Method of Processing Moving Picture and Apparatus Thereof

Abstract

A method of processing moving picture and an apparatus thereof are disclosed. A method of processing a moving picture comprising: calculating a color distribution vector for each of plural sub-frames which are generated by dividing a frame of the moving picture; generating a first order differential of the color distribution vector based on the color distribution vector; generating a second order differential of the color distribution vector based on the first order differential of the color distribution vector; and generating a feature vector of the frame based on the color distribution vector, the first order differential of the color distribution vector and the second order differential of the color distribution vector, is provided. The moving picture processing method can provide an efficient mean to determine commonality between moving pictures by extracting a feature from a frame of the moving pictures.

What is claimed is: 
     
         1 . A method of processing a moving picture on an apparatus including at least one computer processor for executing commands that direct operations of the apparatus and a memory operatively coupled to the at least one processor, the memory storing code operable when executed with the at least one processor, the method comprising:
 calculating a color distribution vector for each of a plurality of sub-frames generated by dividing a frame of the moving picture;   generating a first order differential of the color distribution vector based on the color distribution vector;   generating a second order differential of the color distribution vector based on the first order differential of the color distribution vector; and generating a feature vector of the frame based on the color distribution vector, the first order differential of the color distribution vector and the second order differential of the color distribution vector.   
     
     
         2 . The method of  claim 1 , wherein the generating of a frame feature vector comprises selecting a plurality of components, as components of the frame feature vector, from a set consisting of components of the color distribution vector, the first order differential of the color distribution vector and the second order differential of the color distribution vector. 
     
     
         3 . The method of  claim 1 , wherein the calculating of the color distribution vector comprises calculating an average color vector of the sub-frame by averaging color vectors of pixels of the sub-frame. 
     
     
         4 . The method of  claim 1 , wherein the color distribution vector is expressed using at least one selected from the group consisting of RGB, YUV and CYMK coordinate systems. 
     
     
         5 . The method of  claim 3 , wherein the calculating of the color distribution vector comprises normalizing the average color vector of the sub-frame, and
 the normalizing of the average color vector utilizes at least one selected from the group consisting of a minimum vector and an average vector of average color vectors of the plurality of sub-frames belonging to a time section including the sub-frame and corresponding to a same display area as the sub-frame in the moving picture.   
     
     
         6 . A method of processing a moving picture on an apparatus including at least one computer processor for executing commands that direct operations of the apparatus and a memory operatively coupled to the at least one processor, the memory storing code operable when executed with the at least one processor, the method comprising:
 generating a frame feature vector for each of a first moving picture and a second moving picture; and   detecting a common section of the first moving picture and the second moving picture by comparing the frame feature vector of the first moving picture with the frame feature vector of the second moving picture,   wherein the detecting of the common section comprises comparing moving picture segments by generating commonality evaluation value of a first moving picture segment and a second moving picture segment by comparing feature vectors of p frames of the first moving picture segment of the first moving picture with feature vectors, corresponding arrangement to an arrangement of the p frames of the first moving picture segment, of p frames of the second moving picture segment of the second moving picture, p being a natural number of greater than or equal to 1.   
     
     
         7 . The method of  claim 6 , wherein the commonality evaluation value is calculated based on a distance between the feature vector of the first moving picture segment and the corresponding feature vector of the second moving picture segment. 
     
     
         8 . The method of  claim 6 , wherein the distance between the feature vector of the first moving picture segment and the feature vector of the second moving picture segment is defined based on at least one of an L1 norm, an L2 norm, an L1 norm with a limited maximum value and an L1 norm with a threshold function, and
 the commonality evaluation value is generated based on a sum of distances of p vector pairs between the first moving picture segment and the second moving picture segment.   
     
