发明名称 Placing unobtrusive overlays in video content
摘要 Methods and systems for placing an overlay in video content are provided. A method receives video content and input indicating an overlay to be placed in the video. The method determines, based on overlay and video properties, locations where the overlay can be placed. The method presents suggested locations for the overlay and receives a selection of a suggested location. The overlay is placed in the selected location. A system includes memory with instructions for inserting an overlay into video content. The system receives an indication of an overlay to be placed in the video, performs attention modeling on the video to identify zones likely to be of interest to a viewer. The system presents locations within the identified zones where the overlay can be inserted and receives a selection of a location. The system inserts the overlay into the selected location and renders the video with the inserted overlay.
申请公布号 US9467750(B2) 申请公布日期 2016.10.11
申请号 US201313906838 申请日期 2013.05.31
申请人 Adobe Systems Incorporated 发明人 Banica Dan;Cucu Andrian;Chirita Paul-Alexandru
分类号 H04N21/81;H04N21/234;H04N21/8545;H04N21/44;H04N21/23;H04N21/85;H04N21/2547;H04N21/431 主分类号 H04N21/81
代理机构 Kilpatrick Townsend & Stockton LLP 代理人 Kilpatrick Townsend & Stockton LLP
主权项 1. A computer-implemented method for placing an overlay in video content, the method comprising: receiving, at an overlay server, video content; receiving, at the overlay server, an indication of an overlay to be placed in the received video content, the overlay being an item of electronic content including one or more of text, image, and multimedia content; generating, by an attention modeling module of the overlay server, saliency maps indicating relative salience of regions within frames of the video content based upon feature values in a region differing from other feature values in regions adjacent to the region; computing an auxiliary matrix by cumulating saliency values from the saliency maps; identifying, based on the saliency maps and the properties of the overlay, a plurality of unobtrusive locations where the overlay can be placed within the frames of the video content, wherein the unobtrusive locations are in lower salience regions; calculating unobtrusiveness values of the plurality of unobtrusive locations, the calculating being based at least in part on the auxiliary matrix; determining, by the overlay server, based on properties of the overlay, the unobtrusiveness values, and properties of the video content, an optimal location from amongst the plurality of unobtrusive locations where the overlay can be placed within the video content; and placing the overlay in the optimal location.
地址 San Jose CA US