Abstract: A traffic signal fixture verification system including an optical recognition means configured to obtain one or more images of two or more traffic signal fixtures in proximity to an ego vehicle, and to detect a motion status of one or more vehicles in proximity to the ego vehicle, a processing means configured to determine a relevance value for two or more traffic signal fixtures identified in the one or more images, monitor a status of each of two or more relevant traffic signal fixtures having a relevance value greater than a threshold value, and based on the relevance values of the two or more relevant traffic signal fixtures, the respective status of each of the two or more relevant traffic signal fixtures, and optionally, and/or the motion status of the one or more vehicles surrounding the vehicle, actuate an accelerator function or a braking function of the ego vehicle.

Abstract: Systems and methods are provided for detecting a flashing light on one or more traffic signal devices. The method includes capturing a series of images of one or more traffic signal elements in a traffic signal device over a length of time. The method further includes, for each traffic signal element, analyzing the series of images to determine one or more time periods at which the traffic signal element is in an on state or an off state, and analyzing the time periods to determine one or more distinct on states and one or more distinct off states. The method further includes identifying one or more cycles correlating to a distinct on state immediately followed by a distinct off state, or a distinct off state immediately followed by a distinct on state, and, upon identifying a threshold number adjacent cycles, classifying the traffic signal element as a flashing light.

Abstract: The invention provides a method and device for protecting a child inside a vehicle, a computer device, a computer-readable storage medium, and a vehicle, which are applied to the technical field of automobiles. The method for protecting a child inside a vehicle includes: receiving image data inside a vehicle; performing facial detection on the image data to detect passengers in the vehicle; further classifying the detected passengers in the vehicle into children and adults according to the facial detection; and performing a corresponding protection operation when a result of the classification indicates that there is a child alone in the vehicle.

Abstract: The present disclosure relates to a service system and method for detecting the number of in-vehicle persons of a vehicle in a high occupancy vehicle lane. In more detail, the present disclosure relates to a service system and method for detecting the number of in-vehicle persons of a vehicle in a high occupancy vehicle lane, the service system and method detecting a vehicle violating the law about use of a high occupancy vehicle lane by calculating the number of in-vehicle persons of a vehicle using a high occupancy vehicle lane by tracking the number of in-vehicle persons on the basis of images of the vehicle taken by a camera disposed diagonally to the traveling direction of the vehicle and a camera disposed orthogonally to the traveling direction of the vehicle.

Abstract: A looking away determination device includes: a determination unit that determines that a driver is in a looking away state when a proportion of an image in which a face of the driver is not detected with respect to a plurality of images obtained by imaging the driver is equal to or greater than a first predetermined value, the first predetermined value being determined based on driving state information that indicates a state during driving by the driver.

Abstract: A method for determining a state of vigilance of a driver in a vehicle using a predetermined image-analyzing algorithm. The method especially includes a step of executing the predetermined algorithm on the generated sequence of images in order to detect a series comprising at least one movement of the head of the driver, a step of determining the speed and/or the amplitude of each identified movement and of the dynamic and static periods of the head of the driver, a step of detecting dynamic and static periods of the head of the driver and of measuring the frequency and duration of each period, and a step of determining a state of vigilance of the driver from the speed and/or the amplitude determined for each identified movement and from the frequency and duration of each detected period.

Abstract: Learning-based 3D property extraction can include: capturing a series of live 2D images of a participatory event including at least a portion of at least one reference visual feature of the participatory event and at least a portion of at least one object involved in the participatory event; and training a neural network to recognize at least one 3D property pertaining to the object in response to the live 2D images based on a set of timestamped 2D training images and 3D measurements of the object obtained during at least one prior training event for the neural network.

Abstract: A method of re-identifying a rough gemstone comprises providing a 3D model of a first rough gemstone; generating a series of virtual 2D silhouette images of the 3D model; processing each 2D image of the series of virtual 2D silhouette images to obtain a dataset associated with the first rough gemstone; and comparing the dataset of the first rough gemstone with an existing dataset of a rough gemstone. Where the dataset of the first rough gemstone and the existing dataset match each other, the method comprises re-identifying the first rough gemstone as the same rough gemstone from which the existing dataset was obtained.

