Stoplift, Inc.

Ncr Corporation

Vikram Srinivasan

Malay Kundu

Joshua Migdal

Matthew Farrow

Xiaowei Chen

Brian Frank O'Donnell

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.

Method and apparatus for detecting suspicious activity using video analysis

Video frames from a video are compressed into a single image or a single data structure that represents a unique visual flowprint or visual signature for a given activity being modeled from the video frames. The flowprint comprises a computed summary of the original pixel values associated with the video frames within the single image and the flowprint is specific to movements occurring within the video frames that are associated with the given activity. In an embodiment, the flowprint is provided as input to a machine-learning algorithm to allow the algorithm to perform object tracking and monitoring from the flowprint rather than from the video frames of the video, which substantially improves processor load and memory utilization on a device that executes the algorithm, and substantially improved responsiveness of the algorithm.

Image/video analysis with activity signatures

A computer system monitors a private network for presence of data traffic. In one embodiment, the private network is a retail environment in which a customer purchases an item scanned at a point-of-sale terminal. The data traffic can be point-of-sale transaction information generated in response to purchase of the item at the point-of-sale terminal. Subsequent to detecting presence of the data traffic in the network, the computer system analyzes the data traffic to identify private information in the data traffic. To protect the private information from improper disclosure to unauthorized entities, the computer system modifies the data traffic. Thus, techniques herein can include detecting occurrence of one or more point-of-sale events in a private network, anonymizing the event information (e.g., data traffic), and forwarding the anonymized event information associated with the point-of-sale events out of the private network to a remote resource.

Anonymization and synchronization based on use of protected content

Methods and apparatus provide for a Cart Inspector to create a suspicion level for a transaction when a video image of the transaction portrays an item(s) left in a shopping cart. Specifically, the Cart Inspector obtains video data associated with a time(s) of interest. The video data originates from a video camera that monitors a transaction area. The Cart Inspector analyzes the video data with respect to target image(s) associated with a transaction in the transaction area during the time(s) of interest. The Cart Inspector creates an indication of a suspicion level for the transaction based on analysis of the target image(s). Creation of a high suspicion level for the transaction indicates that the transaction's corresponding video images most likely portray occurrences where the purchase price of an item transported through the transaction area was not included in the total amount paid by the customer.

Cart inspection for suspicious items

The present disclosure includes a system in which a video displayer, having access to video surveillance data and point-of-sale transaction data, provides random-access review of point-of-sale transactional video. Embodiments herein provide a new method of reviewing security video of a transaction taking place at a retail establishment's point-of-sale transaction area, or register. Embodiments herein enable random and instantaneous access to any number of transaction events that may be of interest to a loss prevention investigator. In one embodiment, a video displayer obtains video data comprising a point-of-sale transaction occurring at a point-of-sale transaction area, and transaction data from a point-of-sale terminal. The video displayer displays video of individual transaction events from a larger transaction, and visually modifies displayed video at a moment in the video when a transaction event occurs.

Method and apparatus for random-access review of point of sale transactional video

Techniques disclosed herein include a reviewer interface for providing random-access review of point-of-sale (POS) video, visual indicators to point to point to objects within the point-of-sale video, and/or display of interactive statistical features. The system obtains video data of point-of-sale transactions, and corresponding transaction data correlated with the video data. The system identifies and displays transaction events of interest. In one embodiment, such a display includes displaying a visual indicator positioned at a spatial location within displayed video to identify a location of an object in the displayed video that corresponds to the transaction event identified as a transaction event of interest. The system also includes functionality to display visual indicators associated with transaction data to convey magnitude or quantity of transaction events of interest. The system also includes interactive graphs and filtering criteria for displaying transaction statistics and to browse details of transaction events.

Method and apparatus for web-enabled random-access review of point of sale transactional video

According to one configuration, a computer environment includes a first monitoring system, a second monitoring system, and an analyzer. The first monitoring system produces video of an item being entered into a point of sale system. The second monitoring system monitors events associated with entering of the item into the point of sale system. The analyzer detects, via a communication from the second monitoring system, an occurrence of at least one event associated with entering of the item. Based on communication, the analyzer correlates the at least one event to a particular time in the video when the at least one event occurred.

Correlating detected events with image data

A system performs video identification of items involved with transactions, as captured in video data, and compares this item identification information with transaction data obtained from a transaction terminal such as a point-of-sale register to identify situations that are suspicious and may indicate fraudulent activity or operator error. In particular, the system as disclosed herein utilizes unique camera positions, and can use video data from more than one camera, to perform robust detections of fraudulent or suspicious activities associated with transactions in the transaction area. By obtaining video data originating from at least one video camera that monitors a transaction area, the system can automatically (i.e. no human involvement needed) analyze the video data to track items involved in a transaction in the transaction area. Using this information, the system can compare the video analysis of the tracked items to transaction data produced from a transaction terminal to identify suspicious activity. The system can also create, update and maintain object models for items tracked in a transaction area, in part, to assist in identifying suspicious activity.

Growing community of inventors

Billerica, MA, United States of America

Vikram Srinivasan