Abstract: A system for anomaly detection in a self-checkout environment, comprising a processing unit for receiving transaction data from a self-checkout terminal: characterising an activity based on a set of features extracted from the received transaction data; defining a plurality of active intervals for each characterised activity; determining a meta-feature vector for each defined active interval of the plurality of active intervals; comparing each meta feature vector with a predefined set of vectors; and determining an anomaly based on the comparison.

Abstract: A system and a method for navigating an aerial robotic device movable within an aerial movement volume are provided. The method comprises generating a global environment map of the aerial movement volume, and detecting static obstacles therefrom. The method further comprises generating a depth map detailing presence or absence of objects with reference to a current location of the aerial robotic device, and detecting dynamic obstacles therefrom. The method further comprises re-scaling the depth map to correspond to the global environment map of the aerial movement volume, and tracing a route for the aerial robotic device from the current location to the target location avoiding the one or more static obstacles and the one or more dynamic obstacles. The method further comprises navigating the aerial robotic device based on the traced route to enable the aerial robotic device from the current location to the target location.

Abstract: A system for detecting a scan irregularity in scanning process during check-out at a retail store, includes an image receiving module for receiving a video stream of a scanning zone, an image processing module for detecting visual scan intervals in image frames of the video stream, and a decision module. The decision module is configured to process each detected visual scan interval, wherein a processed visual scan interval includes a valid scan action, wherein the valid scan action is a user action performed for scanning an item. The decision module is further configured to detect a scan irregularity in the check-out process, wherein the scan irregularity occurs when an item identified for scanning in a processed visual scan interval is absent in a list of scanned items generated by the scanner during corresponding interval, and provide an alert regarding the scan irregularity at a user computing device.

Abstract: A system for navigating an aerial robotic device (ARD) from a first to a second location includes an object detection module for detecting and generating a first object record of a non-stationary object, an object tracking module for receiving second object records, and comparing the first object record with each second object record, which includes determining whether a distance between centers of bounding boxes of the first and second object records is less than a pre-defined threshold value, identifying the first object record to be a match with the second object record, and updating the second object record with details of the first object record, when the calculated distance is less than the pre-defined threshold, updating a prediction list of a second object record with predicted future locations of corresponding object,and navigating the ARD in the presence of a non-stationary object based on prediction list of corresponding second object record.

Abstract: A system for navigating an aerial robotic device (ARD) includes an object detection module for detecting a non-stationary object in aerial movement volume, an object tracking module for adding location of the non-stationary object from a first object record to a first position of a tracking list of a substantially matching second object record a trajectory prediction module for updating a prediction list of the substantially matching second object record with one or more next trajectory points predicted over a predefined time period T, including determining an acceleration vector of the object in a next sample based on magnitude of current longitudinal and normal components of acceleration vector, and a phase of the velocity vector in next sample; and predicting a trajectory point of corresponding object in next sample accordingly, and a collision avoidance module for navigating the ARD in presence of a non-stationary object based on the updated prediction list.

Abstract: A system for navigating an aerial robotic device (ARD) from a first location to a second location in an aerial movement volume includes an object detection module configured to detect a first non-stationary object in the aerial movement volume, an object tracking module configured to compare update a sequentially ordered tracking list of one or more previous trajectory points of a second non-stationary object with the location of the first non-stationary object, a trajectory prediction module configured to use the tracking list to calculate a pre-defined number N of predicted next trajectory points of a first non-stationary object, each of said predicted next trajectory points being equally spaced by a time interval of ?t; and a collision avoidance module configured to adapt a pre-defined navigation trajectory of the ARD to avoid collision of the ARD with the first non-stationary object during a forecasted period of N×?t.

Abstract: A POS terminal for a retail environment, comprising a data acquisition device for generating event data from a user scan of a product along a scanning path of the POS terminal, said path comprising an entry point and an exit point; and a processing unit for receiving at least a portion of event data from the data acquisition device and process the event data according to a set of predefined rules, to determine a control parameter for the POS terminal, generate a user alert based on the control parameter and communicate the user alert to the end user; the data acquisition device comprising: a universal product code, U PC, scanner; a plurality of illumination units arranged along the scanning path for illuminating the product; a plurality of sensors for sensing event data including a shape, size and volume of the product and a parameter of a hand of the user as the product is scanned along the scanning path.

