US 12,307,772 B2
System and method for automated foreign material exclusion attendant
Michael R. Vindler, Pittsburgh, PA (US); Zachary Franczyk, Oakmont, PA (US); Scott A. Karstetter, Monroeville, PA (US); Phani Ram Kumar Kuruganty, Robbinsville, NJ (US); and Rajat Vikram Singh, Santa Clara, CA (US)
Assigned to Siemens Energy, Inc., Orlando, FL (US)
Filed by Siemens Energy, Inc., Orlando, FL (US)
Filed on Mar. 14, 2022, as Appl. No. 17/654,706.
Claims priority of provisional application 63/161,777, filed on Mar. 16, 2021.
Prior Publication US 2022/0301314 A1, Sep. 22, 2022
Int. Cl. G06T 7/00 (2017.01); G06F 16/51 (2019.01); G06F 16/583 (2019.01); G06T 7/11 (2017.01); G06V 20/50 (2022.01)
CPC G06V 20/50 (2022.01) [G06F 16/51 (2019.01); G06F 16/5854 (2019.01); G06T 7/0004 (2013.01); G06T 7/11 (2017.01); G06T 2207/20081 (2013.01); G06T 2207/20092 (2013.01)] 14 Claims
OG exemplary drawing
 
1. A method to account for a foreign material in a foreign material zone, the method comprising:
training an object detection model to identify an object using a set of database images of objects on a computer utilizing Artificial Intelligence (AI) algorithms to create an AI-based trained object detection model;
receiving the object in an area within a field of view of a camera;
creating an image of the object using the camera;
distinguishing whether the object is entering the foreign material zone or exiting the foreign material zone;
identifying the object using the AI-based trained object detection model;
inspecting the object to determine if the object includes a subcomponent to retrain and improve the AI-based trained object detection model; and
in response to the distinguishing step, one of:
storing the image in a log representing the objects in the foreign material zone in response to the object being identified by the AI-based trained object detection model when the object is entering the foreign material zone; and
removing the image from the log when the object is exiting the foreign material zone.