Abstract: An industrialized system and method for rice grain recognition. An optical image is taken and transmitted to a digital platform, wherein the system segments the optical image and extracts and/or measures appropriate grain features from the image describing different aspects of the grain. The image is processed by the system which includes a selector selecting different machine learning structures, applying the different machine learning structures to the extracted features for rice grain recognition, and selecting the best of the applied machine learning structures by a random sampling process. The selected best of the applied machine learning structures is further optimized by varying an appropriate threshold by a threshold trigger based on a confusion matrix comprising. An active learning structure based on the confusion matrix to the user. The system is retrained based on the feedback parameters of the feedback loop.

Abstract: A hierarchical deep-learning object detection framework provides a method for identifying objects of interest in high-resolution, high pixel count images, wherein the objects of interest comprise a relatively a small pixel count when compared to the overall image. The method uses first deep-learning model to analyze the high pixel count images, in whole or as a patchwork, at a lower resolution to identify objects, and a second deep-learning model to analyze the objects at a higher resolution to classify the objects.

Abstract: A vehicle display device includes: an obstacle information acquisition section configured to acquire information relating to a plurality of obstacles in surroundings of a vehicle; and a mark display section configured to display a predetermined individual mark prompting caution toward an individual obstacle among the plurality of obstacles by superimposed display in a display region inside a vehicle cabin, and to display a predetermined cluster mark prompting caution toward a plurality of the obstacles by superimposed display in the display region in a case in which a predetermined condition has been satisfied.

Abstract: An electronic device and a control method therefor are provided. The present electronic device comprises: a communication interface including a circuit, a memory for storing at least one instruction, and a processor for executing the at least one instruction, wherein the processor acquires contents through the communication interface, acquires information about a text included in an image of the contents, and acquires, on the basis of the information about the text included in the image of the contents, caption data of the contents by performing voice recognition for voice data included in the contents.

Abstract: An extraction method executed by a computer includes: acquiring a first word input by a first user; acquiring a second word input by a second user; calculating a first distributed representation of a first character string, the first character string including the first word and a character string that identifies the first user; calculating a second distributed representation of a second character string, the second character string including the second word and a character string that identifies the second user; calculating a similarity between the first distributed representation and the second distributed representation; and extracting a word associated with the second distributed representation on a basis of the similarity.

Abstract: Disclosed are systems and methods for generating search result data based on machine-encoded text generated by computer vision optical character recognition machine learning techniques performed on digital media. The disclosed systems and methods provide a novel framework for performing machine learning visual search or machine learning text extraction techniques on digital media in order to extract and analyze the data therein and further conduct search queries based on the extracted and analyzed data. The disclosed framework may leverage the aforementioned computer vision machine learning techniques in order to provide a user with relevant search results regarding objects and text detect in digital media captured on a user device.

Abstract: Methods and systems are presented for detecting a boundary of a document within a digital image. Upon receiving an image, the image is converted into a binary image. One or more kernel-based transformations are performed on the binary image using a horizontal kernel and a vertical kernel. A plurality of edges are identified based on the one or more kernel-based transformations. The plurality of edges includes a plurality of horizontal edges and a plurality of vertical edges. Multiple quadrilaterals are constructed using different combinations of horizontal edges and vertical edges from the plurality of edges. A particular quadrilateral is selected from the multiple quadrilaterals based on how well the edges fit the perimeters of the quadrilaterals. The selected quadrilateral is used to define a boundary of the document within the digital image.

Abstract: Techniques described herein relate to a method for predicting field values of documents. The method may include identifying a field prediction model generation request; obtaining, training documents from a document manager; selecting a first training document; making a first determination that the first training document is a text-based document; performing text-based data extraction to identify first words and first boxes included in the first training document; identifying first keywords and first candidate words included in the first training document based on the first words and the first boxes; and generating a first annotated training document using the first keywords and the first candidate words, wherein the first annotated training document comprises color-based representation masks for the first keywords, the first candidate words, and first general words included in the first training document.

