Abstract: A method for preventing a hardware wallet from being maliciously paired, comprising: a hardware wallet waiting to receive a connection request; when a connection request is received, determining whether a first terminal sending the connection request has been paired and connected; if so, waiting to receive an instruction of the first terminal; and when receiving a pairing transfer instruction sent by the first terminal, clearing terminal information stored in a whitelist of the hardware wallet. By means of the present technical solution, a hardware wallet can achieve pairing transfer only by means of the authorization of a previously paired terminal, thereby improving the security of the hardware wallet.

Abstract: A sales management system includes a first device including a first processor that is configured to detect a customer moving an item of merchandise in an extraction direction away from a merchandise display, a second device including a second processor that is configured to detect movement of an item of merchandise from the merchandise display and determine a movement direction thereof, and a third processor that is configured to determine whether the extraction and movement directions are substantially identical when the first processor detects the customer moving an item away from the merchandise display and the second processor detects movement of an item from the merchandise display at substantially the same time, and determine the item as a first merchandise to be purchased by the customer when the extraction and movement directions are determined to be the substantially identical.

Abstract: The present disclosure provides a self-service settlement method, apparatus and storage medium, and relates to the technical field of self-service shopping, wherein the method includes: obtaining a monitoring image acquired by an image capture device and corresponding to commodities to be settled which are placed on a settlement counter; obtaining information of the commodities to be settled through image recognition; obtaining a first weight acquired by a weight detection device, obtaining a second weight based on the information of the commodities to be settled, judging whether the information of the commodities to be settled is matched with commodities to be confirmed according to a weight comparison result; and obtaining purchased commodity settlement information under the condition that the information of the commodities to be settled is matched with the commodities to be confirmed, and performing checkout processing.

Abstract: A camera abnormality detecting device according to an embodiment includes an acquiring section and a notifying section. The acquiring section acquires, from an image photographed by a camera provided in a conveyance body to be capable of photographing an inside of a basket placed on a basket receiving section of the conveyance body, an image of a region where an upper edge of the basket is surmised to be reflected. The notifying section notifies, based on the image acquired by the acquiring section, whether an angle of view of the camera is blocked.

Abstract: A multimedia query system is described that includes a multimedia capture system configured to capture raw multimedia data comprising at least one of raw video data or raw audio data, a metadata engine configured to extract one or more anchor points of metadata from the raw multimedia data and to store the one or more anchor points of metadata, wherein the anchor points of metadata includes references to respective portions of the raw multimedia data. The multimedia query system further includes a storage engine configured to store the raw multimedia data, a recall engine configured to receive a query and to apply the query to the one or more anchor points of metadata to identify one or more raw multimedia data candidates from the portions of the raw multimedia data, and a query engine configured to generate a response to the query based on the one or more raw multimedia data candidates.

Abstract: System, method, and media for providing automatic recording of an event. The event may be detected from a set of data collected at a sensor. A recording device manager may send signals to other sensors and electromechanical devices to activate these sensors and electromechanical devices based on detection of the triggering event. The sensor may collect data associated with the triggering event and the electromechanical devices may perform actions based on the triggering event.

Abstract: A facility may allow an authorized user to sponsor other users to enter. Actions taken by those users may be associated with the account of the authorized user. Sensor data obtained at a portal may be indicative of whether a user attempted to provide credentials to a sensor at the portal, time between entry of users, attributes about the user, and so forth. Information about when the users have exited may also be obtained. For example, if three people entered one after another and then left at the same time, they may be deemed to form a group. Based on this information, the actions taken by the users in the group may be associated with the account of the authorized user.

Abstract: Cash trapping at an Automated Teller Machine (ATM) is detected in real time. One or more images from one or more cameras are analyzed. The camera(s) is/are focused overhead of the ATM or on a cash slot of a dispense module for the ATM. The images are analyzed for determining one or more of whether the dispenser module is authentic, whether the cash slot opened or did not open when it should have opened for a cash withdraw, whether visual features of the dispense module have changed over a configurable period of time, and whether hands, gestures, and actions of a person present at the ATM indicate that cash trapping is taking place at the ATM. When cash trapping is detected at the ATM a variety of automated actions are processed, such as shutting down the dispense module, shutting down the ATM, notifying a financial institution, and/or notifying legal authorities.

