Abstract: A method of tracking objects of a scene is disclosed. The method determines two or more tracks which have merged. Each track is associated with at least one of the objects and having a corresponding graph structure. Each graph structure comprising at least one node representing the corresponding track. A new node representing the merged tracks is created. The graph structures are added as children nodes of the new node to create a merged graph structure. A split between the objects associated with one of the tracks represented by the nodes of the merged graph structure is determined. Similarity between one or more of the nodes in the merged graph structure and foreground areas corresponding to split objects is determined. One of the nodes in the merged graph structure is selected based on the determined similarity. A new graph structure for tracking the objects is created, the new graph structure having the selected node at the root of the new graph structure.

Abstract: A method for automatically determining a dynamic queue configuration includes acquiring a series of frames from an image source surveying a queue area. The method includes detecting at least one subject in a frame. The method includes tracking locations of each detected subject across the series of frames. The method includes generating calibrated tracking data by mapping the tracking locations to a predefined coordinate system. The method includes localizing a queue configuration descriptor based on the tracking data.

Abstract: An image recognition system and method for a vehicle, including at least two camera units, each being configured to record an image of a road in the vicinity of the vehicle and to provide image data representing the respective image of the road, a first image processor configured to combine the image data provided by the at least two camera units into a first top-view image. The first top-view image is aligned to a road image plane, a first feature extractor configured to extract lines from the first top-view image, a second feature extractor configured to extract an optical flow from the first top-view image and a second top-view image, generated before the first top-view image by the first image processor, and a curb detector configured to detect curbs in the road based on the extracted lines and the extracted optical flow and provide curb data representing the detected curbs.

Abstract: A device includes an illumination device that casts light of a prescribed polarization direction on a scattering body, a camera that picks up images of the scattering body at a plurality of different polarization angles, and a processor that executes a process of generating and outputting an inner layer image, of an inner layer of an inside of the scattering body, in response to a depth from a surface of the scattering body on the basis of the images of the scattering body picked up at the plurality of different polarization angles.

Abstract: A method for authenticating an object, comprising determining a physical dispersion pattern of a set of elements, determining a physical characteristic of the set of elements which is distinct from a physical characteristic producible by a transfer printing technology, determining a digital code associated with the object defining the physical dispersion pattern, and authenticating the object by verifying a correspondence of the digital code with the physical dispersion pattern, and verifying the physical characteristic.

Abstract: Implementations generally relate to producing a still image from a video or series of continuous frames. In some implementations, a method includes receiving the frames that a capture device shot while moving in at least two dimensions. The method further includes analyzing the frames to determine changes of positions of objects in at least two of the frames due to movement of the objects in the scene relative to changes of positions of objects due to the movement of the capture device during the shoot time. The method further includes determining, based at least in part on the variability of the objects, one or more target subjects which the capture device captures during the shoot time. One or more still images are generated from the plurality of frames having at least a portion of the target subject.

Abstract: An image segmentation threshold value determining method, comprising: defining a plurality of image regions of a first sensing image; determining a first, a second part image segmentation threshold values according to a first, second image regions of the image regions; performing a first, a second image segmentation operation to the first sensing image according to the first, the second part image segmentation threshold values to acquire a first, a second segmented images; and selecting one of the first part image segmentation threshold value and the second part image segmentation threshold value as the first image segmentation threshold value according to the first segmented image and the second segmented image.

Abstract: A method of extracting a bed area of a bed performed by a computer, includes detecting linear edges which remain stationary among plural images; and selecting a bed area candidate based on lengths of the linear edges and angles between the linear edges which cross to each other in a U shape formed as combinations of the detected linear edges.

Abstract: An objective assessment method for a color image quality based on online manifold learning considers a relationship between a saliency and an image quality objective assessment. Through a visual saliency detection algorithm, saliency maps of a reference image and a distorted image are obtained for further obtaining a maximum fusion saliency map. Based on maximum saliencies of image blocks in the maximum fusion saliency map, a saliency difference between each reference image block and a corresponding distorted image block is measured through an absolute difference, and thus reference visual important image blocks and distorted visual important image blocks are screened and extracted. Through manifold eigenvectors of the reference visual important image blocks and the distorted visual important image blocks, an objective quality assessment value of the distorted image is calculated.

Abstract: In a case where a specific point is designated on a map, extracted structure data, which is data of structures contained in an extraction range defined in advance with respect to the specific point as a datum, is extracted from map data. In a case where multiple extracted structure data items are extracted, at least one structure, the evaluated value of which is different from evaluated values of other structures by a selection threshold value or greater for a selection index, is selected as a landmark structure. A three-dimensional map image containing at least a road image and a structure image is displayed on a display screen in an emphasized manner such that the selected landmark structure offers visibility higher than visibility non-emphasized structures.

