Highlight Reels

Abstract

Techniques and apparatuses for generating highlight reels are described. These techniques and apparatuses enable a user to quickly and easily generate a highlight reel to highlight audiovisual media, such as photos and video clips.

What is claimed is: 
     
         1 . A method comprising:
 determining one or more persons to highlight in a highlight reel;   determining, based on faces of the one or more determined persons appearing in images or video clips and quality metric values of the images or the video clips, determined images or video clips by which to highlight the one or more persons; and   arranging the determined images or video clips into the highlight reel.   
     
     
         2 . The method as recited in  claim 1 , wherein determining the one or more persons to highlight is based on persons tagged or facially recognized within selected source media that includes the images or video clips. 
     
     
         3 . The method as recited in  claim 1 , wherein determining images or video clips is further based on contextual variety of the images or the video clips, the contextual variety sufficient to show the one or more persons in various different contextual environments or different events. 
     
     
         4 . The method as recited in  claim 1 , wherein determining images or video clips by which to highlight the one or more persons is based in part on a selected target duration for the highlight reel and wherein the method continues to determine images or video clips in a greedy manner until the selected target duration is met. 
     
     
         5 . The method as recited in  claim 1 , wherein the one or more persons includes two or more persons and wherein determining images or video clips by which to highlight the two or more persons is based on a weighting assigned to each of the two or more persons. 
     
     
         6 . The method as recited in  claim 1 , further comprising:
 receiving or determining, automatically and without user interaction, additional images or video clips;   determining, based on the additional images or video clips having faces of the one or more determined persons and quality metric values of the additional images or video clips, to include one or more of the additional images or video clips within the highlight reel; and   updating the highlight reel to include the one or more of the additional images or video clips.   
     
     
         7 . The method as recited in  claim 1 , further comprising determining the quality metric values of the images or the video clips. 
     
     
         8 . A system for generating a highlight reel comprising:
 one or more computer processors; and   one or more computer-readable storage media having instructions stored thereon that, responsive to execution by the one or more computer processors, perform operations comprising:
 determining one or more persons to highlight in the highlight reel; 
 determining, based on faces of the one or more determined persons appearing in images or video clips and quality metric values of the images or the video clips, determined images or video clips by which to highlight the one or more persons; and 
 arranging the determined images or video clips into the highlight reel. 
   
     
     
         9 . The system as recited in  claim 8 , wherein determining the one or more persons to highlight is based on persons tagged or facially recognized within selected source media that includes the images or video clips. 
     
     
         10 . The system as recited in  claim 8 , wherein determining images or video clips is further based on contextual variety of the images or the video clips, the contextual variety sufficient to show the one or more persons in various different contextual environments or different events. 
     
     
         11 . The system as recited in  claim 8 , wherein determining images or video clips by which to highlight the one or more persons is based in part on a selected target duration for the highlight reel and wherein the method continues to determine images or video clips in a greedy manner until the selected target duration is met. 
     
     
         12 . The system as recited in  claim 8 , wherein the one or more persons includes two or more persons and wherein determining images or video clips by which to highlight the two or more persons is based on a weighting assigned to each of the two or more persons. 
     
     
         13 . The system as recited in  claim 8 , wherein the operations further comprise:
 receiving or determining, automatically and without user interaction, additional images or video clips;   determining, based on the additional images or video clips having faces of the one or more determined persons and quality metric values of the additional images or video clips, to include one or more of the additional images or video clips within the highlight reel; and   updating the highlight reel to include the one or more of the additional images or video clips.   
     
     
         14 . The system as recited in  claim 8 , wherein the operations further comprise determining the quality metric values of the images or the video clips. 
     
     
         15 . A computing device comprising:
 one or more computer processors;   one or more computer-readable storage media having instructions stored thereon that, responsive to execution by the one or more computer processors, perform operations comprising:
 determining one or more persons to highlight in the highlight reel; 
 generating an interface, the interface configured to receive selection of at least one of the one or more determined persons; 
 receiving, via the interface, the selection of at least one of the one or more determined persons; 
 determining, based on faces of the one or more selected persons appearing in images or video clips and quality metric values of the images or the video clips, determined images or video clips by which to highlight the one or more selected persons; and 
 arranging the determined images or video clips into the highlight reel. 
   
     
     
         16 . The computing device as recited in  claim 15 , wherein determining the one or more persons to highlight is based on persons tagged or facially recognized within selected source media that includes the images or video clips. 
     
     
         17 . The computing device as recited in  claim 15 , wherein determining images or video clips is further based on contextual variety of the images or the video clips, the contextual variety sufficient to show the one or more selected persons in various different contextual environments or different events. 
     
     
         18 . The computing device as recited in  claim 15 , wherein determining images or video clips by which to highlight the one or more selected persons is based in part on a selected target duration for the highlight reel and wherein the method continues to determine images or video clips in a greedy manner until the selected target duration is met. 
     
     
         19 . The computing device as recited in  claim 15 , wherein the one or more selected persons includes two or more selected persons and wherein determining images or video clips by which to highlight the two or more selected persons is based on a weighting assigned to each of the two or more selected persons. 
     
     
         20 . The computing device as recited in  claim 15 , wherein the operations further comprise:
 receiving or determining, automatically and without user interaction, additional images or video clips;   determining, based on the additional images or video clips having faces of the one or more selected persons and quality metric values of the additional images or video clips, to include one or more of the additional images or video clips within the highlight reel; and   updating the highlight reel to include the one or more of the additional images or video clips.