Abstract: An audio/video recording and communication device (A/V device) including one or more motion sensors arranged in a first row, a first camera, one or more second cameras arranged in a second row, a first cover disposed over the one or more motion sensors, a second cover disposed over the first camera, and a third cover disposed over the one or more second cameras. The one or more motion sensors may include a first motion sensor having a first orientation, a second motion sensor having a second orientation, and a third motion sensor having a third orientation. Additionally, the one or more second cameras may include a camera having a first orientation, a camera having a second orientation, and a camera having a third orientation. In some instances, the first camera is located between the one or more motion sensors and the one or more second cameras.

Abstract: A method and an apparatus for processing an image are provided. The method may include: acquiring a set of image sequences, the set of image sequences including a plurality of image sequence subsets divided according to similarity measurements between image sequences, each image sequence subset including a basic image sequence and other image sequence, wherein a first similarity measurement corresponding to the basic image sequence is greater than or equal to a first similarity measurement corresponding to the other image sequence; creating an original three-dimensional model using the basic image sequence; and creating a final three-dimensional model using the other image sequence based on the original three-dimensional model.

Abstract: The present disclosure provides a method and a device for recognizing a product, an electronic device and a non-transitory computer readable storage medium, relating to a field of unmanned retail product recognition. The method includes the following. A video taken by each camera in a store is acquired. A recognition is performed on each video to obtain a video segment that a product delivery is recognized and to obtain participated users. The participated users include a delivery initiation user and a delivery reception user. The video segment is inputted into a preset delivery recognition model to obtain a recognition result. The recognition result includes a product delivered and a delivery probability. The product information of products carried by the participated users is updated based on the recognition result.

Abstract: A video feature extraction method and device are provided. The method includes extracting one or more frames from a video object to obtain one or more frames of images; stage-by-stage processing each of the one or more frames of images by multi-typed pooling processes to obtain an image feature of the one or more frames of images; and determining a video feature according to the image feature of the one or more frames of images. The multi-typed pooling processes include a maximum pooling process, a minimum pooling process and an average pooling process.

Abstract: In certain embodiments, streaming of a live video to trigger-associated recipients in response to triggers in an environment may be facilitated. In some embodiments, one or more triggers may be detected in an environment, and one or more actions associated with the detected triggers may be performed. As an example, where such associated actions include streaming a live video of the environment to one or more recipients, the recipients may be selected as candidates to receive the live video stream based on the recipients being part of a recipient list associated with a detected trigger. In some embodiments, although a first recipient of the recipient list may initially be selected to receive the live video stream, the live video may be streamed to a second recipient of the recipient list based on the first recipient being unavailable to receive the live video stream.

Abstract: Aspects of the disclosure relate to using cognitive automation for enhanced ATM security. A computing platform may receive, from a first automated teller machine (ATM), first ATM information indicating a first interaction between a user and the first ATM. The computing platform may receive, from a first camera, a first image, which may show the user performing the first interaction with the first ATM. Based on the first ATM information and the first image, the computing platform may determine that the first ATM is experiencing malicious activity. The computing platform may send, to a second ATM, one or more commands directing the second ATM to perform a first security action, which may cause the second ATM to perform the first security action.

Abstract: An object tracking system that includes a first sensor and a second sensor that are each configured to capture frames of at least a portion of a global plane for a space. The system is configured to identify a pixel location for a marker within a frame from the first sensor and to determine an (x,y) coordinate for the marker using a first homography. The system is further configured to identify a pixel location for a different marker in a frame from the second sensor and to determine an (x,y) coordinate for the marker using a second homography. The system is further configured to determine a distance difference between the computed distance between the (x,y) coordinates and an actual distance. The system is further configured to recompute the first homography and/or the second homography in response to determining that the distance difference exceeds a difference threshold level.

