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
- 2012.11
- 수록면
- 1,570 - 1,573 (4page)
이용수
초록· 키워드
오류제보하기
In this paper stationary and moving objects detection algorithm based on the Gabor filtering and Polar histogram is proposed. To generate the surround view, acquired images from four fisheye cameras that are mounted on the car are used. After generating surround view, object detection algorithm is applied to this view. The procedure of object detection algorithm is as follows. In the first step, Finding areas that are considered as object, Gabor filter is used. Differently from general view image, objects in surround view appears horizontally. Using this characteristic, Gabor filter is used in the direction of 0 degree only. After using Gabor filter, to increase the accuracy, Canny edge detection is used to eliminate false areas that are detected in the first step. The objects exist in surround view in the direction of the camera optical axis radiation. Using this characteristic, Polar histogram is extracted and bins that have high value than
threshold value are determined objects. The proposed algorithm have the recognition rate of 94% in the indoor and outdoor place videos with vehicle is stopped.
threshold value are determined objects. The proposed algorithm have the recognition rate of 94% in the indoor and outdoor place videos with vehicle is stopped.
목차
Abstract
1. 서론
2. 제안하는 방법
3. 실험 방법 및 결과
4. 결론
References
참고문헌 (0)
참고문헌 신청이 논문의 저자 정보
이 논문과 함께 이용한 논문
최근 본 자료
댓글(0)
0
UCI(KEPA) : I410-ECN-0101-2014-556-000410246