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

Pothole Detection Based on Convolutional Neural Network Using Computer Vision

논문 기본 정보

저자정보
(Kumoh National Institute of Technology) (Kumoh National Institute of Technology)
저널정보
한국통신학회 한국통신학회 학술대회논문집 2020년도 한국통신학회 동계종합학술발표회 논문집
발행연도
수록면
1,264 - 1,267 (4page)
오류 신고하기

피인용 0

Pothole Detection Based on Convolutional Neural Network Using Computer Vision
검색

    초록·키워드

    Computer Vision-Based Potholes detection implementation for vehicles to detect Potholes in Real-time for driver assistance to avoid accidents is presented. The model is trained on YOLO (You only look once) object detection system to detect the Potholes on road. The collection of data set is a difficult and extensive task which required different angles images with proper resolution. Implementation of YOLOv3 Tiny for pothole detection is done on modified data set for Pothole detection in real-time and the performance of the model is benchmarked with respect to accuracy and mean average precision (MAP). Keywords- Pothole Detection, Object Detection, Computer Vision, Deep Learning.

    최근 본 자료 전체보기