Abstract: Method for coding or recognizing of surveillance videos is provided to improve compressing efficiency and recognizing accuracy of surveillance videos. The method for coding surveillance videos includes: establishing a background database and a foreground object database; wherein, the background database includes a set of background images; the foreground object database includes a set of foreground objects; coding a surveillance image by referring to a background image in the background database and a foreground object in the foreground object database.

Abstract: A fast object detection method based on deformable part model (DPM) is provided. The method includes importing a trained classifier for object detection, receiving an image frame from a plurality of frames in a video captured by a camera, and identifying regions possibly containing at least one object via objectness measure based on Binarized Normed Gradients (BING). The method also includes calculating Histogram of Oriented Gradients (HOG) feature pyramid of the image frame, performing DPM detection for the identified regions possibly containing the at least one object, and labeling the at least one detected object using at least one rectangle box via non-maximum suppression (NMS). Further, the method includes processing a next frame from the plurality of frames in the captured video until the video ends and outputting object detection results.

Abstract: The present disclosure is directed toward systems and methods that enable more accurate digital object classification. In particular, disclosed systems and methods address inaccuracies in digital object classification introduced by variations in classification scores. Specifically, in one or more embodiments, disclosed systems and methods generate probability functions utilizing digital test objects and transform classifications scores into normalized classification scores utilizing probability functions. Disclosed systems and methods utilize normalized classification scores to more accurately classify and identify digital objects in a variety of applications.

Abstract: A traffic lane boundary line extraction apparatus includes: an image-data-acquiring-unit configured to acquire vehicle outside image data captured by a travelling vehicle; a candidate-area-detection-unit configured to detect a candidate area of a traffic lane boundary line from a road surface part of the vehicle outside image data; a road-surface-area-setting-unit configured to set a road surface area corresponding to the candidate area in the road surface part of the vehicle outside image data for each of the candidate area; a luminance-calculation-unit configured to calculate a representative luminance of the candidate area, and a representative luminance of the road surface area; and if a difference between the representative luminance of the candidate area and the representative luminance of the road surface area is greater than a predetermined threshold value, a candidate area evaluation unit configured to evaluate that the candidate area is suitable for the traffic lane boundary line.

Abstract: An image forming apparatus includes a storage unit that stores a plurality of print jobs, an acquisition unit that acquires, when a desired print job is selected from the plurality of print jobs stored in the storage unit, a print setting of the selected print job, a determination unit that determines whether a print-cost-reducing print setting exists that reduces a print cost more than a print cost of the print setting acquired by the acquisition unit, and a changing unit that, if it is determined that the print-cost-reducing setting exists, enables changing the print setting of the selected print job to the print-cost-reducing print setting.

Abstract: A method of generating a region-based representation of a document is disclosed. A global compositing sequence is generated based on a predetermined rule, using fill data and at least one compositing operation associated with a plurality of objects of the document, to form an object-based representation of the document. The region-based representation of the document is generated based on a further compositing sequence determined for regions formed using the object-based representation. The method also determines whether at least one of the regions satisfies the predetermined rule using a relative arrangement of the objects in the object-based representation. Where the region satisfies the predetermined rule, a reference to the global compositing sequence is created. Where the region does not satisfy the predetermined rule, a local compositing sequence is generated using fill data and compositing operations associated with the objects contributing to the region.

Abstract: An image processing apparatus includes an image analyzing unit, a tone-curve generating unit, and an image correcting unit. The image analyzing unit acquires a model parameter by modeling data distribution of an image with a probability distribution model. The tone-curve generating unit generates a tone curve on the basis of control information in which the model parameter acquired by modeling the data distribution of the image to be processed is associated with a target value of the model parameter. The image correcting unit corrects the image to be processed by using the generated tone curve.

Abstract: An image printing method and printer is provided. The method comprises obtaining an original data file of an image to be printed from a database; dividing the original data file into a plurality of first data files and storing the first data files in a plurality of first memory blocks correspondingly; receiving an image printing request, the image printing request carrying first position information of the image to be printed; determining from its position information of the image to be printed second position information contained in the first position information, and filling a first data file corresponding to the second position information to a second memory block from the first memory block where the first data file is located through memory mapping mechanism to form a second data file to be printed; and printing and outputting the second data file in the second memory block.

Abstract: Example systems and related methods may relate to processing and printing print data in the case of an error. Namely, a printing device may include a communication interface and a controller. The controller includes a processor configured to execute instructions. The instructions include receiving multi-page print data in a first file format via a communication interface. The instructions also include when an error condition is determined during print data processing, responsively transmitting an error message via the communication interface and storing an error page location. The instructions further include receiving the print data in a second file format and determining a remainder portion and a discard portion of the print data in the second file format based on the error page location. The instructions further include processing the remainder portion of the print data in the second file format.

