Method and apparatus for detecting suspicious activity using video analysis

A method of detecting suspicious activity, the method comprising:

• obtaining video data originating from at least one video camera that monitors an area;
• analyzing frames of video from at least one region of interest of the video data to identify respective events that indicate presence of at least one item in the region of interest, each respective event having an item detection time;
• identifying items, transacted in the area, from transaction data associated with the area, each transacted item having an item transaction time;
• time synchronizing the respective events identified from the video data with the items identified from the transaction data;
• comparing the items identified from the transaction data with the respective events identified from video analysis to determine whether a given event identified from the video data has a corresponding item entry in the transaction data based on the time synchronization;
• and
• in response to determining an absence of an item entry having an item transaction time that corresponds to an item detection time of the given event, indicating the given event as suspicious.

A method for identifying suspicious retail transaction activity, the method comprising:

• collecting video data from a transaction area, the transaction area including a transaction terminal in which customers transact items during a transaction;
• applying video analysis to at least a portion of the video data to detect presence of at least one item, wherein the step of applying video analysis comprises analyzing frames of video from at least one region of interest in at least a portion of the video data to identify a respective event indicating the presence of the at least one item associated with the transaction;
• comparing the presence of the at least one item associated with the transaction from the video data to transaction data indicating items transacted by a customer at the transaction terminal to identify items that were not recorded at the transaction terminal, the step of comparing comprises analyzing a set of items identified as being transacted in the transaction area from the transaction data in comparison to events produced from analysis of the video data to determine if the at least one item represented by the respective event produced from the analysis of the video data is indicated as an item for transacting in the transaction data, and correlating a relationship between video events from the analysis of the video data and transaction items indicated as having been transacted in the transaction data to identify events indicating an item in the video data that does not have a corresponding record in the transaction data.

A method of detecting suspicious activity, the method comprising:

• collecting video data from a transaction area, the transaction area including a transaction terminal in which customers transact items during a transaction;
• applying video analysis to at least a portion of the video data to detect presence of at least one item, wherein the step of applying video analysis comprises analyzing frames of video from at least one region of interest in at least a portion of the video data, wherein analyzing frames of video from the at least one region of interest includes identifying an item carrier as the at least one region of interest, and identifying a respective event indicating presence of at least one item carried by the item carrier that is associated with the transaction;
• notifying of the item carried by the item carrier;
• and
• comparing the presence of the at least one item carried by the item carrier from the video data to transaction data indicating items transacted by a customer at the transaction terminal to identify items that were not recorded at the transaction terminal, the step of comparing comprises analyzing a set of items identified as being transacted in the transaction area from the transaction data in comparison to events produced from analysis of the video data to determine if the at least one item represented by the respective event produced from the analysis of the video data is indicated as an item for transacting in the transaction data, and correlating a relationship between video events from the analysis of the video data and transaction items indicated as having been transacted in the transaction data to identify events indicating an item carried by the item carrier that does not have a corresponding record in the transaction data.