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
학술대회자료
저자정보
Kyung-tai Kim (Konkuk University) Yeounggwang Ji (Konkuk University) Eunjeong Ko (Konkuk University) Pyeoung-Kee Kim (Silla University) Eun Yi Kim (Konkuk University)
저널정보
한국산업정보학회 한국산업정보학회 학술대회논문집 2014 The International Industrial Information Systems Conference
발행연도
2014.1
수록면
181 - 184 (4page)

이용수

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

초록· 키워드

오류제보하기
Recently, we are developing a video-based traffic surveillance system (TSS). This system provides users with traffic information. Our TSS system consists of lane detection, vehicle detection and classification, and traffic parameter extraction. We use real-time streaming captured from CCTV camera locates at each road. The proposed system first finds lanes on the road using accumulated movements of the vehicles. Then, within road area, it detects vehicle regions among background and recognizes its type as one of five types: sedan, SUV, truck, bus and bike. Finally, traffic parameter is calculated and uploaded to database. Since road scenes are usually degraded, it makes difficult to estimate vehicle’s motion and background accurately.
In this paper, an effective video restoration algorithm is proposed. For higher quality of result a variety of features such as color, blurring, and noise are considered. Images are firstly enhanced using intensity normalization between two consecutive frames. In addition to remove the grain noise, we use the combined filter of Gaussian filter and median filter. The experimental results show that the proposed method is effective at removing the global noise in video and is applicable to the automatic vehicle extraction system.

목차

Abstract
Ⅰ. INTRODUCTION
Ⅱ. TRAFFIC SURVEILLANCE SYSTEM(TSS)
Ⅲ. EXPERIMENTAL RESULTS
Ⅳ. CONCLUSION
REFERENCES

참고문헌 (0)

참고문헌 신청

이 논문의 저자 정보

최근 본 자료

전체보기

댓글(0)

0

UCI(KEPA) : I410-ECN-0101-2016-530-000944789