Abstract: A system for anomaly detection in a self-checkout environment, comprising a processing unit for receiving transaction data from a self-checkout terminal: characterising an activity based on a set of features extracted from the received transaction data; defining a plurality of active intervals for each characterised activity; determining a meta-feature vector for each defined active interval of the plurality of active intervals; comparing each meta feature vector with a predefined set of vectors; and determining an anomaly based on the comparison.

Abstract: An enhanced service system comprises a pair of first wires between a first position proximal to an entry point of a drive through facility and a second position proximal to a receiving window in the drive through facility, and an aerial host unit coupled to the pair of first wires using a pair of first and second host wires. The aerial host unit is longitudinally movable between the first position and the second position and includes an aerial host member moveably supported by the first and second host wires to move laterally between the pair of first wires to approach an incoming customer vehicle, facilitate the customer to place an order, receive payment from the customer, and direct the customer to the receiving window where the aerial host member retrieves the items corresponding to the placed order from the receiving window and transfers the retrieved items to the customer.

Abstract: An enhanced service system comprises a pair of first wires between a first position proximal to an entry point of a drive through facility and a second position proximal to a receiving window in the drive through facility, and an aerial host unit coupled to the pair of first wires using a pair of first and second host wires. The aerial host unit is longitudinally movable between the first position and the second position and includes an aerial host member moveably supported by the first and second host wires to move laterally between the pair of first wires to approach an incoming customer vehicle, facilitate the customer to place an order, receive payment from the customer, and direct the customer to the receiving window where the aerial host member retrieves the items corresponding to the placed order from the receiving window and transfers the retrieved items to the customer.

Abstract: An aerial navigation system comprises four anchor points mounted on top of four upright members respectively at substantially same height from a ground, a carrier device coupled to a first set of four electric motors mounted at the four anchor points through a set of first wires. The set of first wires, the four upright members and the ground effectively define a volume. The carrier device is moveable in a bounded horizontal plane defined by the four anchor points. A robotic device is suspended from the carrier device using a second wire and moves vertically relative to the carrier device through activation of a fifth electric motor. A control unit is coupled to the first set of four electric motors and the fifth electric motor for controlling the three-dimensional movement of the robotic device to permit navigation from a current location to a target location inside the defined volume.

Abstract: A navigation control system for an aerial robotic device suspended from a carrier device in an aerial movement volume of an aerial module. The navigation control system is configured to detect one or more stationary obstacles located in corresponding Aerial Movement Volume, create a 3D map representing the Aerial Movement Volume together with one or more bounding boxes enclosing each stationary obstacle in the Aerial Movement Volume, use an optimisation algorithm to compute an optimal route for the aerial robotic device, determine control parameters for a plurality of electric stepper motors driving the carrier device and the aerial robotic device based on the computed optimal route for the aerial robotic device, and navigate the aerial robotic device in accordance with the computed optimal route to enable the aerial robotic device to reach the required destination while avoiding intervening stationary obstacles.

Abstract: A system for detecting a scan irregularity in scanning process during check-out at a retail store, includes an image receiving module for receiving a video stream of a scanning zone, an image processing module for detecting visual scan intervals in image frames of the video stream, and a decision module. The decision module is configured to process each detected visual scan interval, wherein a processed visual scan interval includes a valid scan action, wherein the valid scan action is a user action performed for scanning an item. The decision module is further configured to detect a scan irregularity in the check-out process, wherein the scan irregularity occurs when an item identified for scanning in a processed visual scan interval is absent in a list of scanned items generated by the scanner during corresponding interval, and provide an alert regarding the scan irregularity at a user computing device.

