Abstract: A system for identifying and managing areas of risk in warehouse environments includes video sensors configured to capture video streams and a central processing unit communicatively coupled to video sensors. The central processing unit comprises a raw risk information collection unit configured to store information captured by video sensors, a processing and aggregating unit configured to process and aggregate video streams to produce risk identification information associated with an Operator Route, a risk map generation unit configured to generate a Warehouse Risk Map based on the risk identification information, wherein the Warehouse Risk Map is generated by superimposing an identified risk zone on a warehouse map, and a risk map updating unit for updating the Warehouse Risk Map in real-time when at least one of the risk type, risk level, and risk zone changes for at least one risk instance recorded on the Warehouse Risk Map.

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 determining an action performed within an input image includes a memory to store one or more instructions, and a processor communicatively coupled to the memory, and configured to execute the one or more instructions in the memory. The processor employs a convolutional neural network (CNN) that includes a predefined number of initial stages for extracting one or more significant features corresponding to the input image, wherein each initial stage includes a first layer, and a residual block, and wherein the first layer is selected from a group consisting of a convolution layer, a max pooling layer, and an average pooling layer. The CNN includes a final stage for classifying the extracted significant features into one or more predefined classes, wherein the final stage is formed of a global average pooling layer, and a dense layer.

Abstract: A system for automatically displaying output information on a display surface based on activities in a target environment includes an image capturing device for capturing data of the target environment in real-time, a processing unit for processing the data to determine a location for displaying the output information, and determine a content of the output information, and a video output unit for displaying the output information on the display surface. The video output unit is configured to rotate in a 360° manner, and wherein an angle of rotation of the video output unit is controlled by the processing unit. The image capturing device further captures the output information displayed on the display surface in real time, and provides feedback data to the processing unit in real-time, so as to enable the processing unit to control a focus, a direction, and the output information displayed on the video output unit.

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 process shaping in a retail store environment comprises a video generation and processing component, a data source integration and aggregation component for aggregating and integrate information received from various sources, a process sensing component for generating one or more continuous processes, a process aggregator and weighing component for aggregating the one or more continuous processes into a merged weighted process, a proof of problem and value component for determining one or more process variations, a ripple effect analyser for sending one or more nudging messages to the retail store environment, and a gamified feedback algorithm component for communicating a nudging action corresponding to a nudging message, to one or more entities in the retail store environment.

Abstract: A system for identifying a type of a user in a warehousing environment includes a plurality of Infra Red (IR) Light Emitting Diode (LED) devices provided to users in the warehousing environment, a plurality of cameras, and a user identification unit. The user identification unit includes a memory to store one or more instructions, and a processor communicatively coupled to the memory, and configured to receive an image frame captured by the plurality of cameras, detect one or more IR LED devices in the image frame based on signals emitted by the one or more IR LED devices, detect an IR LED group of each detected IR LED device based on a geometric configuration, a blinking frequency, and a color of LEDs of corresponding IR LED device, and determine a type of user of each IR LED device based on detected LED group of corresponding IR LED device.

Abstract: A system for performing automated auditing of goods includes an audit robot that includes a rotatable platform, and an overhead camera, a multi-tracking camera system, an audit controller configured to receive and process the one or more images to detect a delivery personnel and corresponding pallet of goods when the delivery personnel enters the warehousing environment, generate an alert to instruct the delivery personnel to keep the pallet on the platform of the audit robot, trigger the rotatable platform to rotate when the pallet is kept, trigger the overhead sensor and the multi-tracking camera system to generate image data of the pallet, while the platform is being rotated, process at least one of: image data, scanning data, order and supplier information, historical information, time, and identity of the delivery personnel to assess a risk level of the pallet, and automatically check-in the pallet when risk level is assessed as zero.

Abstract: A system for detecting scan and non-scan events in a self-check out (SCO) process includes a a scanner for scanning objects and generating point of sale (POS) data, a video camera for generating a video of the scanning region, proximity sensors proximal to the video camera for defining an Area of Action (AoA), wherein the video camera starts capturing scanning region, when the objects enter the AoA, and the POS data includes non-zero values, an Artificial neural network (ANN) for receiving an image frame and generating one or more values, each indicating a probability of classification of the image frame into one or more classes respectively, and a processing unit for processing the POS data, and probabilities of one or more classes to detect a correlation between video data and POS data, and detect one of: scan and non-scan event in the image frame based on the correlation.

Abstract: A method for distributing load in a network of processing nodes, wherein the network includes a requesting node, and a set of external processing nodes. The method includes sending an Internet Control Message Protocol (ICMP) message to each external processing node, classifying each external processing node as being either a responding or a non-responding node based on its response time, identifying a responding node that has the capability to fulfill a video processing request, determining first and second sets of excluded responding nodes, selecting the identified node for fulfilling the video processing request, when the identified node does not form a part of the first and second sets of excluded responding nodes, sending a transmission package from the requesting node to the selected identified node for processing, and receiving a binary response from the selected node.

Abstract: A system for detecting an articulate body pose from an imagery content includes an imaging module for capturing the imagery content, and a processor that is operable to obtain a top-down view of the imagery content, and process the top-down view to detect the articulate body pose using a machine learning algorithm, wherein the articulate body pose includes a plurality of joints. The processing includes creating a part confidence map corresponding to each joint of the articulate body pose, generating a heatmap by projecting the part confidence map on the top-down view of the imagery content, creating a part affinity map corresponding to each body part, generating a vector map by projecting the part affinity map on the top-down view of the imagery content, and generating a body-framework corresponding to the articulate body pose, using the heatmap and the vector map.

Abstract: A warehouse management system is configured to include a biometric processing engine to authenticate a user though facial recognition of the user, a natural language processing engine to enables touchless interaction of the user with the system, a voice synthesizer to execute synthesized voice interrogative prompts and respond to responses received from the user, and a quantity detection engine for capturing images of transaction articles and feeding to an artificial image quantization engine (AIQE) for extracting quantities from the captured images and to an artificial image self-learning engine (AISLE) for self-learning of the AIQE.

Abstract: A goods receipt management system includes processors coupled to a non-transitory storage device and operable to execute routines that include a face recognition engine to use facial features of a user to recognize the user as an authorised person, a dialogue manager engine to obtain from the authorised person a stated number of goods items being delivered, a quantification engine to receive an image of the goods items and calculate the number of goods items appearing in the image, a comparison engine to compare the calculated number of goods items with the stated number of goods items, and in the event of a substantial match, to record the calculated number of goods items, and a performance improvement engine to use the image of the goods items to re-tune configuration variables, in the event of a mis-match between calculated number of goods items and stated number of goods items.

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: An imaging arrangement for capturing one or more views of a horizontal shelf of an autonomous retail store includes an image sensor positioned at a back portion of the horizontal shelf, a top mirror mounted at a top portion of the horizontal shelf, to enable the image sensor to capture a top view of one or more products on the horizontal shelf, a front mirror mounted at a front top portion of the horizontal shelf, and a back mirror mounted at a back top portion of the horizontal shelf, wherein the back mirror is inclined at a pre-defined angle with respect to the front mirror, and wherein the front and back mirrors enable the image sensor to capture a front view of the one or more products on the horizontal shelf.

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 pre-defined event has occurred, and transmits the alert to a remote device associated with an employee.

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 pre-defined event has occurred, and transmits the alert to a remote device associated with an employee.