Generating a composite image from video frames

Abstract

A method described herein includes acts of receiving a sequence of images of a scene and receiving an indication of a reference image in the sequence of images. The method further includes an act of automatically assigning one or more weights independently to each pixel in each image in the sequence of images of the scene. Additionally, the method includes an act of automatically generating a composite image based at least in part upon the one or more weights assigned to each pixel in each image in the sequence of images of the scene.

1 - 20 . (canceled) 
     
     
         21 . A mobile computing device comprising:
 a processor;   a camera; and   a memory that comprises a plurality of components that are executed by the processor, the plurality of components comprising:
 a weight assignor component that is configured to detect an object in frames of video captured by the camera; and 
 an image generator component that generates a composite image based upon the weight assignor component detecting the object in the frames of the video, the composite image comprising:
 the object as captured in one frame in the frames; and 
 the object as captured in another frame in the frames. 
 
   
     
     
         22 . The mobile computing device of  claim 21  being a mobile telephone. 
     
     
         23 . The mobile computing device of  claim 21 , the weight assignor component is further configured to assign weights to pixels in the frames of the video captured by the camera, the weight assignor component configured to detect the object in the frames based upon the weights assigned to the pixels. 
     
     
         24 . The mobile computing device of  claim 23 , the weights based upon saliency values assigned to the pixels in the frames of the video, the saliency values indicative of importance of preserving the pixels in the composite image. 
     
     
         25 . The mobile computing device of  claim 23 , the weights based upon flow confidence values assigned to the pixels in the frames of the video, the flow confidence values indicative of pixels between frames align with one another. 
     
     
         26 . The mobile computing device of  21 , the composite image depicts motion of the object across the frames of the video. 
     
     
         27 . The mobile computing device of  claim 21 , the composite image has a resolution that is greater than a resolution of either the one frame or the another frame. 
     
     
         28 . The mobile computing device of  claim 21 , the plurality of components further comprising a reference frame selector component that is configured to select a reference frame in the frames of the video, the image generator component configured to generate the composite image based upon the reference frame. 
     
     
         29 . The mobile computing device of  claim 28 , the plurality of components further comprising an alignment component that is configured to perform a global alignment on the frames of the video based upon the reference frame selected by the reference frame selector component, the global alignment stabilizes the frames with respect to motion of the camera when the frames are being captures. 
     
     
         30 . The mobile computing device of  claim 28 , the plurality of components further comprising an alignment component that is configured to perform local alignments of objects in the frames of the video, the alignment component detects that the object is moving across the frames of the video based upon the local alignments. 
     
     
         31 . The mobile computing device of  21 , the plurality of components further comprises a sharpness detector component that is configured to identify a frame in the frames that is heavily blurred, the sharpness detector component discards the frame that is heavily blurred such that the image generator component fails to consider the frame that is heavily blurred when generating the composite image. 
     
     
         32 . The mobile computing device of  claim 21 , the plurality of components further comprises a frame analyzer component that is configured to automatically determine that the composite image is to be generated rather than a panoramic image based upon misalignment between the frames of the video. 
     
     
         33 . A method executed by a mobile computing device, the method comprising:
 receiving a video of a scene, the video comprises frames;   detecting a moving object in the frames of the video; and   generating a composite image based upon the detecting of the moving object in the frames of the video, the composite image comprises:
 the moving object captured in one frame in the frames; and 
 the moving object captured in another frame in the frames. 
   
     
     
         34 . The method of  claim 33 , the composite image depicts motion of the moving object across the frames of the video. 
     
     
         35 . The method of  claim 33 , the composite image being a still image. 
     
     
         36 . The method of  claim 33 , the mobile computing device being a mobile telephone. 
     
     
         37 . The method of  claim 33 , further comprising:
 selecting a reference frame from the frames; and   generating the composite image based upon the selecting of the reference frame.   
     
     
         38 . The method of  claim 37 , wherein generating the composite image based upon the selection of the reference frame comprises:
 correcting for motion of a camera that captures the video based upon the reference frame.   
     
     
         39 . The method of  claim 33 , wherein generating the composite image comprises:
 assigning values to pixels in the frames of the video, the values indicative of importance of preserving the pixels in the composite image; and   generating the composite image based upon the values assigned to the pixels.   
     
     
         40 . A computer-readable data storage device comprising instructions that, when executed by a processor, cause the processor to perform acts comprising:
 receiving a video captured by a camera, the video comprises a frame that comprises an object at a first location and another frame that comprises the object at a second location; and   generating a composite image responsive to receiving the video, the composite image comprises the object at the first location and the object at the second location.