Abstract: A system and method for analysing queues in frames of video enables operators to preferably draw three regions of interest overlaid upon the video as short, medium, and long queue regions that form a notional queue area within the video. The regions are drawn with knowledge of, or in anticipation of, foreground objects such as individuals and vehicles waiting for service in a queue. Examples include retail point of sale locations or for automated teller machine (ATM) transactions. In conjunction with a video analytics system that analyses the movement of the foreground objects relative to the queue regions, the system determines the number of objects occupying each queue region, length of the queue, and other queue-related statistics. The system can then create reports and send messages that include the queue analysis results for directing operators to change their staffing resources as part of a real-time queue servicing and optimization response.

Abstract: A system and method for computer vision driven applications in an environment that can include collecting image data across an environment; maintaining an environmental object graph from the image data whereby maintaining the environmental object graph is an iterative process that includes: classifying objects, tracking object locations, detecting interaction events, instantiating object associations in the environmental object graph, and updating the environmental object graph by propagating change in at least one object instance across object associations; and inspecting object state for at least one object instance in the environmental object graph and executing an action associated with the object state. The system and method can be applied to automatic checkout, inventory management, and/or other system integrations.

Abstract: A system for monitoring shopping carts uses cameras to generate images of the carts moving in a store. In some implementations, cameras may additionally or alternatively be mounted to the shopping carts and configured to image cart contents. The system may use the collected image data, and/or other types of sensor data (such as the store location at which an item was added to the basket), to classify items detected in the shopping carts. For example, a trained machine learning model may classify item in a cart as “non-merchandise,” “high theft risk merchandise,” “electronics merchandise,” etc. When a shopping cart approaches a store exit without any indication of an associated payment transaction, the system may use the associated item classification data, optionally in combination with other data such as cart path data, to determine whether to execute an anti-theft action, such as locking a cart wheel or activating a store alarm.

Abstract: A system includes a sensor, a weight sensor, and a tracking subsystem. The tracking subsystem receives an image feed of top-view images generated by the sensor and weight measurements from the weight sensor. The tracking subsystem detects an event associated with an item being removed from a rack in which the weight sensor is installed. The tracking subsystem determines that a first person and a second person may be associated with the event. In response, the tracking subsystem dilates contours associated with the first and second person from a first depth to a second depth until the contours enter a zone adjacent to the rack. A number of iterations is determined for each contour to enter the zone adjacent to the rack. If the first person's contour enters the zone in fewer iterations, the item is assigned to the first person.

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 method for checkout based on an image identification technique of convolutional neural network includes acquiring N pictures of M items to be classified placed on a checkout counter, N shooting angles corresponding to the N pictures have at least one shooting angle for taking pictures downwards from just above, performing object detection in the pictures acquired downwards from just above to obtain first rectangular area images, then respectively performing the object detection in remaining pictures according to the number of the pictures to obtain remaining rectangular area images, obtaining preliminary classification results according to the first rectangular area images, the remaining rectangular area images and a pre-trained first-level classification model, and obtaining first-level classification results according to the preliminary classification results and a pre-trained first-level linear regression model, using the first-level classification results as first classification results and performing c

Abstract: Methods, systems, and apparatus for a detection system. The detection system includes a first camera configured to capture a first image data of a surrounding environment. The first image data includes multiple objects. The detection system includes a memory configured to store image data. The detection system includes an electronic control unit. The electronic control unit is configured to obtain the first image data. The electronic control unit is configured to recognize the multiple objects. The electronic control unit is configured to determine that an object among the multiple objects within the surrounding environment is different than a baseline of the surrounding environment. The electronic control unit is configured to record and capture, in the memory and using the camera, the first image data for a time period before and after the determination that the object is different than the baseline.

Abstract: One or more embodiments of the application provide a method and apparatus for blockchain-based recordkeeping, which are applicable to a self-service vending terminal. The self-service vending terminal is a node of a blockchain. The method includes: obtaining first record information, wherein the first record information is generated based on identification information of a target buyer; receiving second record information, wherein the second record information is generated based on purchase live stream data associated with the target buyer; generating a target transaction based on the first record information and the second record information; and sending the target transaction to a distributed database of a blockchain, for the target transaction to be recorded in the distributed database of the blockchain in response to the target transaction being verified by nodes of the blockchain based on a consensus.

