公开(公告)号：US11999354B2

公开(公告)日：2024-06-04

申请号：US17186329

申请日：2021-02-26

Applicant: Korea Advanced Institute of Science and Technology

Inventor： Sei-Bum Choi ,  Min-Hyun Kim ,  Jin-Rak Park ,  Seung-In Shin ,  Jong-Chan Park

IPC: B60W40/06 ,  B60W40/068 ,  G01S15/88 ,  G06F18/213 ,  G06F18/2415 ,  G06V10/82 ,  G06V20/56

CPC classification number: B60W40/068 ,  G01S15/88 ,  G06F18/213 ,  G06F18/2415 ,  G06V10/82 ,  G06V20/56

Abstract: The present invention relates to a method and apparatus for estimating a road surface type by using an ultrasonic signal and, more particularly, to a method for estimating a road surface type by using an artificial neural network model machine-learned with respect to a reflected ultrasonic signal and an apparatus for performing same. According to the present invention, provided are a method and apparatus for providing highly accurate road surface information at low cost, by machine-learning both characteristics of an ultrasonic signal reflected from a road surface and a road surface state, establishing a model between the two, and then estimating the type of the road surface by utilizing the model. In particular, even a road surface where thin ice, that is, black ice, is formed, which was not detectable in the conventional method for estimating a road-surface friction coefficient, may be accurately estimated, thereby contributing to safer driving.

公开(公告)号：US20210182632A1

公开(公告)日：2021-06-17

申请号：US17186329

申请日：2021-02-26

Applicant: Korea Advanced Institute of Science and Technology

Inventor： Sei-Bum CHOI ,  Min-Hyun Kim ,  Jin-Rak Park ,  Seung-In Shin ,  Jong-Chan Park

IPC: G06K9/62 ,  G06N3/08 ,  G01S15/88

Abstract: The present invention relates to a method and apparatus for estimating a road surface type by using an ultrasonic signal and, more particularly, to a method for estimating a road surface type by using an artificial neural network model machine-learned with respect to a reflected ultrasonic signal and an apparatus for performing same. According to the present invention, provided are a method and apparatus for providing highly accurate road surface information at low cost, by machine-learning both characteristics of an ultrasonic signal reflected from a road surface and a road surface state, establishing a model between the two, and then estimating the type of the road surface by utilizing the model. In particular, even a road surface where thin ice, that is, black ice, is formed, which was not detectable in the conventional method for estimating a road-surface friction coefficient, may be accurately estimated, thereby contributing to safer driving.