Back to results
US 11,697,558 B2Granted
Automated detection of carton damage
AssigneeTarget Brands, Inc.
InventorsMatthew Nokleby, Deepti Pachauri, Kenneth Zins
Life of this patent
Estimating the term…
Abstract
Methods and systems for automated detection of carton damage are disclosed. One method includes capturing one or more images of a carton via a camera system at a routing location within a warehouse of a retail supply chain, and applying a machine learning model to determine a likelihood of damage of the carton. The method can include, based on the likelihood of damage being above a particular threshold, identifying the carton as damaged. A carton assessment record can be stored in a carton damage tracking database, including the one or more images of the carton alongside the likelihood of damage and the routing location.
Claims21
A method comprising:
- capturing one or more images of a carton via a camera system at a routing location within a warehouse of a retail supply chain;
- applying a machine learning model to determine a likelihood of damage of the carton;
- based on the likelihood of damage being above a particular threshold, identifying the carton as damaged;
- storing a carton assessment record in a carton damage tracking database, the carton assessment record including the one or more images of the carton alongside the likelihood of damage and the routing location;
- receiving user feedback regarding whether the carton is damaged;
- and
- retraining the machine learning model with the user feedback.
4 more elements
A carton damage detection system comprising:
- an image capture system located at a routing location within a warehouse of a retail supply chain;
- and
- an image analysis server local to the image capture system, the image analysis server communicatively connected to the image capture system and configured to host a carton damage tracking database, the image analysis server configured to:
- receive at least one image of a carton from the image capture system;
- apply a machine learning model to the at least one image to determine a likelihood that the carton is damaged;
- and
- store a carton assessment record in the carton damage tracking database, the carton assessment record including the at least one image of the carton alongside the likelihood that the carton is damaged and the routing location;
- wherein the image analysis server is configured to receive user feedback regarding whether the carton is damaged, the user feedback being used to retrain the machine learning model.
5 more elements
A method comprising:
- automatically capturing one or more images of cartons via camera systems positioned at each of a plurality of routing locations within a warehouse of a retail supply chain;
- applying a machine learning model to determine a likelihood of damage to each of the cartons, the machine learning model being a convolutional neural network trained using sample images of damaged cartons and undamaged cartons;
- based on the likelihood of damage to a carton from among the imaged cartons being above a particular threshold, identifying the carton as damaged;
- storing a carton assessment record in a carton damage tracking database for each of the cartons, the carton assessment record including the one or more images alongside the likelihood of damage and the routing location at which the images are captured;
- identifying a location within the warehouse as a root cause of damage to cartons based on damage being detected via the camera systems of the plurality of routing locations;
- receiving user feedback regarding whether the carton is damaged;
- and
- retraining the machine learning model with the user feedback at an image analysis server communicatively connected to the camera systems.
5 more elements
A carton damage detection system comprising:
- an image capture system located at a routing location within a warehouse of a retail supply chain;
- an image analysis server local to the image capture system, the image analysis server communicatively connected to the image capture system and configured to host a carton damage tracking database, the image analysis server configured to:
- receive at least one image of a carton from the image capture system;
- apply a machine learning model to the at least one image to determine a likelihood that the carton is damaged;
- and
- store a carton assessment record in the carton damage tracking database, the carton assessment record including the at least one image of the carton alongside the likelihood that the carton is damaged and the routing location;
- and
- a dashboard accessible via the image analysis server, the dashboard configured to present at least some contents of the carton assessment record.
5 more elements
A method comprising:
- automatically capturing one or more images of cartons via camera systems positioned at each of a plurality of routing locations within a warehouse of a retail supply chain;
- applying a machine learning model to determine a likelihood of damage to each of the cartons, the machine learning model being a convolutional neural network trained using sample images of damaged cartons and undamaged cartons;
- based on the likelihood of damage to a carton from among the imaged cartons being above a particular threshold, identifying the carton as damaged;
- storing a carton assessment record in a carton damage tracking database for each of the cartons, the carton assessment record including the one or more images alongside the likelihood of damage and the routing location at which the images are captured;
- identifying a location within the warehouse as a root cause of damage to cartons based on damage being detected via the camera systems of the plurality of routing locations;
- and
- comparing a rate of damage to cartons at the location to a rate of damage to cartons at corresponding locations of other warehouses within the retail supply chain.
4 more elements
Dependencies are inferred from the claim text.