Automatically authoring video compositions using video cliplets

Abstract

A system and a method for automatically authoring video compositions from longer units of digitized video (or a source video) by using short segments of video (or video “cliplets”). The video composition authoring process provides an aesthetically-pleasing layout of data elements to create a video composition. The data elements include multimedia elements, parameter information and description information. Any data elements that are missing but required are automatically selected by the system. The user may then review preliminary video composition results and refine the results if desired. The video composition authoring system includes an element selection and layout module for selecting the data elements in the video composition, and an iterative refinement module that allows the user to change and refine the preliminary results.

1 . A method for authoring a video composition from source video, comprising: 
 inputting a set of data elements that includes video;    determining required data elements needed to author the video composition;    automatically selecting any of the required data elements that have not been previously determined;    using the required data elements to generate preliminary video composition results; and    presenting the preliminary video composition results to a user to allow user refinement of the preliminary video composition results to produce the video composition.    
   
   
       2 . The method of  claim 1 , further comprising determining whether the user wants to select any of the required data elements and, if so, allowing the user to select any of the required data elements.  
   
   
       3 . The method of  claim 1 , further comprising allowing a user to specify a layout of the required data elements within the video composition.  
   
   
       4 . The method of  claim 3 , further comprising: 
 determining that the user has not specified layout information for each required data element; and    automatically specifying the layout information not specified by the user.    
   
   
       5 . The method of  claim 1 , wherein the video includes a set of cliplets and wherein automatically selecting any of the required elements further comprises selecting at least some of the set of cliplets for the video composition based on cliplet interest ratings.  
   
   
       6 . The method of  claim 5 , wherein cliplet interest ratings include at least one of the following: (a) voice recognition; (b) speaker recognition; (c) face detection; (d) zoom detection; (e) pan detection; (f) any type of audio analyses; (g) any type of audio recognition; (h) any type of video analyses; (i) any type of video recognition.  
   
   
       7 . The method of  claim 6 , wherein the cliplet interest ratings are correlated with cliplet usage statistics.  
   
   
       8 . A method for authoring a video composition from source video using short segments of the source video called video cliplets, comprising: 
 generating a set of windows to be contained within the video composition;    automatically selecting a cliplet to be placed within each window of the set of windows so as to create the video composition based on multi-dimensional cliplet interest ratings associated with the cliplet;    presenting the video composition to a user for review;    allowing the user to change the cliplets within each of the windows if the user if not satisfied with the video composition after the review; and    allowing a user to choose an output style of the video composition.    
   
   
       9 . The method of  claim 8 , wherein automatically selecting a cliplet further comprises correlating usage statistics with the cliplet interest ratings to increase the accuracy of the cliplet interest ratings.  
   
   
       10 . The method of  claim 8 , wherein automatically selecting a cliplet further comprises: 
 defining cliplet interest rating categories;    ranking each of the cliplets in each of the cliplet interest rating categories; and    selecting the top-ranked cliplets in each of the cliplet interest rating categories to be placed in each of the windows.    
   
   
       11 . The method of  claim 10 , further comprising: 
 determining whether any of the top-ranked cliplets in each of the cliplet interest rating categories are close in time; and    if so, then choosing one of the top-ranked cliplets that are close in time and discarding the other ones of the top-ranked cliplets that are close in time.    
   
   
       12 . The method of  claim 8 , wherein automatically selecting a cliplet further comprises: 
 defining cliplet interest rating categories;    defining a set of M number of cliplets within each of the cliplet interest rating categories; and    randomly selecting for each of the cliplet interest rating categories a set of N number of cliplets from the set of M number of cliplets, where M is greater than N.    
   
   
       13 . The method of  claim 8 , wherein allowing the user to change the cliplets within each of the windows further comprises providing drag and drop functionality such that using an input device a user can perform at least one of the following in the video composition: (a) change a location of a cliplet; (b) modify the cliplet; (c) add a cliplet; (d) delete a cliplet.  
   
   
       14 . The method of  claim 8 , further comprising allowing the user to add text annotation to any of the cliplets.  
   
   
       15 . The method of  claim 8 , further comprising allowing a user to add text annotation to the video composition.  
   
   
       16 . The method of  claim 8 , further comprising allowing a user to add at least one of the following to the video composition: (a) a title for the video composition; (b) a credits list.  
   
   
       17 . A computer-readable medium having computer-executable instructions for authoring and generating a video composition using video cliplets generated from digitized video, comprising: 
 creating a layout of the video composition as a two-dimensional collage of cliplet windows;    allowing a user to select video cliplets to place in the cliplet windows; and    automatically selecting video cliplets to place in the cliplet windows if the user does not select enough video cliplets to fill each of the cliplet windows.    
   
   
       18 . The computer-readable medium of  claim 17 , wherein creating a layout of the video composition further comprises automatically determining a layout of the two-dimensional collage of cliplets windows.  
   
   
       19 . The computer-readable medium of  claim 17 , wherein creating a layout of the video composition further comprises allowing a user to determine a layout of the two-dimensional collage of cliplets windows.  
   
   
       20 . The computer-readable medium of  claim 17 , further comprising allowing the user to review the video composition and change the video composition if the user desires.