-
公开(公告)号:US09858297B2
公开(公告)日:2018-01-02
申请号:US14340114
申请日:2014-07-24
发明人: Dong Jun Park , Yeon Geol Ryu , Hak Chul Shin , Dong Whan Jung
IPC分类号: G06F17/30
CPC分类号: G06F17/3028
摘要: Provided are a system for search and a method for operating thereof. The system for search includes: a preliminary data analysis part which extracts a variety of attributes through analysis of images being input, analyzes a trend about a category as information requested by a client with the image analysis result, and stores the trend analysis result as metadata; an index part which stores the image analysis result, and structuralizes, organizes and stores the stored metadata in order to easily search the metadata; and a search part which extracts trend information matching a category input by a client, from the index part and provides the trend information in a predetermined format.
-
公开(公告)号:US09870518B2
公开(公告)日:2018-01-16
申请号:US15024188
申请日:2014-03-25
发明人: Dong Jun Park , Hak Chul Shin , Yeon Geol Ryu
CPC分类号: G06K9/6232 , G06F17/30247 , G06F17/30265 , G06K9/00771 , G06K9/46 , G06K9/6253
摘要: Provided is a data processing system providing various user interfaces to users by analyzing and processing data collected via various routes, by using a parallel and distributive manner based on the assumption that generation, analysis, storage, and consumption of data is performed at various locations.
-
公开(公告)号:US09286693B2
公开(公告)日:2016-03-15
申请号:US14161890
申请日:2014-01-23
发明人: Young Joon Yoo , Ha Wook Jeong , Kwang Moo Yi , Jin Young Choi , Dong Jun Park , Jeong Eun Lim
CPC分类号: G06T7/2033 , G06K9/00771 , G06K9/00785 , G06K9/62 , G06K9/6226 , G06K9/6297 , G06T7/246 , G06T2207/10016 , G06T2207/20076 , G06T2207/20081 , G06T2207/30241
摘要: Provided are a method and apparatus for detecting an abnormal movement. The apparatus includes a feature tracing unit configured to extract features of a moving object in an input image, trace a variation in position of the extracted features according to time, and ascertain trajectories of the extracted features; a topic online learning unit configured to classify the input image in units of documents which are bundles of the trajectories, and ascertain probability distribution states of topics, which constitute the classified document, by using an online learning method which is a probabilistic topic model; and a movement pattern online learning unit configured to learn a velocity and a direction for each of the ascertained topics, and learn a movement pattern by inferring a spatiotemporal correlation between the ascertained topics.
摘要翻译: 提供了用于检测异常运动的方法和装置。 该装置包括:特征追踪单元,被配置为提取输入图像中的移动物体的特征,根据时间跟踪提取的特征的位置变化,并确定提取的特征的轨迹; 主题在线学习单元,其被配置为通过使用作为概率主题模型的在线学习方法,以构成所述分类文档的主题的主题的概率分布状态来确定输入图像的单位,并且确定所述主题的概率分布状态; 以及运动模式在线学习单元,被配置为学习每个所确定的主题的速度和方向,并且通过推断确定的主题之间的时空相关性来学习运动模式。
-
公开(公告)号:US10032483B2
公开(公告)日:2018-07-24
申请号:US15107011
申请日:2014-03-26
发明人: Yeon Geol Ryu , Dong Jun Park , Hak Chul Shin
IPC分类号: G11B27/031 , H04N21/8549 , G06T11/60 , G06F3/0481
摘要: An embodiment of the present invention provides a summary image browsing system and method. A summary image browsing method of the present invention may comprise the steps of: tracking motion trajectory of an object from an input video; extracting the object from the input video and then generating a series of object segments; and synthesizing the series of object segments with a background image along the motion trajectory of the object and generating a summary image having a thickness according to an occurrence time interval for each object extracted from the input video.
-
公开(公告)号:US09792362B2
公开(公告)日:2017-10-17
申请号:US14468532
申请日:2014-08-26
发明人: Dong Jun Park , Jeong Eun Lim , Ho Jung Lee
IPC分类号: G06F17/30
CPC分类号: G06F17/30837 , G06F17/3079
摘要: Provided is a video search system and method. The video search system includes: a search engine configured to extract video data matching a search condition from an original video; and a browsing engine configured to generate a summarized video based on the extracted video data, render a plurality of objects in the summarized video on a background model in an overlapping manner in an object appearing order in the original video, and display the rendered objects.
-
-
-
-