Abstract: A virtual management system comprises video cameras, and various other sensors that acquire event data indicative relating to the processing of stock. This data is passed to a local data collection device that aggregates the event data and passes it via a network to a number of remote data processing modules. The event data is allocated to each of the data processing modules based upon their assigned tasks by a virtual manager agent. A data processing module receives the aggregated event data from the local data collection device via a network and processes the event data according to a set of pre-defined rules. The data processing module generates an alert in response to the processing of the event data indicating that a predefined event has occurred, and transmits the alert to a remote device associated with an employee.

Abstract: A system for detecting a scan irregularity in scanning process during check-out at a retail store, includes an image receiving module for receiving a video stream of a scanning zone, an image processing module for detecting visual scan intervals in image frames of the video stream, and a decision module. The decision module is configured to process each detected visual scan interval, wherein a processed visual scan interval includes a valid scan action, wherein the valid scan action is a user action performed for scanning an item. The decision module is further configured to detect a scan irregularity in the check-out process, wherein the scan irregularity occurs when an item identified for scanning in a processed visual scan interval is absent in a list of scanned items generated by the scanner during corresponding interval, and provide an alert regarding the scan irregularity at a user computing device.

Abstract: A system for assigning a social attribute class to a human subject in a predefined closed environment includes an image capturing component, a pose detection component configured to perform pose detection and tracking of a human subject in real-time, an action detection component configured to detect an action of the human subject, an activity detection component configured to relate a sequence of actions to detect an activity of the human subject, and a social attribute classification component. The social attribute classification component is configured to determine an average speed (s) of the human subject as a first social attribute, an interaction time of the human subject (Tint) as a second social attribute, an analysis time (Tanal) as a third social attribute, and automatically assigns a social attribute class to the human subject based on the values of the first, second and third social attributes.

Abstract: A system for recognizing human activity from a video stream includes a classifier for classifying an image frame of the video steam in one or more classes and generating a class probability vector for the image frame based on the classification. The system further includes a data filtering and binarization module for filtering and binarizing each probability value of the class probability vector based on a pre-defined probability threshold value. The system furthermore includes a compressed word composition module for determining one or more transitions of one or more classes in consecutive image frames of the video stream and generating a sequence of compressed words based on the determined one or more transitions. The system furthermore includes a sequence dependent classifier for extracting one or more user actions by analyzing the sequence of compressed words to and recognizing human activity therefrom.

Abstract: A system for recognizing human activity from a video stream includes a classifier for classifying an image frame of the video steam in one or more classes and generating a class probability vector for the image frame based on the classification. The system further includes a data filtering and binarization module for filtering and binarizing each probability value of the class probability vector based on a pre-defined probability threshold value. The system furthermore includes a compressed word composition module for determining one or more transitions of one or more classes in consecutive image frames of the video stream and generating a sequence of compressed words based on the determined one or more transitions. The system furthermore includes a sequence dependent classifier for extracting one or more user actions by analyzing the sequence of compressed words to and recognizing human activity therefrom.

Abstract: A method for segmenting motion data and inferring layering order in a video includes segmenting a first image frame of the video using intra-frame mode estimation, segmenting further image frames of the video using inter-frame mode matching, generating a label change map for a current segmented image frame by generating a binary map of the current segmented image frame, and then marking one or more pixels whose labels have changed with respect to a previous segmented image frame, detecting one or more non-still image segments of the current segmented image frame, detecting one or more moving image segments in the one or more non-still image segments, estimating motion of the one or more moving image segments, representing each moving segment as a vector of seven parameters, and clustering one or more similar moving segment vectors based on corresponding one or more parameters.

Abstract: A system for detecting a scan irregularity in scanning process during check-out at a retail store, includes an image receiving module for receiving a video stream of a scanning zone, an image processing module for detecting visual scan intervals in image frames of the video stream, and a decision module. The decision module is configured to process each detected visual scan interval, wherein a processed visual scan interval includes a valid scan action, wherein the valid scan action is a user action performed for scanning an item. The decision module is further configured to detect a scan irregularity in the check-out process, wherein the scan irregularity occurs when an item identified for scanning in a processed visual scan interval is absent in a list of scanned items generated by the scanner during corresponding interval, and provide an alert regarding the scan irregularity at a user computing device.