Abstract: Provided is a sensor data processing apparatus and method for autonomous driving. The sensor data processing apparatus for autonomous driving includes a receiver configured to receive a plurality of pieces of sensor data from a plurality of sensors, and a processor configured to obtain information related to the plurality of pieces of sensor data based on a generation time point of the plurality of pieces of sensor data, generate an event indicating an update of a synchronization data group and the plurality of pieces of sensor data based on the information, and transmit synchronized sensor data to a client based on the synchronization data group and the event.

Abstract: Provided are a method and device for annotating a detected object. The method of annotating a detected object may include classifying a class of the object, generating a bounding box including a first quadrangle and a second quadrangle both sharing one side, for the object based on the class of the object, and generating an annotation on the object in units of the bounding box.

Abstract: Provided are a method of managing off-chain data and a device therefor. A method of operating a device that constitutes a blockchain network includes generating a first hash value regarding unit data using a first hash function and determining a target shard to store the unit data from among a plurality of shards based on the first hash value, transmitting a first request to store the unit data in the target shard to an external device, and obtaining a changed root value of the target shard changed as the unit data is stored from the external device, wherein the root value represents entire data stored in the target shard.

Abstract: Provided are a method and apparatus for performing authentication on a vehicle on-demand service. A method by which an integrated communication control unit performs authentication on a vehicle on-demand service, includes: storing, in a service authentication server, a first option value related to a vehicle service, received from a tool in factory (TIF) device; obtaining or generating a private root private key and a private root certificate; generating a device certificate and a device private key signed with the private root private key for each performance controller; generating a service token for the first option value by using the private root certificate and the private root private key; and transmitting the generated service token, the private root certificate, and the device private key for each performance controller.

Abstract: A method for generating a vehicle speed profile and a device performing same are disclosed. The method according to an embodiment may comprise the operations of: acquiring a plurality of input speed profiles on the basis of target vehicles located around a vehicle; generating an input array on the basis of the plurality of input speed profiles; and inputting the input array into a neural network to output a speed profile of the vehicle, corresponding to a driving route of the vehicle.

Abstract: Provided are a method and device for collecting data of a computing device. The method of collecting data of a computing device includes, in response to a reset of the computing device, determining whether the reset corresponds to a warm reset, based on the reset corresponding to the warm reset, loading error dump data, generating and storing extended error dump data based on the error dump data, and loading a kernel, and initializing the error dump data, wherein the error dump data is recorded in volatile memory, and the extended error dump data is stored in non-volatile memory.

Abstract: Provided are a method and apparatus for determining a location of an object on a lane map, wherein the method includes acquiring image data captured by a camera mounted on a vehicle, generating feature information regarding a plurality of features included in the image data by performing certain processing on the image data, determining a plurality of features corresponding to a same object in a plurality of pieces of image data, on the basis of a degree of correlation between the plurality of features included in the image data, and determining a location of an object on the lane map, on the basis of location information of the vehicle on the lane map and feature location information on the plurality of pieces of image data.

Abstract: Provided are a method and apparatus for generating a virtual stop line, wherein the method includes determining a target crosswalk from among one or more crosswalks on a driving route, setting a region of interest for the target crosswalk, and determining whether or not to generate a virtual stop line, on the basis of a location of a pedestrian within the region of interest.

Abstract: Provided are a method and device for providing an in-vehicle interface. The method may provide a first interface before driving of a vehicle, a second interface after the driving of the vehicle starts, and a third interface after completion of the driving of the vehicle.

Abstract: A method and system for generating an efficient driving route for a transportation vehicle providing a personal mobility service is disclosed. A transportation vehicle may be a car, truck, bicycle, motorcycle, or the like that transport a payload. A payload may be a person or a product being transported by the vehicle. The personal mobility service broadly refers a service that enables users to plan and book a transportation service at a convenient location and time. A plurality of transportation requests each comprising an origin and a destination is received from the users, a driving route creation device generates an efficient route that visits all destinations of the plurality of transportation requests, and the route may be presented to the users.

Abstract: A method of operating an infotainment device includes extracting context information by inputting an utterance of a user regarding a place to a model, obtaining a search condition for identifying the place based on the context information, and providing a response to the user based on the search condition and a place visit history of the user.

Abstract: An electronic device for controlling a turn signal and an operating method thereof are provided. A method of controlling a turn signal includes, based on route information of a vehicle, identifying a position where a direction change of the vehicle is required, and based on a distance between the position where the direction change is required and a position of the vehicle, controlling a turn signal of the vehicle corresponding to the direction change.

Abstract: A method of generating an improved training data video includes recognizing an object included in a first image by applying at least two recognition techniques to the first image acquired during driving, applying at least two detection techniques to a result of recognizing the object and detecting a frame by each of the applied detection techniques, generating a frame set including a plurality of frames by integrating the detected frames, and generating a second image by sampling the integrated frame set.

Abstract: Provided are a method and apparatus for controlling a vehicle, the method including receiving traffic signal information, determining whether or not a vehicle passes through a crosswalk, on the basis of the traffic signal information and driving information of the vehicle, in response to determining that the vehicle does not pass through the crosswalk, generating a virtual stop line, and controlling the vehicle not to cross the virtual stop line.

Abstract: The present disclosure relates to a method and apparatus for generating a lane polyline by using a neural network model. The method according to an embodiment may extract a multi-scale image feature by using a base image obtained from at least one sensor loaded in a vehicle. According to the method, the multi-scale image feature is input to a first neural network model as input data and a BEV feature may be obtained as output data from the first neural network model. Also, according to the method, the BEV feature may be input to a second neural network model as input data and a polyline image with respect to a certain road may be obtained as output data from the second neural network model. In the present disclosure, a lane polyline obtained from the neural network may be utilized in vehicle control without going through an additional treatment process.

Abstract: The present disclosure provides a method of generating traffic flow statistical data by using wiper motion information of a vehicle, the method comprising: (a) receiving, by a management server, vehicle driving information including location information and wiper motion information of a vehicle driving on a road, from the vehicle; and (b) generating, by the management server, traffic flow statistical data of the road on which the vehicle is driving, based on the vehicle driving information.

Abstract: A method of training a neural network configured to obfuscate a facial image and an electronic device for performing the method are provided. The method includes obtaining, based on an input facial image, an output facial image in which the input facial image is obfuscated, extracting, based on the input facial image, a feature of the input facial image for reconstructing identification information included in the input facial image from the output facial image, extracting, based on the output facial image, a feature of the output facial image corresponding to the feature of the input facial image, and training the neural network based on a difference between the feature of the input facial image and the feature of the output facial image.

Abstract: Provided are face image generation method and device for generating a controllable talking face image.

Abstract: The present disclosure relates to a method and apparatus for performing multipath search. The method according to an embodiment of the present disclosure may calculate a distance between an origin point and a destination point in a group of destination points. In addition, the method may generate a travel path between the origin point and the destination point using a first path-finding method when the distance between the destination point and the origin point is less than a threshold value, and generate the travel path between the origin point and the destination point using a second path-finding method when the distance between the destination point and the origin point is greater than or equal to the threshold value.

Abstract: Provided is a method of improving an object recognition rate including recognizing a first object in a first image obtained while driving, detecting whether the recognized first object has disappeared for a preset time period and then reappeared in the first image, based on detecting that the first object has reappeared, calculating training data for the first object, and controlling such that a recognition model for recognizing an object included in an image is to be trained based on information based on the calculated training data.