지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학술대회자료
- 저자정보
- 발행연도
- 2011.11
- 수록면
- 1,600 - 1,604 (5page)
이용수
초록· 키워드
오류제보하기
Detecting changes in the environment while driving is critical in any vision based driving assistance system. These environmental changes have to be handled separately to enhance ADAS (advanced driver assistance system) performance. In particular, this paper focuses on detecting tunnel using a simple and computationally efficient approach. Conventional tunnel detection approaches use tunnel entry and exit information for its recognition. These approaches fail for different tunnel cases and during night condition. In this paper, we propose tunnel recognition algorithm using the pattern of lights available inside the tunnel. The first order line fitting algorithm is used to track the tunnel lights, which almost follow straight lines. The magnitude of error in line fitting decides whether the image has a tunnel or not. It has been observed that the intensity inside the tunnel is less compared to outside environment during day condition. Using this criterion, brightness parameter is calculated to avoid unnecessary processing of normal day image. The proposed algorithm has been tested on both day and night images captured from grayscale monocular camera mounted on the ego vehicle.
목차
Abstract
1. INTRODUCTION
2. FIRST ORDER LINE FITTING
3. SYSTEM OVERVIEW
4. PROPOSED ALGORITHM
5. EXPERIMENTAL 5. EXPER
6. CONCLUSION
7. REFERENCE
참고문헌 (0)
참고문헌 신청이 논문의 저자 정보
최근 본 자료
댓글(0)
0
UCI(KEPA) : I410-ECN-0101-2013-556-001415025