发明名称 Augmented reality navigation for repeat photography and difference extraction
摘要 Systems and methods for repeat photography and difference extraction that help users take pictures from the same position and camera angle as earlier photos. The system automatically extracts differences between the photos. Camera poses are estimated and then indicators are rendered to show the desired camera angle, which guide the user to the same camera angle for repeat photography. Using 3D rendering techniques, photos are virtually projected onto a 3D model to adjust them and improve the match between the photos, and the difference between the two photos are detected and highlighted. Highlighting the detected differences helps users to notice the differences.
申请公布号 US8803992(B2) 申请公布日期 2014.08.12
申请号 US201012779021 申请日期 2010.05.12
申请人 Fuji Xerox Co., Ltd. 发明人 Shingu Jun;Kimber Donald;Rieffel Eleanor;Vaughan James;Tuite Kathleen
分类号 H04N5/228 主分类号 H04N5/228
代理机构 Sughrue Mion, PLLC 代理人 Sughrue Mion, PLLC
主权项 1. A system, comprising: a camera receiving live feed; a database of pictures; a determining unit determining an angle and a position associated with an object to be captured, wherein the determining unit determines a plurality of angles and a position associated with the live feed relative to the object to be captured; a guiding unit providing a first indication being overlaid onto the live feed and displayed on a display device to indicate the angle associated with the object to be captured relative to the live feed, and providing a second indication being overlaid onto the live feed and displayed on the display device to indicate the position of the object to be captured relative to the live feed, and wherein a third indication is provided if at least one angle in the plurality of angles and the position associated with the live feed is within a specified tolerance to the angle and position of the object to be captured; wherein said first and second indications are simultaneously overlaid onto the live feed, wherein the first indication is represented by a cone, wherein a vertex of the cone is located at the object and an axis of the cone is extended in a camera-to-object direction, and a vertex angle formed between the vertex and the axis indicates an amount of difference between the live feed and the object that is acceptable.
地址 Tokyo JP