Samsung Electronics Co., Ltd.

Postech Academy-industry Foundation

Cheol-hun Jang

Dae-hyun Ji

Yoon-suk Hyun

Do-kwan Oh

Ja-hoo Koo

Seung-Yong Lee

Jae-woo Lee

Yong-Jin Kim

Won-ju Lee

Mi-sook Ha

A method of generating a second neural network model according to an example embodiment includes: inputting unlabeled input data to a first neural network model; obtaining prediction results corresponding to the unlabeled input data based on the first neural network model; and generating a second neural network model based on the prediction results of the first neural network model and a degree of distribution of the prediction results.

Method of outputting prediction result using neural network, method of generating neural network, and apparatus therefor

A method of controlling a vehicle using a first model trained according to optimized output of a second model.

Method and apparatus for controlling vehicle

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.

Method and apparatus for determining road line

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.

Method and apparatus for determining driving information

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.

Apparatus and method for converting image

Provided are a color to grayscale image conversion method of converting a color image into a grayscale image while maintaining original features of the color image, and a recording medium storing a program for performing the same. When an original color image is input, a target gradient with the features of the input original color image is acquired, and a global mapping function for converting the original color image into a grayscale image is determined based on the acquired target gradient. Thereafter, the original color image is converted into a grayscale image using the determined global mapping function. Therefore, it is possible to quickly convert a color image into a grayscale image, and to acquire a high-quality grayscale image with features of color difference included in the original color image.

Growing community of inventors

Pohang-si, South Korea

Cheol-hun Jang