Abstract: Human behavior is determined by sequential event detection by constructing a temporal-event graph with vertices representing primitive images of images of a video stream, and also of idle states associated with the respective primitive images. A human activity event is determined as a function of a shortest distance path of the temporal-event graph vertices.

Abstract: Multi-mode video event indexing includes determining a quality of object distinctiveness with respect to images from a video stream input. A high-quality analytic mode is selected from multiple modes and applied to video input images via a hardware device to determine object activity within the video input images if the determined level of detected quality of object distinctiveness meets a threshold level of quality, else a low-quality analytic mode is selected and applied to the video input images via a hardware device to determine object activity within the video input images, wherein the low-quality analytic mode is different from the high-quality analytic mode.

Abstract: Multi-mode video event indexing includes determining a quality of object distinctiveness with respect to images from a video stream input. A high-quality analytic mode is selected from multiple modes and applied to video input images via a hardware device to determine object activity within the video input images if the determined level of detected quality of object distinctiveness meets a threshold level of quality, else a low-quality analytic mode is selected and applied to the video input images via a hardware device to determine object activity within the video input images, wherein the low-quality analytic mode is different from the high-quality analytic mode.

Abstract: Human behavior is determined by sequential event detection by constructing a temporal-event graph with vertices representing adjacent first and second primitive images of a plurality of individual primitive images parsed from a video stream, and also of first and second idle states associated with the respective first and second primitive images. Constructing the graph is a function of an edge set between the adjacent first and second primitive images, and an edge weight set as a function of a discrepancy between computed visual features within regions of interest common to the adjacent first and second primitive images. A human activity event is determined as a function of a shortest distance path of the temporal-event graph vertices.

Abstract: Multi-mode video event indexing includes determining a quality of object distinctiveness with respect to images from a video stream input. A high-quality analytic mode is selected from multiple modes and applied to video input images via a hardware device to determine object activity within the video input images if the determined level of detected quality of object distinctiveness meets a threshold level of quality, else a low-quality analytic mode is selected and applied to the video input images via a hardware device to determine object activity within the video input images, wherein the low-quality analytic mode is different from the high-quality analytic mode.

Abstract: An approach that dynamically learns a set of attributes of an operator of a point of sale (POS) is provided. In one embodiment, there is an attribute tool, including an extraction component configured to receive sensor data of a set of moving objects, and extract a set of attributes from each of the set of moving objects captured within the scan area at the POS; an identification component configured to update an appearance model with the set of attributes from each of the set of moving objects; and an analysis component configured to analyze the appearance model to identify at least one of the set of moving objects as an operator of the POS.

Abstract: A foreground object blob having a bounding box detected in frame image data is classified by a finite state machine as a background, moving foreground, or temporally static object, namely as the temporally static object when the detected bounding box is distinguished from a background model of a scene image of the video data input and remains static in the scene image for a threshold period. The bounding box is tracked through matching masks in subsequent frame data of the video data input, and the object sub-classified within a visible sub-state, an occluded sub-state, or another sub-state that is not visible and not occluded as a function of a static value ratio. The ratio is a number of pixels determined to be static by tracking in a foreground region of the background model corresponding to the tracked object bounding box over a total number of pixels of the foreground region.

Abstract: A method, data processing system, apparatus, and computer program product for monitoring objects. A plurality of images of an area is received. An object in the area is identified from the plurality of images. A plurality of points in a region within the area is identified from a first image in the plurality of images. The plurality of points has a fixed relationship with each other and the region. The object in the area is monitored to determine whether the object has entered the region. A determination that the object has not entered the region is made in response to identifying an absence of a number of the plurality of points in a second image in the plurality of images.

Abstract: Multi-mode video event indexing includes determining a quality of object distinctiveness with respect to images from a video stream input. A high-quality analytic mode is selected from multiple modes and applied to video input images via a hardware device to determine object activity within the video input images if the determined level of detected quality of object distinctiveness meets a threshold level of quality, else a low-quality analytic mode is selected and applied to the video input images via a hardware device to determine object activity within the video input images, wherein the low-quality analytic mode is different from the high-quality analytic mode.

Abstract: Human behavior is determined by sequential event detection by constructing a temporal-event graph with vertices representing adjacent first and second primitive images of a plurality of individual primitive images parsed from a video stream, and also of first and second idle states associated with the respective first and second primitive images. Constructing the graph is a function of an edge set between the adjacent first and second primitive images, and an edge weight set as a function of a discrepancy between computed visual features within regions of interest common to the adjacent first and second primitive images. A human activity event is determined as a function of a shortest distance path of the temporal-event graph vertices.

Abstract: An approach that dynamically learns a set of attributes of an operator of a point of sale (POS) is provided. In one embodiment, there is an attribute tool, including an extraction component configured to receive sensor data of a set of moving objects, and extract a set of attributes from each of the set of moving objects captured within the scan area at the POS; an identification component configured to update an appearance model with the set of attributes from each of the set of moving objects; and an analysis component configured to analyze the appearance model to identify at least one of the set of moving objects as an operator of the POS.

Abstract: An approach that detects potentially fraudulent transactions is provided. In one embodiment, there is a fraud detection tool including, an identification component configured to identify a first person present within a zone of interest at a point of sale (POS) device using a set of sensor devices; a transaction component configured to determine whether the POS device has performed a first transaction and a second transaction while the first person is present within the zone of interest at the POS device; an analysis component configured to: analyze a transaction type of the first transaction and the second transaction; and detect whether the second transaction is potentially fraudulent based on a determination of whether the POS device has performed a first transaction and a second transaction while the first person is within the zone of interest at the POS device, and an analysis of the transaction type of the second transaction.

Abstract: An approach that automatically distinguishes between in-store customers and in-store employees is provided. In one embodiment, there is a learning tool configured to construct a model for an in-store employee; and a classifying tool, further comprising matching tool configured to: match attributes between a particular person and the constructed models for an in-store employee, the classifying tool configured to: classify persons into categories of employees and customers based on amount of matching attributes between a particular person and the model for an in-store employee.

Abstract: Under the present invention a transaction is processed and analyzed for potential fraud or error. Specifically, a description of a (proposed) transaction is accessed. Among other things, the description contains an expected set of events (e.g., derived from historical data). As the transaction is being performed a set of multimedia devices will record the same. The multimedia signal(s) from the set of devices will be analyzed to determine what event(s) actually took place. The actual event(s) will be compared to the expected event(s) to determine if any deviation/difference exists. If there is a difference, and it is beyond a predetermined tolerance, a notification can be generated. Regardless, a log of the activities will be kept.

Abstract: A non-scan detect system for a retail checkout station includes a non-scan detect module. The non-scan detect module, when operated, causes the non-scan detect system to detect the passing of an item across a scanner device of a retail checkout station, determine that the item passing across the scanner device was not registered as a scan, establish a potential non-scanned item based on the item not being registered as a scan, obtain an image of the potential non-scanned item, establish a scanned item based on an item passing across the scanner device being registered as a scan, extract features associated with the scanned item, compare the features associated with the scanned item with the image of the potential non-scanned item, and trigger an actual non-scan if the features of the scanned item do not substantially match the image of the potential non-scanned item.

Abstract: A method for detecting a non-scan at a retail checkout station includes detecting the passing of an item across a scanner device of a retail checkout station, obtaining an image of the item passing across the scanner, detecting a scan of an item passing across the scanner to establish a scanned item, and establishing a register associated with the scanned item. A scan occurs if the image of the item passing across the scanner substantially matches the register associated with the scanned item. Conversely, a non-scan is triggered when the image of the item passing across the scanner does not match the register associated with the scanned item.