Abstract: Provided are a method and apparatus for determining driving information. The apparatus generates a probability map corresponding to a target object to be detected from a driving image, extracts representative points from a candidate region of the target object detected from the driving image, extracts some of the representative points based on the probability map, calculates a confidence value for the candidate region of the target object based on the extracted some representative points, and determines driving information of the vehicle based on the confidence value.

Abstract: Provided are an apparatus and a method for converting an image. The apparatus includes an image sensor configured to obtain an image of a road, and a processor. The processor is configured to segment an input image into a plurality of region images, determine a vanishing point corresponding to each of the plurality of region images, obtain a translation relation for converting two-dimensional (2D) coordinates of a point in a region image among the plurality of region images into three-dimensional (3D) coordinates, based on a vanishing point of the region image, and generate road profile data based on translation relations of the plurality of region images.

Abstract: Disclosed is a method and apparatus of detecting an object of interest, where the apparatus acquires an input image, sets a region of interest (ROI) in the input image, and detects the object of interest from a restoration image, having a resolution greater than a resolution of the input image, corresponding to the ROI.

Abstract: An image processing method and an image processing device detect an object from a driving image of a vehicle, obtain information on an altitude difference between the vehicle and the object, and input image domain coordinates of the object in the driving image and the information on the altitude difference to a neural network and determine world domain coordinates of the object.

Abstract: A magnetic core according to one embodiment of the present invention includes a first magnetic core having pure iron or an Fe-based alloy and a second magnetic core disposed to surround at least a part of an outer circumferential surface of the first magnetic core and including ferrite.

Abstract: A training data generation method includes acquiring an image captured from a vehicle and location information of the vehicle corresponding to the image; acquiring map data corresponding to the acquired location information; determining truth data including information associated with a road included in the image from the acquired map data; and generating training data including the image and the determined truth data.

Abstract: A road line determination method and apparatus is provided. The method includes: performing detection of two road lines of a lane in which the vehicle is driving from a driving image; determining whether at least one road line of the two road lines is not detected; if it is determined that the at least one road line is not detected, determining at least one road line for the at least one undetected road line based on first information about a drivable road area comprising the road; and controlling driving of the vehicle based on the at least one determined road line.

Abstract: A polarizing layer includes a substrate and a plurality of parallel wires disposed on the substrate. Each of the plurality of wires includes a base layer disposed on the substrate and an anti-reflective layer disposed on the base layer. The base layer includes aluminum or an aluminum alloy. The anti-reflective layer has a thickness within a range of 12 nm to 40 nm.

Abstract: A bacterium that constitutively produces monophosphoryl lipid A (MLA) and a method of producing MLA by using the bacterium may simply produce MLA and a derivative thereof without acid hydrolysis, reduce a probability of natural mutation, and increase yields of MLA and a derivative thereof by constitutive expression of the MLA and derivative thereof.

Abstract: Disclosed is a washing system capable of detecting a level of contamination of a laundry tub by executing a big data, an artificial intelligence (AI) algorithm and/or a machine learning algorithm in a 5G environment connected for things Internet. The washing system capable of detecting a level of contamination of a laundry tub according to one embodiment of the present disclosure includes a composite sensor for detecting a level of contamination of a laundry tub, a washing machine controller that receives a digital signal from the composite sensor to determine a level of contamination of the laundry tub, and a server communicating with the washing machine. The washing machine controller or the server learns AI model with the training data set through a machine learning algorithm in order to predict a progressing degree of contamination of the laundry tub.

Abstract: A polypropylene resin composition includes: a base resin; a thermoplastic elastomer; and an inorganic filler; a major-axis diameter/minor-axis diameter, which is an aspect ratio of the inorganic filler, is 2 to 8. A molded product includes an injection molding of the polypropylene resin composition. The polypropylene resin composition may simultaneously impart excellent rigidity, impact resistance, and excellent dimensional stability even when applied to a molded product having a small thickness, while maintaining a low specific gravity.