Abstract: A method of generating and optimizing a codebooks for document analysis comprises: receiving a first set of document images; extracting a plurality of keypoint regions from each document image of the first set of document images; calculating local descriptors for each keypoint region of the extracted keypoint regions; clustering the local descriptors such that each center of a cluster of local descriptors corresponds to a respective visual word; generating a codebook containing a set of visual words; and optimizing the codebook by maximizing mutual information (MI) between a target field of a second set of document images and at least one visual word of the set of visual words.

Abstract: Methods and systems for extracting and processing data using optical character recognition in real-time environments. For example, the methods and systems provide novel techniques during extracting data using OCR and for a mechanism to process that data. These methods and systems are particularly relevant in real-time environments as the methods and system limit the need for manual review.

Abstract: A method—for biometric based person recognition systems is provided. The method provides an identification of a personalized bioelectric code and a personal ID code by identifying persons and gestures of a person with a benefit of behavioral biometric data of Electromyography (EMG) signals. The method includes the steps of: making the person wishing to create a password to wear a wristband, simultaneously recording of hand movements in eight bioelectric signals from eight EMG sensors in recordings of up to 10 seconds, repeating each selected movement type by the person at least ten times, clearing a recorded raw signal group from noise signals with a bandpass filter, separating a signal cleaned from the noise signals into to windows, creating a customized behavioral biometric data set with generated attributes for each transaction, obtaining the personalized bioelectrical code and the personal ID code.

Abstract: A sensor device including a fingerprint sensor and an antenna. The a fingerprint sensor has a silicon-based area sensor, a sensor area, and an electrically conductive contact region arranged laterally adjacent to the sensor area and configured to be touched upon the contact area being touched by a finger in order to bring the finger to a predetermined potential. The antenna is coupled to the fingerprint sensor to inductively couple the fingerprint sensor to a booster antenna.

Abstract: A terminal device is disclosed, including a display module, an optical fingerprint sensor, at least two backlight assemblies, and a light emitter. The display module includes a display screen and a light-transmissive cover that covers the display screen. The light emitter and the display screen are both fastened onto an inner surface of the light-transmissive cover, the optical fingerprint sensor is provided on a side of the display screen facing away from the light-transmissive cover, and the at least two backlight assemblies are provided sequentially between the display screen and the optical fingerprint sensor. Along a direction from the display screen to the optical fingerprint sensor, areas of light-transmissive regions of the at least two backlight assemblies are gradually reduced. Light emitted by the light emitter experiences a finger, and then successively passes through the display module and the light-transmissive regions and is projected onto the optical fingerprint sensor.

Abstract: An electronic device includes a display screen, a first lens module, a fingerprint sensor, and a first driving mechanism. The first lens module, the fingerprint sensor, and the first driving mechanism are disposed close to a non-display surface of the display screen. The fingerprint sensor is configured to receive an optical signal transmitted through the display screen and the first lens module to collect fingerprint information. The first driving mechanism is configured to drive the first lens module to move, so as to change a fingerprint information collection area of the fingerprint sensor.

Abstract: An image processing device outputs, by using a result of machine learning, an image including three or more gradations and indicating a central line in response to an input of a fingerprint image, the machine learning being performed by using data including at least a fingerprint image, central line information indicating a central line in the fingerprint image, and zone information indicating a zone that is a portion of the fingerprint image which is effective for fingerprint collation, and generates a binary central line image based on the output image.

Abstract: Provided is a method for determining a match between a candidate fingerprint and a reference fingerprint characterized by minutiae local features. The method includes evaluating a similarity of the candidate fingerprint local feature and the reference fingerprint local feature of a current local feature pair, and determining a match depending on the similarity evaluation and geometric coherence evaluations performed for said current local feature pair. Other embodiments are disclosed.

Abstract: A computer system obtains a digital 3-dimensional model of a body surface, such as a human face. Portions of the surface correspond to reference points in the model. The system obtains image data of a personal care device in use as well as image data of the surface on which the model is based. The system calculates a relative location of the device relative to the reference points based on the image data of the surface. The system determines a true position of the device with respect to the surface based on the image data of the device in use, known physical dimensions of the device, and its relative location, even when the device is partially occluded from view. The system may, based on the true position of the device, cause device to perform actions such as application of a cosmetic or administration of a skin therapy.