     
         9 . A method of processing a moving picture on an apparatus including at least one computer processor for executing commands that direct operations of the apparatus and a memory operatively coupled to the at least one processor, the memory storing code operable when executed with the at least one processor, the method comprising:
 generating a feature vector for a first moving picture and a second moving picture, respectively;   detecting a common section in the two moving pictures by comparing a feature vector of the first moving picture and a feature vector of the second moving picture; and   manipulating a moving picture cluster identifier by matching cluster identifiers of the first moving picture and the second moving picture, such that the first moving picture and the second moving picture have a same cluster identifier, in case, in the detecting of common section, a common section is detected in the first moving picture and the second moving picture, and   replacing a cluster identifier, in case an old cluster identifier of any moving picture of the two moving pictures is replaced with a new cluster identifier during the matching of cluster identifiers, for another moving picture which has the old cluster identifier with the new cluster identifier.   
     
     
         10 . The method of  claim 9 , further comprising:
 generating a feature vector for a third moving picture;   generating a text token for the first to third moving picture respectively; and   detecting a common section in the first moving picture and the third moving picture by comparing the feature vector of the first moving picture with the feature vector of the third moving picture,   wherein, in case there is a text token shared by the first moving picture and the second moving picture and no text token shared by the first moving picture and the third moving picture, detecting a common section in the first moving picture and the second moving picture precedes detecting a common section in the first moving picture and the third moving picture.   
     
     
         11 . The method of  claim 10 , wherein the text token is obtained based on at least one of title information, file name information, tag information and URL information of the first to third moving picture, respectively. 
     
     
         12 . The method of  claim 9 , further comprising, for a plurality of moving pictures in a single cluster, converting time information of the plurality of moving pictures to a time axis, the time axis being commonly applied for the plurality of moving pictures. 
     
     
         13 . The method of  claim 9 , further comprising determining a representative moving picture among a plurality of moving pictures in a single cluster,
 wherein the representative moving picture a longest moving picture among the plurality of moving pictures in the single cluster.   
     
     
         14 . A non-transitory recorded medium having recorded a program for executing a method of any of  claims 1  to  13 , the recorded medium being readable by a computer. 
     
     
         15 . An apparatus of processing a moving picture, comprising:
 a feature vector generating part generating a feature vector for each of a first moving picture and a second moving picture; and   a common section detecting part detecting a common section in the first moving picture and the second moving picture by comparing the feature vector of the first moving picture with the feature vector of the second moving picture,   wherein the feature vector generating part calculating a color distribution vector for each of a plurality of sub-frames generated by dividing a frame of the moving picture and generating a feature vector based on the color distribution vector, a first order differential of the color distribution vector and a second order differential of the color distribution vector.   
     
     
         16 . The apparatus of  claim 15 , wherein the feature vector generating part selects a plurality of components, as components of the frame feature vector, from a set consisting of components of the color distribution vector, the first order differential of the color distribution vector and the second order differential of the color distribution vector. 
     
     
         17 . An apparatus of processing a moving picture, comprising:
 a feature vector generating part generating a feature vector for each of a first moving picture and a second moving picture; and   a common section detecting part detecting a common section in the first moving picture and the second moving picture by comparing a feature vector of the first moving picture with a feature vector of the second moving picture; and   a moving picture clustering part matching cluster identifiers of the first moving picture and the second moving picture, such that the first moving picture and the second moving picture have a same cluster identifier, in case, in the detecting of common section, a common section is detected in the first moving picture and the second moving picture, and replacing a cluster identifier, in case an old cluster identifier of any moving picture of the two moving pictures is replaced with a new cluster identifier during the matching of cluster identifiers, for another moving picture which has the old cluster identifier with the new cluster identifier.   
     
     
         18 . The apparatus of  claim 17 , wherein the feature vector generating part generates a feature vector for a third moving picture, and
 further comprising a text token generating part which generates a text token for the first to third moving pictures, respectively,   wherein, there is a text token shared by the first moving picture and the second moving picture and no text token shared by the first moving picture and the third moving picture, the common section detecting part performs detecting a common section of the first moving picture and the second moving picture preliminarily to detecting a common section of the first moving picture and the third moving picture.