Abstract: A skin whitening method including: administering to a subject a cosmetic composition including a tranexamic acid-peptide having skin whitening activity selected from the group consisting of Tranexamil-AS, Tranexamil-AT, Tranexamil-AP, Tranexamil-GP, Tranexamil-ES, Tranexamil-KK, Tranexamil-HK, Tranexamil-MY, Tranexamil-GH, Tranexamil-MA, Tranexamil-AH, Tranexamil-CC, Tranexamil-SA, Tranexamil-WA, Tranexamil-WE, Tranexamil-KD, Tranexamil-NA, Tranexamil-TS, Tranexamil-SS, Tranexamil-EC, Tranexamil-TA, Tranexamil-PF, Tranexamil-VS, Tranexamil-VV, Tranexamil-VP, Tranexamil-AA, Tranexamil-PS, Tranexamil-HA, Tranexamil-GK, Tranexamil-KV, Tranexamil-AR, Tranexamil-RP, Tranexamil-PQ, Tranexamil-QG, Tranexamil-PP, Tranexamil-VR, Tranexamil-SV, Tranexamil-ET, Tranexamil-CG and Tranexamil-NT.

Abstract: A camera module includes a housing to accommodate a lens module, a stop module coupled to the lens module and configured to selectively change an amount of light incident to the lens module, and a coil portion configured to drive the stop module to selectively change an amount of light incident to the lens module. The coil portion is disposed on the housing.

Abstract: A dynamic imbalance detection system capable of whether a washing machine is in a dynamically imbalanced position by using big data and executing an AI algorithm or a machine learning algorithm in a 5G communications network environment built for IoT. The system includes a washing machine and a server communicating with the washing machine. The washing machine includes a vibration sensor attached to a washing machine cabinet and a controller receiving a vibration signal detected by the vibration sensor during the operation of the washing machine and processing the vibration signal into vibration data. The server receives the vibration data from the controller and trains a machine learning algorithm on a training dataset that is obtained by processing one or more features among a displacement magnitude, a displacement ratio, and a displacement phase, and determines result values of dynamic balance and dynamic imbalance labeled with the one or more features.

Abstract: A laundry processing apparatus and a driving method thereof for driving a laundry processing apparatus by executing an artificial intelligence (AI) algorithm and/or machine learning algorithm in a 5G environment connected for the Internet of Things are provided. The driving method may include obtaining a drive current of a motor and a rotational speed of a drum during a cycle of the laundry processing apparatus, classifying a type of load of laundry located inside the laundry processing apparatus based on the obtained drive current and rotational speed, determining whether to change a course of the laundry processing apparatus according to the type of load, outputting a recommended course corresponding to the type of load when a course change of the laundry processing apparatus is determined, and changing the cycle of the laundry processing apparatus to the recommended course upon receiving a selection signal for the recommended course.

Abstract: A skin whitening method including: administering to a subject a cosmetic composition including a tranexamic acid-peptide having skin whitening activity selected from the group consisting of Tranexamil-AS, Tranexamil-AT, Tranexamil-AP, Tranexamil-GP, Tranexamil-ES, Tranexamil-KK, Tranexamil-HK, Tranexamil-MY, Tranexamil-GH, Tranexamil-MA, Tranexamil-AH, Tranexamil-CC, Tranexamil-SA, Tranexamil-WA, Tranexamil-WE, Tranexamil-KD, Tranexamil-NA, Tranexamil-TS, Tranexamil-SS, Tranexamil-EC, Tranexamil-TA, Tranexamil-PF, Tranexamil-VS, Tranexamil-VV, Tranexamil-VP, Tranexamil-AA, Tranexamil-PS, Tranexamil-HA, Tranexamil-GK, Tranexamil-KV, Tranexamil-AR, Tranexamil-RP, Tranexamil-PQ, Tranexamil-QG, Tranexamil-PP, Tranexamil-VR, Tranexamil-SV, Tranexamil-ET, Tranexamil-CG and Tranexamil-NT.

Abstract: An embodiment provides a magnetic core comprising a first powder and a second powder, wherein the hardness of the first powder is lower than that of the second powder, and the volume of the first powder is 40% to 60% with respect to the combined volume of the first powder and the second powder.

Abstract: A thermoplastic resin composition and a molded article produced using the same.

Abstract: A method and apparatus for adjusting a neural network that classifies a scene of an input image into at least one class is provided. The method generates a feature image having a size that is less than a size of an input image by applying a convolutional network to the input image, determines at least one class corresponding to the feature image, generates a class image having a size corresponding to the size of the input image by applying a deconvolutional network to the feature image, calculates a loss of the class image based on a verification class image preset with respect to the input image, and adjusts the neural network based on the loss.

Abstract: An embodiment of the present invention provides a method for forming a metal oxide coating layer on a catalyst support, which comprises a precipitation step for forming a metal-containing precipitate on the catalyst support by contacting the catalyst support with a mixed solution containing a metal oxide precursor and a precipitant, and a calcination step for calcinating the metal-containing precipitate produced on the catalyst support to produce the metal oxide coating layer on the catalyst support.