US Patent Application 17650019. VIDEO BASED CONTINUOUS PRODUCT DETECTION simplified abstract

VIDEO BASED CONTINUOUS PRODUCT DETECTION

Organization Name

3M INNOVATIVE PROPERTIES COMPANY

Inventor(s)

Muhammad J. Afridi of Woodbury MN (US)

Mojtaba Kadkhodaie Elyaderani of St. Paul MN (US)

Matthew T. Scholz of Woodbury MN (US)

VIDEO BASED CONTINUOUS PRODUCT DETECTION - A simplified explanation of the abstract

This abstract first appeared for US patent application 17650019 titled 'VIDEO BASED CONTINUOUS PRODUCT DETECTION

Simplified Explanation

The patent application describes a product authentication system that uses image capture devices to create a video representation of a safe environment.

• The system can determine if a specific product is continuously present during a task in a safe environment.
• The video data is sliced into different orientations with respect to time and space.
• Multiple data streams are created, each with slices of the same orientation.
• The data streams are processed using machine learning models, such as convolutional neural networks.
• These models are trained to determine if the designated product is continuously present in the video data.
• An indicator of the product's continuous presence can be provided to a downstream system.
• This indicator can be used to determine if functions of the downstream system should be performed.

Original Abstract Submitted

A product authentication system includes one or more image capture devices that provide video data representative of an enhanced safety environment. The product authentication system can determine the continuous presence of a designated product during a time period, for example, during performance of a task in an enhanced safety environment. The video data can be spatiotemporally sliced according to multiple orientations with respect to the time axis and the two spatial axes. A plurality of data streams are created In where the slices of each respective data stream have the same orientation. The data streams are processed according to one or more machine learning models, such as convolutional neural networks trained to determine whether the designated product is continuously present in the video data. An indicator of the continuous presence of the designated product can be provided to a downstream system and used to indicate whether functions of the downstream system are to be performed.