Object extraction from video images system and method

Abstract

A computer implemented method of object extraction from video images, the method comprising steps a computer is programmed to perform, the steps comprising: receiving a plurality of video images, deriving a plurality of background templates from at least one of the received video images, calculating a plurality of differences from an individual one of the received video images, each one of the differences being calculated between the individual video image and a respective and different one of the background templates, and extracting an object of interest from the individual video image, using a rule applied on the calculated differences.

What is claimed is: 
     
         1 . A computer implemented method of object extraction from images, the method comprising steps a computer is programmed to perform, the steps comprising:
 receiving a plurality of background templates and at least one image;   calculating a plurality of differences for an individual one of the received at least one image, each one of the differences being calculated between the individual image and a respective one of the received background templates; and   extracting an object of interest from the individual image, using a rule applied on the calculated differences.   
     
     
         2 . The method of  claim 1 , further comprising selecting the rule among a plurality of predefined rules. 
     
     
         3 . The method of  claim 1 , further comprising allowing a user to define the rule. 
     
     
         4 . The method of  claim 1 , further comprising selecting the rule according to circumstances of capturing of the received at least one image. 
     
     
         5 . The method of  claim 1 , further comprising selecting the rule according to a characteristic pertaining to the object of interest. 
     
     
         6 . The method of  claim 1 , further comprising selecting the rule according to a characteristic pertaining to a background of the received at least one image. 
     
     
         7 . The method of  claim 1 , wherein each one of at least two of the received background templates is a template derived using a respective and different one of a plurality of background calculation methods. 
     
     
         8 . The method of  claim 1 , wherein each one of at least two of the received background templates is a template derived using a respective and at least partially different subset of the received at least one image. 
     
     
         9 . The method of  claim 1 , wherein each one of at least two of the received background templates is a template derived using a respective and at least partially less recent subset of the received at least one image. 
     
     
         10 . The method of  claim 1 , wherein each one of at least two of the received background templates is a template derived using a respective and different frequency of sampling of the received at least one image. 
     
     
         11 . The method of  claim 1 , wherein each one of at least two of the received background templates is a template derived using a respective and different in size subset of the received at least one image. 
     
     
         12 . The method of  claim 1 , further comprising updating each one of at least two of the received background templates, with a respective and different update rate. 
     
     
         13 . Apparatus for object extraction from images, the apparatus comprising:
 a computer;   a difference calculator, configured to receive a plurality of background templates and at least one image and calculate a plurality of differences for an individual one of the received at least one image, each one of the differences being calculated between the individual image and a respective one of the received background templates; and   an object extractor, in communication with said difference calculator, configured to extract an object of interest from the individual image, using a rule applied on the calculated differences.   
     
     
         14 . A non-transitory computer readable medium storing computer executable instructions for performing steps of object extraction from images, the steps comprising:
 receiving a plurality of background templates and at least one image;   calculating a plurality of differences for an individual one of the received at least one image, each one of the differences being calculated between the individual image and a respective one of the received background templates; and   extracting an object of interest from the individual image, using a rule applied on the calculated differences.