Method and apparatus for detecting suspicious activity using video analysis
A system detects a transaction outcome by obtaining video data associated with a transaction area and analyzing the video data to obtain at least one video transaction parameter concerning transactions associated with the transaction area. The transaction area can be a video count of items indicated in the video data as detected by an automated item detection algorithm applied to the video data. The system obtains at least one expected transaction parameter concerning an expected transaction that occurs in the transaction area, such as a scan count of items scanned at a point of sale terminal. The system automatically compares the video transaction parameter(s) to the expected transaction parameter(s) to identify a transaction outcome that may indicate fraudulent activity such as sweethearting in a retail environment.
1. A method, comprising:
via a computer processor hardware, performing operations of:
receiving visual information generated by a camera that monitors a transaction area using a background image associated with the transaction area, the visual information capturing images of items passing through the transaction area by identifying the items in the images after subtracting from the images the background image and obtaining the visual information associated with the items;
receiving transaction data from a transaction terminal, the transaction data tracking items passing through the transaction area; and
performing a comparison between the visual information and the transaction data to identify a discrepancy between the visual information and the transaction data.
2. The method of claim 1 , wherein receiving the visual information further includes creating an object map from the images with the object map representing the items.
3. The method of claim 2 , wherein creating further includes applying filters to the object map and identifying skin depicted in the images from the items.
4. The method of claim 3 , wherein applying further includes incorporating a filtered version of the object map into a motion map of motion of the items through the transaction area.
5. The method of claim 1 , wherein receiving the visual information further includes tracking regions of interest within the images based on movement and location of the items within the transaction area as captured in the images.
6. The method of claim 1 , wherein receiving the transaction data further includes time synchronizing the visual information of the images with the transaction data.
7. The method of claim 6 , wherein time synchronizing further includes identifying events associated with the items from a time synchronized version of the visual information and the transaction data.
8. The method of claim 7 , wherein identifying further includes sequencing the events.
9. The method of claim 8 , wherein sequencing further includes identifying patterns from a sequenced version of the events.