contain at least a part of a coronary artery of a heart. The processing circuitry acquires image indexes regarding the pieces of image data. The processing circuitry extracts a set of image data from combinations of pieces of image data having a larger time interval than a predetermined time interval, of the pieces of image data, based on the image indexes in the respective pieces of image data. The processing circuitry performs fluid analysis regarding the coronary artery based on the extracted set of image data to obtain a fluid parameter regarding the coronary artery.

Abstract: A video encoder may use an adaptive Wiener filter inside the core video encoding loop to improve coding efficiency. In one embodiment, the Wiener filter may be on the input to a motion estimation unit and, in another embodiment, it may be on the output of a motion compensation unit. The taps for the Wiener filter may be determined based on characteristics of at least a region of pixel intensities within a picture. Thus, the filtering may be adaptive in that it varies based on the type of video being processed.

Abstract: A method of generating a correction plan for correcting a deformed bone includes inputting to a computer system a first image of the deformed bone in a first plane and inputting to the computer system a second image of the deformed bone in a second plane. Image processing techniques are employed to identify a plurality of anatomical landmarks of the deformed bone in the first image. The first image of the deformed bone is displayed on a display device. A graphical of the deformed bone is autonomously generated and graphically overlaid on the first image of the deformed bone on the display device, the graphical template including a plurality of lines, each line connected at each end to a landmark point corresponding to one of the anatomical landmarks. A model of the deformed bone may be autonomously generated based on the graphical template.

Abstract: To achieve highly accurate image analysis processing without using a large amount of network bandwidth, an analysis apparatus acquires an image via a network, executes analysis processing, acquires additional image data depending on a result of the analysis processing, and executes reanalysis processing by using the additional image data.

Abstract: A method for filtering a digital image, comprising segmenting the digital image into a plurality of tiles; computing tile histograms corresponding to each of the plurality of tiles; deriving a plurality of tile transfer functions from the tile histograms preferably using 1D convolutions; interpolating a tile transfer function from the plurality of tile transfer functions; and filtering the digital image with the interpolated tile transfer function. Many filters otherwise difficult to conceive or to implement are possible with this method, including an edge-preserving smoothing filter, HDR tone mapping, edge invariant gradient or entropy detection, image upsampling, and mapping coarse data to fine data.

Abstract: A system includes a processor configured to obtain an image of a vehicle plate. The processor is also configured to determine identification characters present in the image. The processor is further configured to compare the identification characters to a list of sought-vehicle plates and report a match between the identification characters and a plate on the list of sought-vehicle plates.

Abstract: Systems and methods according to one or more embodiments are provided for detecting an object in a field of view of an imaging device. An object may be detected by an imaging device when the object is present along a trajectory in a target scene. In one example, a system includes a memory component to store a plurality of images of the target scene and a processor. The processor is configured to define the trajectory between two locations within the target scene and extract a subset of pixel values from each of successive images corresponding to the trajectory. The extracted subsets of pixel values are processed to detect an object within the target scene. Additional systems and methods are also provided.

Abstract: A manned unmanned teaming (MUM-T) image system includes an unmanned vehicle (UV) configured to travel in a first heading and includes at least one sensor configured to capture at least one image having a first visual orientation pursuant to the first heading. The MUM-T image system generates image data indicative of the at least one image. A manually operated vehicle (MOV) in signal communication with the UV is configured to travel in a second heading. The MOV comprises an electronic image transformation module configured to receive the image data and to transform the image data into a second orientation different from the first orientation based on the second heading. An electronic display unit is configured to receive the transformed image data and to display the at least one image according to the second orientation.

Abstract: A computer implemented method of matching a medical images of an anatomical structure of a patient's body with an atlas-based representation of the anatomical structure is described. The method includes acquiring patient image data; determining, based on the patient image data, patient substructure data; acquiring general substructure data; determining, for each of the patient substructures and based on the patient substructure data and the general substructure data, substructure matching data; determining, based on the general substructure data and the substructure matching data, anatomical structure atlas data; determining, based on the patient image data and the anatomical structure atlas data, matching transformation data describing an atlas-patient matching transformation between the medical image representation of the anatomical structure and the atlas representation of the anatomical structure.

Abstract: An image target tracking method, device, and system thereof are provided in the present disclosure. The image target relative position determining method includes the following steps: obtaining a target initial position, and performing a sparse sampling according to the target initial position; dividing sampling points into foreground sampling points and background sampling points; clustering adjacent foreground sampling points according to a spatial distribution of the foreground sampling points in order to obtain a clustering result containing a plurality of clusters; and performing a robust estimation according to the clustering result in order to determine a relative position between a target and a camouflage interference in an image.