Method of improving the resolution of a moving object in a digital image sequence

Abstract

A method of improving the resolution of a small moving object in a digital image sequence comprises the steps of: constructing ( 101 ) a high-resolution image background model, detecting ( 102 ) the moving object using the high-resolution image background model, fitting ( 103 ) a model-based trajectory for object registration, and producing ( 104 ) a high-resolution object description. The step of producing a high-resolution object description involves an iterative optimisation of a cost function ( 109 ) based upon a polygonal model of an edge of the moving object. The cost function is preferably also based upon a high resolution intensity description. The iterative optimisation of the cost function may involve a polygon description parameter and/or an intensity parameter.

1 - 15 . (canceled) 
     
     
         16 . A method of improving the resolution of a moving object in a digital image sequence, the method comprising the steps of:
 constructing a high resolution image background model;   detecting the moving object using the high resolution image background model;   registering the object; and   producing a high-resolution object description, wherein the step of producing a high-resolution object description involves an iterative optimization of a function based upon an edge model of the moving object;   subjecting the high-resolution object description to a camera model to produce a low-resolution modeled image sequence;   producing a difference sequence from a registered image sequence and the modeled sequence;   feeding the difference sequence to the cost function; and   minimizing the cost function to produce the next iteration of the polygon description parameter and/or an intensity parameter.   
     
     
         17 . The method of  claim 16 , wherein the object consists mainly or entirely of edge pixels. 
     
     
         18 . The method of  claim 16 , wherein the function is a cost function, and the function is preferably also based upon a high resolution intensity description. 
     
     
         19 . The method of  claim 16 , wherein the edge model is a polygonal model, and wherein the step of registering the object preferably involves a model-based trajectory. 
     
     
         20 . The method of  claim 16 , wherein the high-resolution object description comprises a sub-pixel accurate boundary and/or a high resolution intensity description. 
     
     
         21 . The method of  claim 16 , wherein the step of producing a high-resolution object description involves solving an inverse problem. 
     
     
         22 . The method of  claim 16 , wherein the high resolution image background is estimated using a pixel-based super-resolution method. 
     
     
         23 . The method of  claim 16 , wherein the iterative optimization of a cost function involves a polygon description parameter and/or an intensity parameter. 
     
     
         24 . The method of  claim 16 , wherein the function comprises a regularization term for regulating the amount of intensity variation within the object, preferably according to a bilateral total variation criterion. 
     
     
         25 . A computer program product comprising one or more computer readable storage media having stored thereon computer executable instructions that, when executed by a processor, implement a method that improves the resolution of a moving object in a digital image sequence, the method comprising:
 constructing a high-resolution image background model;   detecting the moving object using the high-resolution image background model;   registering the object; and   producing a high-resolution object description, wherein the step of producing a high-resolution object description involves an iterative optimization of a function based upon an edge model of the moving object;   subjecting the high-resolution object description to a camera model to produce a low-resolution modeled image sequence;   producing a difference sequence from a registered image sequence and the modeled sequence;   feeding the difference sequence to the cost function; and   minimizing the cost function to produce the next iteration of the polygon description parameter and/or an intensity parameter.   
     
     
         26 . The computer program product of  claim 25 , wherein the object consists mainly or entirely of edge pixels. 
     
     
         27 . The computer program product of  claim 25 , wherein the function is a cost function, and the function is preferably also based upon a high resolution intensity description. 
     
     
         28 . The computer program product of  claim 25 , wherein the edge model is a polygonal model, and wherein the step of registering the object preferably involves a model-based trajectory. 
     
     
         29 . The computer program product of  claim 25 , wherein the high-resolution object description comprises a sub-pixel accurate boundary and/or a high resolution intensity description. 
     
     
         30 . The computer program product of  claim 25 , wherein the step of producing a high-resolution object description involves solving an inverse problem. 
     
     
         31 . The computer program product of  claim 25 , wherein the high resolution image background is estimated using a pixel-based super-resolution method. 
     
     
         32 . The computer program product of  claim 25 , wherein the iterative optimization of a cost function involves a polygon description parameter and/or an intensity parameter. 
     
     
         33 . The computer program product of  claim 25 , A computer program product comprising one or more computer readable storage media having stored thereon computer executable instructions that, when executed by a processor, implement a method that improves the resolution of a moving object in a digital image sequence, the method comprising:
 constructing a high-resolution image background model;   detecting the moving object using the high-resolution image background model;   registering the object; and   producing a high-resolution object description, wherein the step of producing a high-resolution object description involves an iterative optimization of a function based upon an edge model of the moving object, wherein the function comprises a regularization term for regulating the amount of intensity variation within the object, preferably according to a bilateral total variation criterion.