Abstract: Example aspects include a method, an apparatus and a computer-readable medium of enforcing a mask wearing rule, comprising monitoring video frames of one or more video feeds. The aspects further include detecting a person in at least one video frame of the video frames. The at least one video frame corresponding to a first area of one or more areas. Additionally, the aspects further include determining whether the person is in violation of a mask wearing rule. Additionally, the aspects further include generating an alert in response to determining that the person is in violation of the mask wearing rule.

Abstract: System and method for training a human perception predictor to determine level of perceived similarity between data samples, the method including: receiving at least one media file, determining at least one identification region for each media file, applying at least one transformation on each identification region for each media file until at least one modified media file is created, receiving input regarding similarity between each modified media file and the corresponding received media file, and training a machine learning model with an objective function configured to predict similarity between media files by a human observer in accordance with the received input.

Abstract: The present application relates to the field of data processing, and provides a method for deploying a face sample library, and a method and an apparatus for business processing based on face recognition. The method for deploying a face sample library, comprises: obtaining historical business information of users corresponding to face samples in a password face sample library under a condition that a number of face samples in the password face sample library is greater than or equal to a preset sample number threshold, wherein confidential business passwords of the users corresponding to the face samples in the same password face sample library are the same; dividing the password face sample library to obtain M levels of face sample sub-libraries according to the historical business information, where M is a positive integer. Use of the technical solution of the present application improves the accuracy of business processing using face recognition.

Abstract: A method and an apparatus for connecting through on-vehicle Bluetooth, and a storage medium includes: acquiring a first face image of a driver in response to an on-vehicle Bluetooth apparatus being on; determining a first face identifier corresponding to the driver by performing face recognition on the first face image; querying a first correspondence according to the first face identifier, in which the first correspondence indicates a correspondence between face identifiers and Bluetooth identifiers of terminals; in response to determining a first Bluetooth identifier matching the first face identifier, establishing, according to the first Bluetooth identifier, a Bluetooth connection between the on-vehicle Bluetooth apparatus and a first terminal Bluetooth apparatus corresponding to the first Bluetooth identifier.

Abstract: The present disclosure provides a method and device to process identity information based on a fundus image. An identity information comparison method includes: recognizing a fundus image by using a neural network to obtain a multi-dimensional feature vector representing the identity of a user; comparing the obtained multi-dimensional feature vector with each multi-dimensional feature vector stored in a database; and determining, according to a comparison result, whether there is a matching between the currently obtained multi-dimensional feature vector and a multi-dimensional feature vector pre-stored in the database.

Abstract: The disclosure includes a method and system for checking in baggage of a passenger. The method includes electronically acquiring, by at least one electronic acquiring device, an originating hardcopy bag tag identifier (OP-BTI) associated with or printed on a printed bag tag from an originating airline travel carrier that is on a luggage item of a passenger. This creates a digital BTI data record linked to the airline travel carrier. The method includes utilizing, by at least one processor, the OP-BTI as a unique identifier to query a database to retrieve return flight data of the passenger. The method includes checking in, by the at least one processor, each luggage item for the passenger for the return flight with a return flight travel carrier identified in the retrieved return flight data.

Abstract: Systems and methods which utilize gravity feed for mail item movement in postage metering operations are shown. Embodiments provide for gravity drop feeding mail items into a portion of a postage metering system for metering operations, such as to activate or apply postage indicia thereto. Embodiments provide for gravity drop exit of mail items from a portion of a postage metering system after metering operations, such as activation or application of postage indicia thereto. Postage metering operations as performed by embodiments of the invention may comprise scanning and activation of preprinted tokens. Postage metering operations according to alternative embodiments of the invention may printing postage indicia. Embodiments provide processing in addition to or in the alternative to the aforementioned postage indicia activation or printing and mail item marking operations, such as weighing, sorting, etc.

Abstract: In some examples, a data processing system can be configured to mount on a vehicle and configured to receive sensor data from a sensor on the vehicle, wherein the sensor data indicates a contamination level of a supply air for the vehicle; receive context data from another system on the vehicle; and generate a recommended maintenance item to be performed on the vehicle based on the sensor data and further based on the context data.

