Electronics and Telecommunications Research Institute

Hye Sun Park

Kyong Ho Kim

Chang Rak Yoon

Seong Yun Cho

Jaehong Oh

A method of providing a user-interactive customized interaction for a transformation of an extended reality (XR) real object includes segmenting a target object from an input image received through a camera, extracting a similar target object having a highest similarity to the target object from three-dimensional (3D) model data that has been previously learnt, extracting texture of the target object through the camera and mapping the texture to the similar target object, transforming a shape of the similar target object by incorporating intention information of a user based on a user interaction, and rendering and outputting the transformed similar target object.

Method and apparatus for providing user-interactive customized interaction for XR real object transformation

Provided are an apparatus and method for providing safe driving information. The method includes building a database including group information obtained by grouping driving environment information and driving situation information according to attributes of the driving environment information and the driving situation information, and provision forms and provision timings of safe driving information determined according to conditions in groups; collecting driving environment information, driving situation information, obstacle information, and information on a driver's line of sight in real time; determining a provision form and a provision timing of safe driving information based on the collected information and the database; and providing the safe driving information according to the determined provision form and timing.

Apparatus and method for providing safe driving information

A method and apparatus for providing a vehicle camera calibration includes choosing overlap images from among the image information captured by a camera mounted on a vehicle, and filtering images having the same vehicle attitude from among the chosen overlap images on a basis of a map coordinate system and status information of the vehicle, picking out objects in the filtered images, separating stationary objects from the picked out objects, and predicting an angular misalignment with respect to the separated stationary objects.

Growing community of inventors

Daejeon, South Korea

Hye Sun Park