Method, system and computer program product for interactively identifying same individuals or objects present in video recordings

Abstract

A method, system and computer program product for interactively identifying same individuals or objects present in video recordings is disclosed. When a thumbnail in a set of thumbnails is selected, new information is obtained. The new information may be that an individual or object is present in the portion of the video recording associated with the thumbnail. A search can be carried out for the individual or object based on the new information. The search generates new match likelihoods for each of displayed thumbnails within a user interface page. The displayed thumbnails are re-ordered based on the new match likelihoods.

1 . A method carried out in a surveillance system that includes at least one storage and a plurality of video cameras, the method comprising:
 capturing, using the plurality of video cameras, a plurality of video recordings;   storing, in the at least one storage, the plurality of video recordings that collectively include a plurality of video portions within which objects appear, wherein each of the video portions has a respective likelihood that an individual of interest appears therein;   determining that each of the likelihoods in respect of a first number of the plurality of video portions exceed a likelihood of appearance threshold, wherein the first number is less than all of the plurality of video portions; and   exporting the first number of the plurality of video portions, the exporting including back-to-back assembly of the first number of the plurality of video portions and subsequent storage thereof on another storage different than the at least one storage.   
     
     
         2 . The method as claimed in  claim 1  further comprising determining that each of the likelihoods in respect of a second number of the plurality of video portions are below the likelihood of appearance threshold. 
     
     
         3 . The method as claimed in  claim 2  wherein the first number of the plurality of video portions correspond to starred results and the second number of the plurality of video portions correspond to results that have not been starred. 
     
     
         4 . The method as claimed in  claim 1  wherein the likelihoods for the first number of the plurality of video portions are percentage likelihoods. 
     
     
         5 . The method as claimed in  claim 4  wherein the likelihoods for the first number of the plurality of video portions are each one hundred percent. 
     
     
         6 . The method as claimed in  claim 1  wherein the another storage comprises a hard disk on a computer terminal. 
     
     
         7 . The method as claimed in  claim 1  wherein the another storage comprises cloud storage. 
     
     
         8 . The method as claimed in  claim 1  further comprising providing a plurality of interface tools within a user interface page, and wherein the exporting is carried out after the providing of the interface tools. 
     
     
         9 . The method as claimed in  claim 8  wherein at least one of the interface tool allows adjustments of start and end times of the video portions being exported. 
     
     
         10 . A surveillance system comprising:
 a plurality of video cameras configured to capture a plurality of video recordings;   a server system configured to store the plurality of video recordings that collectively include a plurality of video portions within which objects appear, wherein each of the video portions has a respective likelihood that an individual of interest appears therein; and   at least one tangible, non-transitory, computer-readable storage medium having instructions encoded therein, wherein the instructions, when executed by at least one processor, cause a carrying out of a method comprising:
 determining that each of the likelihoods in respect of a first number of the plurality of video portions exceed a likelihood of appearance threshold, wherein the first number is less than all of the plurality of video portions; and 
 exporting the first number of the plurality of video portions, the exporting including back-to-back assembly of the first number of the plurality of video portions and subsequent storage thereof outside of the server system. 
   
     
     
         11 . The surveillance system as claimed in  claim 10  wherein the method further includes determining that each of the likelihoods in respect of a second number of the plurality of video portions are below the likelihood of appearance threshold. 
     
     
         12 . The surveillance system as claimed in  claim 11  wherein the first number of the plurality of video portions correspond to starred results and the second number of the plurality of video portions correspond to results that have not been starred. 
     
     
         13 . The surveillance system as claimed in  claim 10  wherein the likelihoods for the first number of the plurality of video portions are percentage likelihoods. 
     
     
         14 . The surveillance system as claimed in  claim 13  wherein the likelihoods for the first number of the plurality of video portions are each one hundred percent. 
     
     
         15 . The surveillance system as claimed in  claim 10  wherein the method further includes providing a plurality of interface tools within a user interface page, and wherein the exporting is carried out after the providing of the interface tools. 
     
     
         16 . The surveillance system as claimed in  claim 15  wherein at least one of the interface tool allows adjustments of start and end times of the video portions being exported. 
     
     
         17 . A method comprising:
 displaying a two dimensional graph having date and time along the x-axis and, along the y-axis, a listing of a plurality of camera identifications of video cameras with respect to which a respective plurality of video recordings of the video cameras are available for viewing, and the video recordings having portions within which there is an above-threshold likelihood of appearance of an individual or object having been identified as being of interest;   plotting, based on the plurality of camera identifications and times on the x-axis associated with the portions of the video recordings, n image thumbnails on the two dimensional graph, where n is an integer greater than two, the n image thumbnails being visually representative of the portions of the video recordings, and a first of the n thumbnails being shown earliest in time along the x-axis and the n th  thumbnail being shown latest in time along the x-axis;   allowing selection of at least one of the n image thumbnails to be removed from the two dimensional graph;   removing the at least one of the n image thumbnails from the two dimensional graph; and   recording that the individual or object is absent in the portion of the video recording associated with the removed thumbnail.   
     
     
         18 . The method of  claim 17  wherein the method is carried out by a computer terminal in communication with a server system, and the recording is recording in memory of the computer terminal. 
     
     
         19 . The method of  claim 17  further comprising:
 allowing a range of date and time along the x-axis to be expanded when user input requesting such is received; and 
 shrinking sizes of the n image thumbnails when the range is expanded. 
 
     
     
         20 . The method of  claim 17  wherein the n image thumbnails include visual indicia of likelihood of appearance of the individual or object.