Abstract: In one aspect, an information processing apparatus includes a first acquisition module, a first extraction module, a first generation module, a second extraction module, a derivation module, and a first output control module. The first acquisition module acquires an input image to output a first image and a second image. The first extraction module extracts first characteristic point information from the first image. The first generation module generates a third image obtained by reducing a data amount of the second image. The second extraction module extracts second characteristic point information from the third image. The derivation module derives a difference between the first characteristic point information and the second characteristic point information. The first output control module outputs the third image corrected in accordance with the difference as an output image.

Abstract: Reader and plate methods, operations, and systems for observing a biological sample are shown and described. In one embodiment, a device for observing biological growth, when present, on a growth plate, includes an imaging device and a variable positioning nest. The nest may include a first sunken frame to receive a first growth plate, and an offset second sunken frame to receive a distinct second growth plate in an operating position offset about the first operating position.

Abstract: An imaging range estimation device includes an image data processor configured to acquire image data imaged by a camera device and generate image data with an object name label added, a reference data generator configured to set, by using geographic information, a region within a predetermined distance that is imagable from an estimated position at which the camera device is installed and generate reference data with an object name label added, and an imaging range estimator configured to calculate a concordance rate by comparing a feature indicated by a region of an object name label of the image data with a feature indicated by a region of an object name label of the reference data, and estimate the imaging range of the camera device to be a region of the reference data that corresponds to the image data.

Abstract: An apparatus is described which includes two or more colour displays arranged to provide piece-wise continuous illumination of a volume, and one or more cameras arranged to image the volume. The apparatus is configured to control the colour displays and the cameras to illuminate the volume with each of two or more illumination conditions. The apparatus is also configured to obtain two or more sets of images, which include sufficient information for calculation of a reflectance map and a photometric normal map of an object or subject positioned within the volume. Each set of images is obtained during illumination of the volume with one or more corresponding illumination conditions. When viewed from the volume, the apparatus only provides direct illumination of the volume from angles within a zone of a hemisphere, which is less than a hemisphere.

Abstract: Systems and methods for image processing are described. Embodiments of the present disclosure include an image processing apparatus configured to efficiently perform texture synthesis (e.g., increase the size of, or extend, texture in an input image while preserving a natural appearance of the synthesized texture pattern in the modified output image). In some aspects, the image processing apparatus implements an attention mechanism with a multi-stage attention model where different stages (e.g., different transformer blocks) progressively refine image feature patch mapping at different scales, while utilizing repetitive patterns in texture images to enable network generalization. One or more embodiments of the disclosure include skip connections and convolutional layers (e.g., between transformer block stages) that combine high-frequency and low-frequency features from different transformer stages and unify attention to micro-structures, meso-structures and macro-structures.

Abstract: A method for processing image information of an imaging sensor of a vehicle in an artificial neural network (“ANN”) is disclosed. The ANN includes at least one encoder and one decoder. The ANN solves a classification task with a plurality of classes and/or a regression task, in which numerical output information quantized according to a plurality of quantization steps is provided. The ANN outputs multiple feature maps at the output interface, wherein allocations of image regions of the image information to classes or numerical output information quantized regarding the image information is/are output by the feature maps in an encoded manner.

Abstract: Described herein are systems and methods for responding to user input using an agent orchestrator. A system may include a cardiac catheter, a user interface, and a computing device configured to receive, from the user interface, a first user input, receive, from the catheter, the procedure data, determine, using an agent orchestrator, a first agent selection datum, wherein determining the first agent selection datum includes generating the first agent selection datum as a function of the first user input using a trained agent selection machine learning model, using a first agent corresponding to the first agent selection datum, determine a first agent output, wherein determining the first agent output includes inputting into the first agent the procedure data, and receiving, as an output from the first agent, the first agent output, and display, using the user interface, the first agent output.

Abstract: A distance calculation apparatus includes an in-vehicle detection unit configured to detect a situation around a subject vehicle, and a microprocessor and a memory connected to the microprocessor. The microprocessor is configured to perform recognizing an object on the basis of a detection data detected by the in-vehicle detection unit, extracting feature points included in the detection data, recognizing a representative position of a predetermined object on the basis of a distribution of feature points corresponding to the predetermined object among the feature points extracted in the extracting when the predetermined object is recognized in the recognizing, and calculating a distance from the subject vehicle to the predetermined object on the basis of the representative position recognized in the recognizing.

Abstract: A crowd motion simulation method is provided based on real crowd motion videos. The method includes framing the videos and storing the framed videos into continuous high-definition images, generating a crowd density map of each image, and accurately positioning an individual in each density map to obtain the accurate position of each individual. The method also includes correlating the positions of each individual in different images to form a complete motion trajectory, and extracting motion trajectory data; and quantifying motion trajectory data, defining training data and data labels, and calculating data correlation. The method further includes building a deep convolutional neural network, and inputting the motion trajectory data for training to learn crowd motion behaviors; and randomly placing a plurality of simulation individuals in a two-dimensional space, testing a prediction effect of the deep convolutional neural network, adjusting parameters for simulation, and drawing a crowd motion trajectory.

Abstract: The invention concerns a method (1) for detecting and tracking objects orbiting around the earth (for example space debris) by means of on-board processing of images acquired by a space platform (for example a satellite, a space vehicle or a space station) by one or more optical sensors, preferably one or more star trackers.

