메뉴 건너뛰기
소속 기관 / 학교 인증
인증하면 논문, 학술자료 등을  무료로 열람할 수 있어요.
한국대학교, 누리자동차, 시립도서관 등 나의 기관을 확인해보세요
(국내 대학 90% 이상 구독 중)
고객센터 ENG
주제분류

논문 기본 정보

저자정보
(인피닉) (인피닉) (인피닉) (인피닉)
저널정보
한국자동차공학회 한국자동차공학회논문집 한국자동차공학회논문집 제31권 제4호
오류 신고하기

피인용 1

검색

    초록·키워드

    The purpose of this paper is to propose the 2D/3D semantic segmentation based on the sensor fusion method using camera and LiDAR sensors to improve the safety of autonomous driving in the actual driving environment. To implement the proposed method, a deep neural network for 2D semantic segmentation is utilized using convolution and transformer and inference strategy to convert predicted 2D segment to 3D coordinate information. Also, through the ablation study and performance evaluation, we present the performance of the proposed method and the validity of the neural network design. Results show the proposed method based on sensor fusion obtained 31.94 % on 2D MIoU, which is around twice the performance of a single modal scheme, and also obtained 17.12 % MIoU in the 3D environment.

    최근 본 자료 전체보기

      UCI(KEPA) : I410-ECN-0101-2023-556-001336926