发明名称 Apparatus and method for creating panorama
摘要 An apparatus for creating a panorama is provided, the apparatus including an image obtainer to obtain at least two images via at least two cameras, an overlapping area analyzer to analyze an overlapping area among the at least two cameras, and extract overlapping image information, an image segmentation unit to segment the at least two images in an object unit, and generate image segmentation information, a depth value extractor to extract a depth value of an object in the at least two images, an image focus setter to set a focus value based on the depth value for the plurality of segmented objects, and a panorama creator to create panorama content of which a focus is convertible using the image segmentation information and the focus value.
申请公布号 US9584723(B2) 申请公布日期 2017.02.28
申请号 US201414156950 申请日期 2014.01.16
申请人 Electronics and Telecommunications Research Institute 发明人 Ki Myung Seok;Yoo Ji Sung;Kim Seong Dae
分类号 H04N7/00;H04N5/232 主分类号 H04N7/00
代理机构 William Park & Associates Ltd. 代理人 William Park & Associates Ltd.
主权项 1. An apparatus for creating a panorama, the apparatus comprising: an image obtainer to obtain at least two images via at least two cameras; an overlapping area analyzer to analyze an overlapping area among the at least two cameras, and extract overlapping image information; an image segmentation unit to segment the at least two images into an object unit, and generate image segmentation information; a depth value extractor to extract a depth value of an object in the at least two images; an image focus setter to set a focus value based on the depth value for the plurality of segmented objects; and a panorama creator to create panorama content of which a focus is convertible using the overlapping image information, the image segmentation information, and the focus value, wherein the focus is convertible for a plurality of objects based on a user zooming in or zooming out, and wherein a virtual location of the user is calculated based on a zooming-in/out factor when a zooming-in/out viewpoint of the user moves.
地址 Daejeon KR