Abstract: Systems and methods for monitoring and analyzing vehicle data within a vehicle and providing analytical processing data to prospective users of vehicles are disclosed. In one embodiment, a method is disclosed comprising monitoring a communications bus installed within a vehicle, the communications bus transmitting data recorded by one or more sensors installed within the vehicle; detecting a message broadcast on the communications bus; extracting an event from the message, the extraction based on a pre-defined list of event types; storing the event in a secure storage device installed within the vehicle; determining that a transfer condition has occurred; and transferring the event data to a remote server in response to determining that the transfer condition has occurred.

Abstract: Disclosed herein is a product inspection apparatus that may include an electronic device having a visual inspection software application. The visual inspection software application may activate a camera of the electronic device to capture images of a product, such as a vehicle. A display screen of the electronic device may present product images. The product images may be digitally processed, and augmented by the addition of computer-generated images associated with a status of inspection of each element of the vehicle in the product images. Each computer-generated image may include a graphical indicator associated with the status of inspection of a particular element. Each computer-generated image may be projected on top of a real world image of the particular element presented on the display screen.

Abstract: A method of setting an operational authority for an electric motorcycle is proposed, the method including a product registration step of pre-registering mapping information of an ID of an electric motorcycle and manager information in a management server; a manager registration step of completing manager registration with the electric motorcycle using the mapping information when the management server receives the ID from the electric motorcycle; a driver registration step of performing driver registration in the electric motorcycle through pairing with the electric motorcycle, when the management server receives driver information from a driver terminal; and an operational authority registration step of completing, when the management server receives a registration request for operational authority information from a manager terminal, a registration of the operational authority information for the electric motorcycle through pairing with the electric motorcycle, by the driver terminal, using the operational

Abstract: A diagnostic system and method for troubleshooting an electronic system of a vehicle includes receiving a diagnostic trouble code set into a diagnostic system. The diagnostic trouble code set includes one or more diagnostic trouble codes. The method includes receiving diagnostic specifications. The diagnostic specifications associate connector pins and wires of the electronic system with possible diagnostic trouble codes. The method includes receiving wiring circuit specifications. The wiring circuit specifications associate wiring circuits of the electronic system with the connectors of the electronic system. The method includes determining a set of possible repair locations based on the diagnostic trouble code set, the diagnostic specifications, and the wiring circuit specifications, and displaying at least one possible repair location of the set of possible repair locations.

Abstract: A performance system can enable an untrained end user to analyze the performance of a vehicle based on performance data that the vehicle's ECU generates. The performance system can include a performance tool that is configured to request performance data from one or more ECUs of a vehicle. The performance system can also include a performance engine that interfaces with the performance tool to create a log of the performance data. The performance engine can be configured to process the performance data log to generate a number of performance values which correspond to performance parameters. The performance engine can then use the performance values to generate performance representations which can then be presented to the end user.

Abstract: An autonomous vehicle (AV) including a vehicle body, and a vehicle computing device is provided. The vehicle computing device includes a processor in communication with a memory device. The processor is configured to identify a time and a geographic location of a traffic collision involving the AV, retrieve map data and contextual data associated with the time and the geographic location of the traffic collision, retrieve vehicle telematics data collected by sensors coupled to the vehicle body, determine for each of a plurality of moments in time during the traffic collision a position and an orientation of the AV during the traffic collision, generate a simulation of the traffic collision including a representation of the AV based upon the map data, the contextual data, and the vehicle telematics data, and provide content to enable display of the simulation on a display device.

Abstract: First data indicating performance of authentication that is performed by a first apparatus that performs authentication based on an electronic key acquired from a mobile apparatus is acquired, and second data including an operation command for a second apparatus is generated based on the first data, and the second data is transmitted to the second apparatus.

Abstract: In accordance with a first aspect of the present disclosure, a communication node is provided, comprising: an ultra-wideband (UWB) communication unit configured to enable UWB communication with a plurality of external communication nodes; a processing unit configured to perform ranging sessions between the communication node and said external communication nodes, wherein said ranging sessions comprise one or more distance measurements based on messages exchanged through the UWB communication unit between the communication node and said external communication nodes; and a prioritization unit configured to prioritize said ranging sessions in dependence on at least one previously measured distance between the communication node and the respective external communication nodes. In accordance with a second aspect of the present disclosure, a method of operating a communication node is provided.