Abstract: Cameras capture time-stamped images of customers, carts, and items possessed by the customers. Customer queues at checkout stations/transaction terminals are monitored for queue lengths, opened terminals, closed terminals, and a total number of items possessed by each customer within each queue. Queue wait times are calculated for each queue and the queue wait times are displayed on monitors adjacent to the queues. Customers approaching the checkout stations are directed to specific queues based on the queue wait times. Closed terminals are opened in advance of a time when a shortest expected wait time for the queues is expected to exceed a threshold wait time. In an embodiment, each queue length is managed based on staff performance metrics associated with staff operating the terminals.

Abstract: A camera abnormality detecting device according to an embodiment includes an acquiring section and a notifying section. The acquiring section acquires, from an image photographed by a camera provided in a conveyance body to be capable of photographing an inside of a basket placed on a basket receiving section of the conveyance body, an image of a region where an upper edge of the basket is surmised to be reflected. The notifying section notifies, based on the image acquired by the acquiring section, whether an angle of view of the camera is blocked.

Abstract: Aspects of the disclosure provide for a method for updating business information. A business at a business location and a reference image for the business at the business location may be selected for an update. From a number of more recent images, a comparison image may be selected based on a likelihood that the comparison image captures the business location. Text and visual features reference image may be compared with text and visual features of the comparison image to determine a text similarity score and a features similarity score. A confidence level indicating whether the business in the reference image is in the comparison image may then be determined using the text similarity score and the feature similarity score. According to the confidence level, the business information of the business may be updated.

Abstract: An information processing apparatus includes an acquisition unit, a determination unit, and a storage unit. The acquisition unit is configured to acquire an image outside a vehicle captured by a camera installed in the vehicle. The determination unit is configured to determine whether or not a determination target image is similar to a reference image based on luminance values of the reference image and the determination target image. The reference image is selected from pieces of image acquired by the acquisition unit. The determination target image is captured after the reference image is acquired. The storage unit is configured to store the image acquired by the acquisition unit excluding the determination target image determined to be similar to the reference image by the determination unit.

Abstract: Embodiments of the present disclosure disclose a method and an apparatus for determining a target object and a human-computer interaction system. The method according to one embodiment of the present disclosure comprises: in response to detecting a position change of an item, determining a to-be-detected image frame sequence based on a detection moment when the position change is detected; performing a human body key point detection to a to-be-detected image frame in the to-be-detected image frame sequence; and determining a target object which performs a target operation action to the item based on a detection result of the human body key point detection. This embodiment improves accuracy of the determined target object.

Abstract: A system is configured to determine whether a member of a social networking service is online or offline with the social networking service. The system updates the online or offline status of the member in accordance with whether the member is connected to the social networking service. The system further implements an anti-jitter mechanism that prevents a waste of computing resources where the member is connected to the social networking service using an intermittent connection. The anti-jitter mechanism leverages heartbeat messages and timestamps to determine whether the member is online or offline with the social networking service. The anti-jitter mechanism further includes the use of one or more delay triggers, where each delay trigger may be generated based on a received heartbeat message. As the status of the member changes, the social networking service disseminates the status change to other members communicatively coupled to the social networking service.

Abstract: In certain embodiments, streaming of a live video to trigger-associated recipients in response to triggers in an environment may be facilitated. In some embodiments, one or more triggers may be detected in an environment, and one or more actions associated with the detected triggers may be performed. As an example, where such associated actions include streaming a live video of the environment to one or more recipients, the recipients may be selected as candidates to receive the live video stream based on the recipients being part of a recipient list associated with a detected trigger. In some embodiments, although a first recipient of the recipient list may initially be selected to receive the live video stream, the live video may be streamed to a second recipient of the recipient list based on the first recipient being unavailable to receive the live video stream.

Abstract: Cameras capture time-stamped images of predefined areas. At least one image includes a representation of multiple individuals in a group of individuals. Attributes retained with each individual are combined with a limb and pose recognition to properly identify each individual of the group within the image.

Abstract: The method for item identification preferably includes determining visual information for an item; calculating a first encoding using the visual information; calculating a second encoding using the first encoding; determining an item identifier for the item using the second encoding; optionally presenting information associated with the item to a user; and optionally registering a new item.

