메뉴 건너뛰기
.. 내서재 .. 알림
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)
로그인 회원가입 고객센터 ENG
주제분류

추천
검색
질문

논문 기본 정보

자료유형
학술저널
저자정보
이재설 (충북대학교) 최경택 (한국교통대학교) 박태형 (충북대학교) 기석철 (충북대학교)
저널정보
한국자동차공학회 한국자동차공학회논문집 한국자동차공학회논문집 제26권 제3호
발행연도
2018.5
수록면
368 - 377 (10page)
DOI
10.7467/KSAE.2018.26.3.368

이용수

표지
📌
연구주제
📖
연구배경
🔬
연구방법
🏆
연구결과
AI에게 요청하기
추천
검색
질문

초록· 키워드

오류제보하기
In this paper, we proposed a method to detect and track vehicles efficiently under the AVM camera environment, which was characterized by a wide viewing angle and serious lens distortion. The algorithm was designed for the FVSA(Forward Vehicle Start Alarm) function, a newly required ADAS function. We created independent nearby and distant detectors to compensate for the massive appearance variation of a vehicle because of distance between the target vehicle and the camera. The proposed detectors were designed with Haar-Like Adaboost and tested against independent nearby and distant data. To reduce false positive among the candidates caught by the detector, a pre-generated mask was used in filtering. Next, the candidate vehicle was verified with nearby and distant classifiers. The classifier was a tested HOG(Histogram of Oriented Gradients) feature of SVM(Support Vector Machine). Tracking is then used to extract a particular car within a video, and if nearby and distant candidates were extracted at the same time, a correct candidate would be created by a Selection and Merge process through a calculated IOU value. To evaluate the performance of the proposed algorithm, we selected 20 test videos from 130 videos of actual road conditions, and extracted 1,640 frames.

목차

Abstract
1. 서론
2. 전방 차량 탐색 방법
3. 실험 결과
4. 결론
References

참고문헌 (19)

참고문헌 신청

함께 읽어보면 좋을 논문

논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!

이 논문의 저자 정보

이 논문과 함께 이용한 논문

최근 본 자료

전체보기

댓글(0)

0