System and method for inventory identification and quantification

Abstract

A solution for inventory identification and quantification using a portable computing device (“PCD”) comprising a camera subsystem is described. An exemplary embodiment of the solution comprises a method that begins with capturing a video stream of a physical inventory comprised of a plurality of individual inventory items. Using a set of tracking points appearing in sequential frames, and optical flow calculations, coordinates for global centers of the frames may be calculated. From there, coordinates for identified inventory items may be determined relative to the global centers of the frames within which they are captured. Comparing the calculated coordinates for inventory items identified in each frame, as well as fingerprint data, embodiments of the method may identify and filter duplicate image captures of the same inventory item within some statistical certainty. Symbology data, such as QR codes, are decoded and quantified as part of the inventory count.

What is claimed is: 
     
         1 . A method for identifying and counting objects appearing in a multi-frame video stream, the method comprising:
 (a) in two sequentially analyzed frames of a multi-frame video stream:
 identifying a previous tracking element that is present in both a previous frame and a current frame; 
   (b) in the previous frame:
 identifying a location of the previous tracking element relative to the previous frame; and 
 identifying unique objects that are present in the previous frame by identifying a symbology for each unique object, identifying the location of each symbology relative to the previous frame, and counting the number of symbologies; 
   (c) in the current frame:
 identifying the location of the previous tracking element in the current frame, and identifying the location differential of the previous tracking element in the current frame relative to its location in the previous frame; 
 identifying unique objects that are present in the current frame by identifying a symbology for each unique object, filtering out each symbology that matches a symbology in the previous frame and that has a position commensurate with the location differential relative to the previous frame, and counting the unfiltered symbologies; 
   (d) identifying a location of the next tracking element relative that is present in both the current frame and a next frame; and continuing at step (b) with current frame and the next frame as the previous frame and the current frame respectively.   
     
     
         2 . The method of  claim 1 , wherein the sequentially analyzed frames are physically sequential. 
     
     
         3 . The method of  claim 1 , wherein the sequentially analyzed frames are selected from the video stream in a manner to ensure that the sequentially analyzed claims include the tracking element in common. 
     
     
         4 . The method of  claim 1 , wherein identifying a location of the previous tracking element relative to the previous frame comprises identifying an x-y coordinate for the previous tracking element within the previous frame. 
     
     
         5 . The method of  claim 4 , wherein identifying a location of the previous tracking element relative to the current frame comprises identifying an x-y coordinate for the previous tracking element within the current frame. 
     
     
         6 . The method of  claim 5 , wherein identifying the location differential of the previous tracking element in the current frame relative to its location in the previous frame comprises calculating the difference in the x-y coordinates of the previous tracking element in the previous frame and the x-y coordinates of the previous tracking element in the current frame. 
     
     
         7 . A system identifying and counting objects appearing in a multi-frame video stream, the system comprising:
 means for, for each sequentially analyzed frame in the video stream, identifying a tracking element that is present in both frames;   means for identifying a location of the tracking element in both frames;   means for identifying a location differential of the tracking element between the sequentially analyzed frames;   means for identifying symbologies appearing in the sequentially analyzed frames;   means for filtering out redundant symbologies by identifying symbologies that are common in both frames and that have the location differential between the frames; and   means for generating a count of the non-redundant symbologies appearing in the video stream.   
     
     
         8 . The system of  claim 7 , wherein the sequentially analyzed frames are physically sequential. 
     
     
         9 . The system of  claim 7 , wherein the sequentially analyzed frames are selected from the video stream in a manner to ensure that the sequentially analyzed claims include the tracking element in common. 
     
     
         10 . The system of  claim 7 , wherein the means identifying a location of the tracking element in both frames comprises identifying an x-y coordinate for the tracking element within each of the sequentially analyzed frames. 
     
     
         11 . The system of  claim 10 , wherein the means for identifying a location differential of the tracking element between the sequentially analyzed frames comprises a means for calculating the difference in the x-y coordinates of the tracking element between the sequentially analyzed frames. 
     
     
         12 . A computer program product comprising a computer usable memory device having a computer readable program code embodied therein, said computer readable program code executable to implement a method for generating a dataset representative of objects identified in a video stream, comprising:
 (a) in two sequentially analyzed frames of a multi-frame video stream:
 identifying a previous tracking element that is present in both a previous frame and a current frame; 
   (b) in the previous frame:
 identifying a location of the previous tracking element relative to the previous frame; and 
 identifying unique objects that are present in the previous frame by identifying a symbology for each unique object, identifying the location of each symbology relative to the previous frame, and counting the number of symbologies; 
   (c) in the current frame:
 identifying the location of the previous tracking element in the current frame, and identifying the location differential of the previous tracking element in the current frame relative to its location in the previous frame; 
 identifying unique objects that are present in the current frame by identifying a symbology for each unique object, filtering out each symbology that matches a symbology in the previous frame and that has a position commensurate with the location differential relative to the previous frame, and counting the unfiltered symbologies; 
   (d) identifying a location of the next tracking element relative that is present in both the current frame and a next frame; and continuing at step (b) with current frame and the next frame as the previous frame and the current frame respectively.   
     
     
         13 . The computer program product of  claim 12 , wherein the sequentially analyzed frames are physically sequential. 
     
     
         14 . The computer program product of  claim 12 , wherein the sequentially analyzed frames are selected from the video stream in a manner to ensure that the sequentially analyzed claims include the tracking element in common. 
     
     
         15 . The computer program product of  claim 12 , wherein identifying a location of the previous tracking element relative to the previous frame comprises identifying an x-y coordinate for the previous tracking element within the previous frame. 
     
     
         16 . The computer program product of  claim 15 , wherein identifying a location of the previous tracking element relative to the current frame comprises identifying an x-y coordinate for the previous tracking element within the current frame. 
     
     
         17 . The computer program product of  claim 16 , wherein identifying the location differential of the previous tracking element in the current frame relative to its location in the previous frame comprises calculating the difference in the x-y coordinates of the previous tracking element in the previous frame and the x-y coordinates of the previous tracking element in the current frame.