Abstract:
An image reconstruction system, apparatus, and method employing a non-sequential scanning scheme using real-time feedback are provided. A projection information generating unit is configured to generate at least one piece of projection information by the X-ray irradiated to the object in the at least one viewpoint. A projection information comparing unit is configured to compare predicted intermediate projection information with measured intermediate projection information from the generated projection information. The predicted intermediate projection information is predicted from pieces of projection information generated from different viewpoints, and the measured intermediate projection information is measured in an intermediate viewpoint corresponding to the predicted intermediate projection information. A determining unit is configured to determine whether to irradiate the X-ray to the object in an additional viewpoint. An image reconstructing unit is configured to reconstruct the generated projection information, and to acquire an image representing the object.
Abstract:
An image processing method includes generating warped image data by warping first reconstructed image data corresponding to a first time point, based on first change data corresponding to a change between first rendered image data corresponding to the first time point and second rendered image data corresponding to a second time point, generating a sampling map that designates a sampling number, a sampling position, or a combination of the sampling number and the sampling position, for each pixel of the second rendered image data corresponding to the second time point by executing a neural sampling map generation model based on the warped image data and scene context information, and rendering the second rendered image data corresponding to the second time point by performing ray tracing on each pixel of the second rendered image data corresponding to the second time point using the sampling map.
Abstract:
An image processing apparatus for performing motion estimation is provided. The image processing apparatus includes at least one processor configured to implement: a position estimation module configured to estimate an initial search position by providing a first frame and a second frame of a video as input to a neural network that is trained to output the initial search position; and a motion estimation module configured to perform motion estimation based on the initial search position.
Abstract:
A method and apparatus with battery short circuit detection are included. In one general aspect, a processor-implemented method includes, based on battery data measured by a battery and a battery model of the battery, determining a detection parameter value used for detecting a short circuit of the battery and a variation factor value correlated with the detection parameter, using the variation factor to extract a reference value corresponding to the detection parameter value from a reference data set, and determining whether a short circuit of the battery has occurred based on a result of comparing the detection parameter value with the reference value.
Abstract:
A processor-implemented method with battery state estimation includes estimating a current state of charge (SOC) of a target battery by correcting a first electrochemical model corresponding to the target battery using a first voltage difference between a measured voltage of the target battery and an estimated voltage of the target battery that is estimated by the first electrochemical model, estimating an end SOC of the target battery by correcting a second electrochemical model using a second voltage difference between an estimated voltage of a virtual battery that is estimated by the second electrochemical model and a preset voltage, and estimating a relative SOC (RSOC) of the target battery based on the current SOC and the end SOC of the target battery, wherein the second electrochemical model is based on the virtual battery corresponding to the target battery being discharged to reach the preset voltage.
Abstract:
A battery charging control method and apparatus is disclosed. The battery charging control method includes inputting a preset magnitude of a current to a battery during a preset period of time, identifying a diffusion characteristic of a material in the battery, and determining whether to change the magnitude of the current to be input to the battery based on the identified diffusion characteristic of the material, in which the diffusion characteristic may be determined based on a distribution of the material in one or more of a cathode of the battery, an anode of the battery, and an electrolyte of the battery in response to the input of the current in the battery.
Abstract:
An image processing apparatus includes a first processor configured to obtain, from a color image, an illumination element image and an albedo element image corresponding to the color image, and a second processor configured to divide the illumination element image into a plurality of subelement images each corresponding to the color image.
Abstract:
A battery control method that calculates a boosting ratio for converters based on voltage values of batteries and a preset voltage value, and transmits the calculated boosting ratio to the converters is disclosed. The converters are configured to boost output voltages of the batteries based on the calculated boosting ratio, and a sum of the boosted output voltages is equal to the preset voltage value.
Abstract:
A battery monitoring method includes identifying a state of charge (SOC) of a battery, obtaining a voltage of the battery with respect to the SOC, in response to the identified SOC being included in a diagnosis section, and determining a state of health (SOH) of the battery based on the obtained voltage of the battery.
Abstract:
A battery charging method includes acquiring a functional relationship of a differential value of an amount of charge or a state of charge (SOC) with respect to a voltage of a battery based on the voltage or the SOC, determining charging steps for charging of the battery by analyzing the functional relationship, and generating a charging profile comprising charging currents for each of the charging steps to charge the battery.