Detection of stock out conditions based on image processing

Abstract

Image analysis techniques, including object recognition analysis, are applied to images obtained by one or more image capture devices deployed within inventory environments. The object recognition analysis provides object recognition data (that may include one or more recognized product instances) based on stored product (training) images. In turn, a variety of functionalities may be enabled based on the object recognition data. For example, a planogram may be extracted and compared to a target planogram, or at least one product display parameter for a product can be determined and used to assess presence of the product within the inventory environment, or to determine compliance of display of the product with a promotional objective. In yet another embodiment, comparisons may be made within a single image or between multiple images over time to detect potential conditions requiring response. In this manner, efficiency and effectiveness of many previously manually-implemented tasks may be improved.

1 - 7 . (canceled) 
     
     
         8 . A method comprising:
 receiving, by a device, one or more images of one or more products in an inventory environment;   analyzing, by the device, the received one or more images to generate object recognition data including one or more recognized product instances;   determining, by the device and based on the one or more recognized product instances, one or more display parameters associated with at least one of the one or more products;   receiving, by the device, information associated with one or more promotional objectives; and   determining, by the device and based on the one or more display parameters associated with the at least one of the one or more products and the received information associated with the one or more promotional objectives, if placement of the at least one of the one or more products in the inventory environment complies with the one or more promotional objectives.   
     
     
         9 . The method of  claim 8 , where, when determining the one or more display parameters associated with the at least one of the one or more products, the method includes:
 determining, based on the one or more recognized product instances, facing information associated with the at least one of the one or more products,
 the facing information indicating that the at least one of the one or more products is recognizable; and 
   determining, based on the facing information, a location of the facing information with respect to the at least one of the one or more products.   
     
     
         10 . The method of  claim 8 , where
 the one or more products include a plurality of products, and   when determining the one or more display parameters associated with the at least one of the one or more products, the method includes:
 determining, based on the one or more recognized product instances, respective facing information for each respective product of the plurality of products,
 the respective facing information indicating that the respective product is recognizable; and 
 
 determining, based on the respective facing information, a respective location of the respective facing information for each of the plurality of products. 
   
     
     
         11 . The method of  claim 10 , where the determined respective location of the respective facing information for each of the plurality of products is associated with at least one of:
 shelf information,   aisle information,   a respective first distance from the respective facing information for each of the plurality of products to at least one end of an aisle, or   a respective second distance from the respective facing information for each of the plurality of products to at least one other product,
 the at least one other product being different than each of the plurality of products. 
   
     
     
         12 . The method of  claim 8 , where, when analyzing the received one or more images to generate the object recognition data, the method includes:
 analyzing the received one or more images to recognize promotional information.   
     
     
         13 . The method of  claim 12 , where, when determining the one or more display parameters associated with the at least one of the one or more products, the method includes:
 determining a proximity of the at least one of the one or more products to the recognized promotional information.   
     
     
         14 . The method of  claim 8 , where, when determining if the placement of the at least one of the one or more products in the inventory environment complies with the one or more promotional objectives, the method includes:
 transmitting a noncompliance notification when the placement of the at least one of the one or more products in the inventory environment does not comply with the one or more promotional objectives.   
     
     
         15 . A system comprising:
 one or more devices to:
 receive one or more images of one or more products in an inventory environment; 
 analyze the received one or more images to generate object recognition data including one or more recognized product instances; 
 determine, based on the one or more recognized product instances, one or more display parameters associated with at least one of the one or more products; 
 receive information associated with one or more promotional objectives; and 
 determine, based on the one or more display parameters associated with the at least one of the one or more products and the received information associated with the one or more promotional objectives, if placement of the at least one of the one or more products in the inventory environment complies with the one or more promotional objectives. 
   
     
     
         16 . The system of  claim 15 , where the one or more devices, when determining the one or more display parameters associated with the at least one of the one or more products, are further configured to:
 determine, based on the one or more recognized product instances, facing information associated with the at least one of the one or more products,
 the facing information indicating that the at least one of the one or more products is recognizable; and 
   determine, based on the facing information, a location of the facing information with respect to the at least one of the one or more products.   
     