Abstract: Embodiments of the present application provide a method and apparatus for updating an online self-learning event detection model.

Abstract: A user verification system is configured to identify likely interactors approaching points of interaction to ensure accurate interactions and to provide loyalty rewards. In an example, a interaction system installs a user verification device with a stereo camera at an interacting device to capture images of the user and to obtain data from the device. The user verification device uses the stereo camera to determine the location of the user to determine if the user is a likely interactor. The user verification device recognizes motions of the user that are indicative of an interactor, such as reaching across the counter or looking at the operator. The user verification device identifies or verifies the interactor based on the record data or the display data. If the user is the likely interactor, then the system conducts a hands-free interaction with the user account or provides loyalty rewards to the user account.

Abstract: There is provided a classifier capable of classifying unknown abnormal data input to the classifier even if there is a small number of abnormal data used for the learning of the classifier. When learning parameters of the classifier, the specific category likelihood of normal patterns for learning relatively deviating from a group of normal patterns for learning is decreased relatively to the specific category likelihood of normal patterns for learning not relatively deviating from the group of normal patterns for learning, and the specific category likelihood of abnormal patterns for learning is decreased relatively to the specific category likelihood of the group of normal patterns for learning.

Abstract: A method and system for remote monitoring are provided. The system includes a network including a plurality of communication points that provide a path of communication between connected devices, wherein the network is adapted to communicate via internet resources, a video device that is communicatively connected using the network an image/alarm converter that is communicatively connected to the video device using the network, and a proprietary router in the network through which the video device is able to connect to the image/alarm converter using a secure communication tunnel established by the proprietary router over the network.

Abstract: Disclosed are systems and methods of capturing sensor data associated with a retail location. The systems and methods further include a point-of-sale device for processing customer transactions and generating an event trigger for capturing sensor data from one or more of the sensors at the retail location. In response to the event trigger, the systems and methods capture data from the one or more sensors at the retail location and provide access to the stored sensor data and event triggers via a user interface of the point-of-sale device for review of the stored sensor data and event trigger.

Abstract: An imaging object tracking system includes an entrance/exit detection camera to take an image of an entrance/exit detection area where an imaging object enters and exits, an entrance/exit detection upper sensor to detect the imaging object being imaged by the entrance/exit detection camera, at least one upper sensor disposed so as to overlap a part of the detection area for detecting the imaging object with an area where the entrance/exit detection upper sensor detects the imaging object, an initial position estimation unit to estimate an initial position of the imaging object on the basis of positional coordinates of the imaging object in a two-dimensional image taken by the entrance/exit detection camera and three-dimensional coordinate information of the entrance/exit detection area, an upper position detection unit to detect a position of the imaging object seen from an upper side thereof, an initial motion path generation unit to generate an initial motion path, and a tracking unit to generate a followin

Abstract: A method for authorizing an action on a self-service system, in which a user is authorized, by using an authorization server, to carry out an action on a self-service system is provided. The user is equipped with a token for his/her identification.

Abstract: A food locker includes a housing, a food support member, a first door, a second door, and a lock. The housing includes a front wall a front wall, a rear wall, and a chamber. The front wall includes a first opening in communication with the chamber. The rear wall includes a second opening in communication with the chamber. The food support member is disposed within the chamber. The first door is supported by the housing and is movable between a closed position and an open position. The food support member is accessible through the first opening when the first door is in the open position. The second door is supported by the housing and is movable between a closed position and an open position. The food support member is accessible through the second opening when the second door is in the open position. The lock is operatively coupled to at least one of the housing and the first door and is actuatable between a locked configuration and an unlocked configuration.

Abstract: A control apparatus includes a detection unit, an association unit, and an output control unit. The detection unit detects a person from an image which includes a plurality of persons. The association unit associates the persons included in the image with each other based on at least one of a position of the person detected by the detection unit, directions of faces of the persons included in the image, and distances between the persons included in the image. The output control unit causes an output unit to output information that is indicative of a relation of the detected person with respect to other persons included in the image based on a result of association performed by the association unit.

