A method of tracking an object includes performing a hybrid search over a sequence of frames. The hybrid search includes periodically performing a global search on selected frames of the sequence of frames and performing a local search on frames between the selected frames of the global search. The method also includes updating a similarity function based on a result of the hybrid search. The method further includes tracking the object based on the hybrid search.

The invention provides for a medical imaging system comprising: a memory for storing machine executable instructions; a processor for controlling the medical instrument. Execution of the machine executable instructions causes the processor to: receive MRF magnetic resonance data acquired according to an MRF magnetic resonance imaging protocol of a region of interest; reconstruct an MRF vector for each voxel of a set of voxels descriptive of the region of interest using the MRF magnetic resonance data according to the MRF magnetic resonance imaging protocol; calculate a preprocessed MRF vector (126) for each of the set of voxels by applying a predetermined preprocessing routine to the MRF vector for each voxel, wherein the predetermined preprocessing routine comprises normalizing the preprocessed MRF vector for each voxel; calculate an outlier map for the set of voxels by assigning an outlier score to the preprocessed MRF vector using a machine learning algorithm.

A radar image processing device includes at least one memory configured to store instructions; and at least one processor configured to execute the instructions to: determine a search range based on a reference block and a layover direction, the reference block being set as an area of interest in a radar image generated from data obtained by an imaging radar, the layover direction being a direction in which layover occurs in the radar image and being estimated from an incident direction of an electromagnetic wave used for observation by the imaging radar; extract a similar block that is similar to the reference block and included in the search range by searching the search range; and perform filtering processing for reducing speckles generated in the radar image by using the reference block and the extracted similar block.

An augmented reality (AR) providing method for recognizing a context using a neural network includes acquiring, by processing circuitry, a video; analyzing, by the processing circuitry, the video and rendering the video to arrange a virtual object on a plane included in the video; determining whether a scene change is present in a current frame by comparing the current frame included in the video with a previous frame; determining a context recognition processing status for the video based on the determining of whether the scene change is present in the current frame; and in response to determining that the context recognition processing status is true, analyzing at least one of the video or a sensing value received from a sensor using the neural network and calculating at least one piece of context information, and generating additional content to which the context information is applied and providing the additional content.

A glaucoma diagnosis apparatus according to an embodiment includes a fundus image processor configured to receive a fundus image and extract a first region of interest (ROI) and a second ROI from the received fundus image, an image classification neural network configured to learn the extracted first ROI and perform classification into a normal fundus image and a glaucoma fundus image on the basis of the learned first ROI, a vertical cup-to-disc ratio (vCDR) calculator configured to recognize an optic disc (OD) and an optic cup (OC) from the extracted second ROI and calculate a vCDR, and a determinator configured to aggregate a vCDR calculation result and an image classification result of the image classification neural network to determine whether glaucoma is present in the fundus image.

Provided are an image detection device, an image detection method and a program, which are capable of improving correspondence to a target deformation by optimizing a template shape, when performing target detection using template matching. An image detection device 100 for detecting a target from an input image comprises: a template generation unit 10 that generates a template for detecting a target; a mask generation unit 20 that generates a mask which shields a portion of the template, on the basis of temporal variations of a feature point extracted from an area including the image target; and a detection unit 30 that detects the target from the image using the template a portion of which is shielded by the mask.

A disparity estimation device calculates, for each of first pixels of a first image and each of second pixels of a second image, a first census feature amount and a second census feature amount, calculates, for each of the first pixels, a first disparity value of the first pixel with integer accuracy, extracts, for each of the first pixels, reference pixels located in positions corresponding to the first disparity value and a near disparity value close to the first disparity value from the second pixels, calculates sub-pixel evaluation values based on the relationship between the pixel values of the first pixel and the neighboring pixel and the pixel values of each of the reference pixels and the neighboring pixel, and estimates a second disparity value of the first pixel with sub-pixel accuracy by equiangular fitting.

A method according to an aspect of the present disclosure includes combining pieces of first feature data and pieces of second feature data. Each of the pieces of first feature data is associated with first identification information related to a corresponding one or more of first constituents included in a first group and indicates a feature of the corresponding one or more of the first constituents. Each of the pieces of the second feature data corresponds to one of clusters in the second group. The second feature data includes statistic data associated with second identification information related to two or more of the second constituents included in a corresponding cluster. The statistic data has a statistic indicating a feature of two or more of the second constituents included in the corresponding cluster. The combining is performed based on the first identification information and the second identification information.

A method, apparatus and computer-readable storage medium are provided to define a storyline based on path probabilities for a plurality of paths through the frames of a video. Relative to a method and for a plurality of frames of a video, regions of a first frame and regions of a second, subsequent frame that have been viewed are identified. tified. For each of at least one first-frame region of one or more regions of the first frame, the method determines a transition probability of transitioning from a respective first-frame frame region of the first frame to each of at least one second-frame region of a plurality of regions of the second frame. Based on the transition probabilities, the method determines a path probability for each of at least one of a plurality of paths through the frames of the video. The method additionally defines a storyline based on the path probabilities.

Devices, systems, and methods obtain a region of an image; generate known-object scores for the region using known-object detectors, wherein each known-object detector of the known-object detectors detects objects in a respective object class; determine a likelihood that the region includes a complete object; and determine a likelihood that the region includes an unknown object based on the likelihood that the region includes a complete object and on the known-object scores.