상세정보
학술지
Horizon Detection in Maritime Images using Scene Parsing Network
- 발행일
- 201806
- 출처
- Electronics Letters, v.54 no.12, pp.760-762
- ISSN
- 0013-5194
- 출판사
- IET
- 협약과제
- 18PS1200, 자율운항 선박을 위한 운항관제 인공지능 시스템 원천기술 개발, 문경덕
- 초록
- A method for horizon detection in maritime scenes using a scene parsing network is proposed. First, each pixel from an input image is segmented into corresponding semantic categories using a scene parsing network, which relies on a deep neural network. Then, the boundary information related to the horizon and the sea is extracted. Scene segmentation allows the proposed method to identify the horizon, regardless of whether the boundary between the sea and sky is smooth or blurry, or whether the image contains many line elements like the horizon. Moreover, least squares and median filtering are iteratively used to retrieve an accurate estimation of the horizon line. Experimental results demonstrate the superior accuracy of the proposed method to identify the horizon when compared to state-of-the-art methods.
- KSP 제안 키워드
- Deep neural network(DNN), Least Squares(LS), Median Filtering, Scene Parsing, Scene Segmentation, Semantic categories, accurate estimation, boundary information, horizon detection, state-of-The-Art