Abstract: To summarize an input image, an image summarization system extracts a background frame and object information of each of objects from an image stream, and selects objects which match a selection condition among extracted objects as a queue object. The image summarization system generates a summarized video based on the queue object and a background frame.

Abstract: An object tracking system includes a sensor, a weight sensor, and a tracking system. The sensor is configured to capture a frame of at least a portion of a rack within a global plane for a space. The tracking system is configured to detect a weight decrease on the weight sensor. The tracking system is further configured to receive the frame of the rack, to determine a pixel location for a person, to determine the person is within a predefined zone associated with the rack. The tracking system is further configured to identify the item associated with the weight sensor and to add the identified item to a digital cart associated with the person.

Abstract: A computer-implemented technique can process overhead images of users in a line at a venue to obtain a user wait time for the line. The processing can include (a) identifying a user of the group of users that is second in the line to obtain a target user, (b) detecting when the target user becomes first in the line to obtain a start time, (c) after the target user becomes first in the line, detecting when the target user leaves the line to obtain an end time, (d) determining a period from the start time to the end time, and (e) calculating the user wait time by calculating a product of (i) the determined period and (ii) a quantity of the group of users in the line after the target user leaves the line. The calculated user wait time can then be output.

Abstract: A data processing apparatus (1) of the present invention includes a unit that retrieves a predetermined subject from moving image data. The data processing apparatus includes a person extraction unit (10) that analyzes moving image data to be analyzed and extracts a person whose appearance frequency in the moving image data to be analyzed satisfies a predetermined condition among persons detected in the moving image data to be analyzed, and an output unit (20) that outputs information regarding the extracted person.

Abstract: The analysis apparatus (2000) includes a co-appearance event extraction unit (2020) and a frequent event detection unit (2040). The co-appearance event extraction unit (2020) extracts co-appearance events of two or more persons from each of a plurality of sub video frame sequences. The sub video frame sequence is included in a video frame sequence. The analysis apparatus (2000) may obtain the plurality of sub video frame sequences from one or more of the video frame sequences. The one or more of the video frame sequences may be generated by one or more of surveillance cameras. Each of the sub video frame sequences has a predetermined time length. The frequent event detection unit (2040) detects co-appearance events of the same persons occurring at a frequency higher than or equal to a pre-determined frequency threshold.

Abstract: Embodiments of the present invention create a three-dimensional virtual model by a user identifying a three-dimensional object, capturing a plurality of two-dimensional images of said object in succession, said plurality of images being captured from different orientations, recording said plurality of images on a storage medium, determining the relative change in position of said plurality of images by comparing two subsequent images, wherein the relative change is determined by a difference in color intensity values between the pixels of one image and another image, generating a plurality of arrays from the difference determined and generating a computer image from said plurality of arrays, wherein said computer image represents said three-dimensional object.

Abstract: A system and method to identify the leader of a group in a retail, restaurant, or queue-type setting (or virtually any setting) through recognition of payment gestures. The method comprises acquiring initial video of a group, developing feature models for members of the group, acquiring video at a payment location, identifying a payment gesture in the acquired video, defining the person making the gesture as the leader of the group, and forwarding/backtracking through the video to identify timings associated with leader events (e.g., entering, exiting, ordering, etc.).

Abstract: The present invention provides an image processing system, an image processing method, and a program capable of suppressing confusion that may arise in a case where a target person is identified when tracking a person. An image processing system includes: a camera control unit which accepts input video images captured by a plurality of video cameras; a tracked person registering unit capable of registering one or more persons appearing in the video images inputted from the camera control unit; and a display screen generating unit which displays switchable windows of the video images inputted from the video cameras for each person registered by the tracked person registering unit.

Abstract: Aspects of this disclosure include technologies to detect unpackaged, unlabeled, or mislabeled products based on product images. Leveraging from improved machine learning techniques, the disclosed technical solution can reduce a full product space for product search to a partial product space. Accordingly, a limited number of product candidates in the partial product space may be visually presented for user evaluation. Sometimes, a product candidate is to be comparatively presented with a live image of the product via a uniquely designed graphic user interface, which further improves the confidence of the user and the accuracy of the underlying transaction.