Abstract: A face authentication machine includes a face image acquirer (camera) that acquires a live image of a predetermined capturing area in a facility including a face image of a user; a display unit (display) that displays a progress of face authentication of the face image included in the live image acquired by the face image acquirer; and a processor (controller) that controls the face image acquirer and the display unit, in which the processor sequentially displays two or more notification screens indicating the progress on the display unit, when the user is detected from the live image.

Abstract: The invention concerns a system (1) to provide access to premises (P1-P4) that comprise entrances (E1.1, E1.2, E2-E4) locked by means of electromechanical key locks (L1.1, L1.2, L2-L4), which for locking and unlocking are powered by insertion and actuation of at least one programmable key (24). In said system (1) an administrator (10) contacts a service unit (20) in possession of a programmable key (24) and provides it with synchronization data (13) for an electromechanical key lock (L1.2) of at least one entrance (E1.1) of at least one premise (P1) at an exact geographic position of a site (S).

Abstract: The present disclosure generally relates to providing electronic locking systems. Using novel designs and network technology, the present systems, methods, and apparatuses can provide a secure alternative to a cam lock or a lock box for storing items that may be left unattended, without the use of a physical key. For example, in certain embodiments, the present systems, methods, and apparatuses can facilitate the locking and unlocking of a cam lock or a lock box by using a digital construct, an encryption system, and various native and/or third-party software components.

Abstract: Evaluation rooms (or fitting rooms) at a clothing store include replenishment closets that are accessible to customers and associates of the clothing store, albeit not at the same time. Doors of evaluation rooms include access control systems with interlocks that govern operation of the respective doors. Before an associate opens a first door between an exterior of an evaluation room and a closet to place an item therein, a second door between an interior of the evaluation room and the closet is locked. After the associate places the item in the closet, the first door is closed and locked, and the second door is unlocked, enabling the customer to open the second door and retrieve the item. Feedback indicating that items are being staged in a closet, or that items are staged therein and the closet is accessible to a customer, is provided to the customer within the evaluation room.

Abstract: A booth includes an openable door and a locking mechanism that locks the door. The door is locked in a case where the door is closed, and the door is not locked in a case where a predetermined condition is satisfied.

Abstract: This disclosure describes techniques for selectively providing access to a physical space. An example method includes identifying a location of a device associated with an authorized user based on an electromagnetic signal received by at least one sensor from the device. The electromagnetic signal has a frequency that is greater than or equal to 24 gigahertz (GHz). The example method further includes determining that the location of the device is within a threshold distance of a location of a threshold to a secured space and determining that an authentication score indicating that an individual carrying the device is the authorized user is greater than a threshold score. The authentication score is associated with multiple authentication factors identified by the device. Based on determining that the authentication score is greater than the threshold score, the threshold is unlocked and/or opened.

Abstract: A wireless electronic lockset comprising a processing unit, a locking bolt, a motor, a wireless communication tag, and a wireless interface is disclosed. The lockset is capable of connecting to a mobile device via a first communication protocol and/or a second communication protocol. The lockset sends a value to the mobile device via the first communication protocol and receives an actuation command via the second communication protocol if the mobile device has been verified by a server. The actuation command causes the lockset to lock or unlock the door.

Abstract: Disclosed are gaming systems, methods and machines that include one or more modular buttons. In particular, a modular button is configured for mounting within a frame or panel. The modular button may be interchangeable, such that various modular buttons may be added, exchanged, and/or removed from the frame. In some examples, the frame may be formed of a metal or other structural material. In some examples, the frame may be formed within a surface of another system, such as a bar-top, a gaming table, or an EGM, as a non-limiting listing of examples. The modular buttons include devices and/or circuitry to enable wireless transfer of power and/or communications.

Abstract: An electronic gaming machine architecture is provided in which a gaming platform application and wagering game applications are executed in separate processes but may share access to common display windows; such display windows may be caused to be generated by the gaming platform application, which may then assign specific display windows to the various wagering game applications, along with window handles usable to direct graphical content thereto. The wagering game applications may then direct graphical content to the display windows, while the gaming platform application may retain control over the size, position, transparency, and/or z-order of the display windows.