     
         17 . The system of  claim 15 , where
 the one or more products include a plurality of products, and   the one or more devices, when determining the one or more display parameters associated with the at least one of the one or more products, are further configured to:
 determine, based on the one or more recognized product instances, respective facing information for each respective product of the plurality of products,
 the respective facing information indicating that the respective product is recognizable; and 
 
 determine, based on the respective facing information, a respective location of the respective facing information for each of the plurality of products. 
   
     
     
         18 . The system of  claim 17 , where the determined respective location of the respective facing information for each of the plurality of products is associated with at least one of:
 shelf information,   aisle information,   a respective first distance from the respective facing information for each of the plurality of products to at least one end of an aisle, or   a respective second distance from the respective facing information for each of the plurality of products to at least one other product,
 the at least one other product being different than each of the plurality of products. 
   
     
     
         19 . The system of  claim 15 , where the one or more devices, when analyzing the received one or more images to generate the object recognition data, are further configured to:
 analyze the received one or more images to recognize promotional information.   
     
     
         20 . The system of  claim 19 , where the one or more devices, when determining the one or more display parameters associated with the at least one of the one or more products, are further configured to:
 determine a proximity of the at least one of the one or more products to the recognized promotional information.   
     
     
         21 . The system of  claim 15 , where the one or more devices, when determining if the placement of the at least one of the one or more products in the inventory environment complies with the one or more promotional objectives, are further configured to:
 transmit a noncompliance notification when the placement of the at least one of the one or more products in the inventory environment does not comply with the one or more promotional objectives.   
     
     
         22 . A non-transitory computer-readable medium storing instructions, the instructions comprising:
 one or more instructions which, when executed by at least one processor, cause the at least one processor to:
 receive one or more images of one or more products in an inventory environment; 
 analyze the received one or more images to generate object recognition data including one or more recognized product instances; 
 determine, based on the one or more recognized product instances, one or more display parameters associated with at least one of the one or more products; 
 receive information associated with one or more promotional objectives; and 
 determine, based on the one or more display parameters associated with the at least one of the one or more products and the received information associated with the one or more promotional objectives, if placement of the at least one of the one or more products in the inventory environment complies with the one or more promotional objectives. 
   
     
     
         23 . The non-transitory computer-readable medium of  claim 22 , where the one or more instructions to determine the one or more display parameters associated with the at least one of the one or more products further include:
 one or more instructions to determine, based on the one or more recognized product instances, facing information associated with the at least one of the one or more products,
 the facing information indicating that the at least one of the one or more products is recognizable; and 
   one or more instructions to determine, based on the facing information, a location of the facing information with respect to the at least one of the one or more products.   
     
     
         24 . The non-transitory computer-readable medium of  claim 22 , where
 the one or more products include a plurality of products, and   the one or more instructions to determine the one or more display parameters associated with the at least one of the one or more products further include:
 one or more instructions to determine, based on the one or more recognized product instances, respective facing information for each respective product of the plurality of products,
 the respective facing information indicating that the respective product is recognizable; and 
 
 one or more instructions to determine, based on the respective facing information, a respective location of the respective facing information for each of the plurality of products. 
   
     
     
         25 . The non-transitory computer-readable medium of  claim 24 , where the determined respective location of the respective facing information for each of the plurality of products is associated with at least one of:
 shelf information,   aisle information,   a respective first distance from the respective facing information for each of the plurality of products to at least one end of an aisle, or   a respective second distance from the respective facing information for each of the plurality of products to at least one other product,
 the at least one other product being different than each of the plurality of products. 
   
     
     
         26 . The non-transitory computer-readable medium of  claim 22 , where
 the one or more instructions to analyze the received one or more images to generate the object recognition data further include:
 one or more instructions to analyze the received one or more images to recognize promotional information, and 
   the one or more instructions to determine the one or more display parameters associated with the at least one of the one or more products further include:
 one or more instructions to determine a proximity of the at least one of the one or more products to the recognized promotional information. 
   
     
     
         27 . The non-transitory computer-readable medium of  claim 22 , where the one or more instructions to determine if the placement of the at least one of the one or more products in the inventory environment complies with the one or more promotional objectives further include:
 one or more instructions to transmit a noncompliance notification when the placement of the at least one of the one or more products in the inventory environment does not comply with the one or more promotional objectives.