Abstract: The present disclosure relates to devices, apparatus and methods of improving the accuracy of image-based assay, that uses imaging system having uncertainties or deviations (imperfection) compared with an ideal imaging system. One aspect of the present invention is to add the monitoring marks on the sample holder, with at least one of their geometric and/optical properties of the monitoring marks under predetermined and known, and taking images of the sample with the monitoring marks, and train a machine learning model using the images with the monitoring mark.

Abstract: The disclosure relates generally to image processing. For example, the invention relates to a method and a device for de-noising an electron microscope (EM) image. The method includes the act of selecting a patch of the EM image, wherein the patch comprises a plurality of pixels, wherein the following acts are performed on the patch: i) replacing the value of one pixel, for example of a center pixel, of the patch with the value of a different, for example randomly selected, pixel from the same EM image; ii) determining a de-noised value for the one pixel based on the values of the other pixels in the patch; and iii) replacing the value of the one pixel with the determined de-noised value.

Abstract: A processor-implemented method with neural network training includes: determining first backbone feature data corresponding to each input data by applying, to a first neural network model, two or more sets of the input data of the same scene, respectively; determining second backbone feature data corresponding to each input data by applying, to a second neural network model, the two or more sets of the input data, respectively; determining projection-based first embedded data and dropout-based first view data from the first backbone feature data; and determining projection-based second embedded data and dropout-based second view data from the second backbone feature data; and training either one or both of the first neural network model and the second neural network model based on a loss determined based on a combination of any two or more of the first embedded data, the first view data, the second embedded data, the second view data, and an embedded data clustering result.

Abstract: Robotic picking devices and methods for performing a picking operation. The disclosed methods may involve executing an imagery analysis procedure to identify a feature of interest of an item, wherein the feature of interest may affect a picking device's ability to perform a picking operation, and generating a grasping plan executable by the picking device, wherein the grasping plan accommodates the feature of interest so that the picking device is able to perform the picking operation.

Abstract: A data processing device includes a plurality of cameras arranged according to a predetermined configuration, where each camera is configured to capture successive images and to detect a current location of one or more elements in the captured images with respect to a coordinate system of the camera, a processor to generate a common camera coordinate system in dependence upon the respective coordinate systems of the plurality of cameras, the common camera coordinate system comprising a set of locations in a three-dimensional space included within the field of view of the plurality of cameras, and a detector to detect a current location of a given element with respect to the common camera coordinate system based on images captured by the plurality of cameras, wherein for each camera, the processor is configured, in response to a detection by the detector that the current location of the given element corresponds to a location in the set of locations of the common camera coordinate system, to generate first dat

Abstract: A method may include capturing image data associated with an object in a defined environment at one or more points in time. The method may include capturing radar data associated with the object in the defined environment at the same points in time. The method may include obtaining, by a machine learning model, the image data and the radar data associated with the object in the defined environment. The method may include pairing each image datum with a corresponding radar datum based on a chronological occurrence of the image data and the radar data. The method may include generating, by the machine learning model, a three-dimensional motion representation associated with the object that is associated with the image data and the radar data.

Abstract: An electronic device is provided. The electronic device includes a camera that collects image data, a communication circuit that performs communication with an external device, a memory, and a processor. The processor obtains first position information about the electronic device, stores first feature point information based on the first position information, obtains an image via the camera, recognizes an object from the image, extracts second feature point information about the recognized object, and calculates second position information of higher accuracy than the first position information based on comparing the first feature point information with the second feature point information.

Abstract: In some embodiments, space objects may be detected within shortwave infrared (SWIR) images captured during the daytime. Some embodiments include obtaining a stacked image by stacking shortwave infrared (SWIR) images. A spatial background-difference image may be generated based on the stacked image, and a matched-filter image may be obtained based on the spatial background-difference image. A binary mask may be generated based on the matched-filter image. The binary mask may include a plurality of bits each of which including a first value or a second value based on whether a signal-to-noise ratio (SNR) associated with that bit satisfies a threshold condition. Output data may be generated based on the spatial background-difference image and the binary mask, where the output data provides observations on detected space objects in orbit.

Abstract: The present disclosure provides an operation method of a PET (positron emission tomography) quantitative localization system, which includes steps as follows. The PET image and the MRI (magnetic resonance imaging) of the patient are acquired; the nonlinear deformation is performed on the MRI and the T1 template to generate deformation information parameters; the AAL (automated anatomical labeling) atlas is deformed to an individual brain space of the patient, so as to generate an individual brain space AAL atlas, where the AAL atlas and the T1 template are in a same space; lateralization indexes of the ROIs of the individual brain space AAL atlas corresponding to the PET image normalized through the gray-scale intensity are calculated; the lateralization indexes are inputted into one or more machine learning models to analyze the result of determining a target.

Abstract: A system may include a camera module that may include a first infrared camera, a second infrared camera, and a visible light camera. The system may further include an autonomous vehicle that may include a vertically extendable arm attached to the camera module. The system may also include a processor configured to initiate movement of the autonomous vehicle around an aircraft according to a predetermined path, initiate a scan of an exterior surface of the aircraft using the first infrared camera, the second infrared camera, the visible light camera, or a combination thereof, determine whether a portion of the exterior surface of the aircraft is damaged based on the scan, and in response to the portion of the exterior surface of the aircraft being damaged, use the first infrared camera, the second infrared camera, and the visible light camera to generate a three-dimensional model of the portion of the exterior surface of the aircraft.