Samsung Electronics Co., Ltd.

Dae-hyun Ji

Cheol-hun Jang

Yoon-suk Hyun

Do-kwan Oh

Won-ju Lee

Ja-hoo Koo

Jae-woo Lee

Dong-wook Lee

Se-ho Shin

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

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.

Training data generating method for image processing, image processing method, and devices thereof

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.

Growing community of inventors

Hwaseong-si, South Korea

Dae-hyun Ji