2019년 컴퓨터종합학술대회
Current Result Document :
| 한글제목(Korean Title) |
지능형 비디오 감시를 위한 온톨로지 기반의 고차원 컨텍스트 추론 기법 |
| 영문제목(English Title) |
Higher-Level Context Inferences based on Ontology For Intelligent Video Surveillance |
| 저자(Author) |
Aftab Alam
Jawad Khan
MD Azher Uddin
Muhammad Numan Khan
Irfan Ullah
YoungKoo Lee
|
| 원문수록처(Citation) |
VOL 46 NO. 01 PP. 0984 ~ 0986 (2019. 06) |
한글내용
(Korean Abstract) |
|
영문내용
(English Abstract) |
There is increasing reliance on the intelligent CCTV systems for effective analysis and interpretation of the streaming data with the intentions to recognize activities and to ensure public safety. Monitoring videos captured by surveillance cameras is always a difficult and time-consuming task. There is a need for automated analysis using computer vision methods in order to recognize/predict abnormal activities and assist authorities. Once, videos are processed using computer vision technologies; another problem is how this data is indexed for search, analysis, and real-time alerts since a large number of cameras continuously capture videos resulting vast amounts of data. In order to address this issue, in this paper, we propose a generic architecture for distributed intelligent surveillance and is composed of four layers. The first layer acquisition large number of the video streams from for device independent video stream data sources. In the second layer, we use computer vision algorithms for semantic video annotation while exploiting the distributed in-memory computing engine. The third layer is used to persist the video stream and the to manage the intermediate results being produced by the second layer. Finally, the intermediate results are mapped to the RDF according to domainspecific application. |
| 키워드(Keyword) |
|
| 파일첨부 |
PDF 다운로드
|