Abstract: A system is provided for integrating conformal electronics devices into apparel. The system includes a flexible substrate onto which a flexible device is disposed. The flexible device can include a stretchable coil that can be used to receive and transmit near field communications. The flexible device also includes an integrated circuit component and a memory unit. In some examples, the device also includes a sensor that is configured to record measurement of the wearer of the apparel and/or the surrounding environment.

Abstract: A vehicle identification card is provided to an insured that includes proof of automotive insurance information and charge account information. The card may include an insurance policy covering the insured's vehicle, the VIN number of the vehicle, and other information about the vehicle such as the vehicle's make and model. The card may include account information that allows the card to be used like a credit card. The card may further include means for wirelessly updating information and providing a display to the user, which includes, but is not limited to, a housing, a memory module, a processor, one or more displays, and a power source.

Abstract: A memory card includes a memory that stores data, a driver that transmits the data received from the memory, and at least one transmitter that transmits the data received from the driver to a receiver provided in an external main unit. The driver and the transmitter are provided in a single IC (Integrated Circuit) chip and are not overlapped with each other in planar view, and the transmitter includes a coil.

Abstract: Various exemplary embodiments relate to a method performed by an RFID tag, the method including: receiving a request for a EPC serial number; determining whether the EPC serial number has a preset value; when the EPC serial number has the preset value, mapping a transponder ID to the EPC serial number; and providing the EPC serial number in response to the RFID read request.

Abstract: RFID inlays or straps may be assembled using impulse heating of metal precursors. Metal precursors are applied to and/or included in contacts on an RFID IC and/or terminals on a substrate. During assembly of the tag, the IC is disposed onto the substrate such that the IC contacts physically contact either the substrate terminals or metal precursors that in turn physically contact the substrate terminals. Impulse heating is then used to rapidly apply heat to the metal precursors, processing them into metallic structures that electrically couple the IC contacts to the substrate terminals.

Abstract: An antenna device includes a first coil and a second coil whose winding axes are parallel or substantially parallel, are disposed so as to be insulated from each other, and that magnetically couple with each other; a first capacitance that is connected in parallel to the first coil and defines a first resonance circuit with the first coil; a second capacitance that is connected in parallel to the second coil and defines a second resonance circuit with the second coil; a third capacitance connected between at least one set of ends of the first coil and the second coil; and a power supply terminal connected to the first coil.

Abstract: A wireless (e.g., near field or RF) communication device, and methods of manufacturing and using the same are disclosed. The wireless communication device includes a receiver and/or transmitter, a substrate with an antenna thereon, an integrated circuit, and one or more protection lines. The antenna receives and/or transmits or broadcasts a wireless signal. The integrated circuit processes the wireless signal and/or information therefrom, and/or generates the wireless signal and/or information therefor. The integrated circuit has a first set of terminals electrically connected to the antenna. The protection line(s) are on a common or different substrate as the antenna. The protection line(s) sense or determine a continuity state of a package or container on which the communication device is placed or to which the communication device is fixed or adhered, and are electrically connected to a second set of terminals of the integrated circuit different from the first set of terminals.

Abstract: An “Interestingness Modeler” uses deep neural networks to learn deep semantic models (DSM) of “interestingness.” The DSM, consisting of two branches of deep neural networks or their convolutional versions, identifies and predicts target documents that would interest users reading source documents. The learned model observes, identifies, and detects naturally occurring signals of interestingness in click transitions between source and target documents derived from web browser logs. Interestingness is modeled with deep neural networks that map source-target document pairs to feature vectors in a latent space, trained on document transitions in view of a “context” and optional “focus” of source and target documents. Network parameters are learned to minimize distances between source documents and their corresponding “interesting” targets in that space.

Abstract: A computer-implemented method that includes receiving, by a processing unit, an instruction that specifies data values for performing a tensor computation. In response to receiving the instruction, the method may include, performing, by the processing unit, the tensor computation by executing a loop nest comprising a plurality of loops, wherein a structure of the loop nest is defined based on one or more of the data values of the instruction. The tensor computation can be at least a portion of a computation of a neural network layer. The data values specified by the instruction may comprise a value that specifies a type of the neural network layer, and the structure of the loop nest can be defined at least in part by the type of the neural network layer.

Abstract: The present invention provides a semiconductor circuit for emulating neuron firing process having a floating body device instead of the conventional capacitor. By using a floating body to store excess holes generated by impact ionization, it is possible to emulate signal accumulation of a neuron, trigger firing when the storage is in excess of a predetermined threshold value, and return to an original state after the firing.

Abstract: A system for utilizing a neural network to make real-time predictions about the health, reliability, and performance of a monitored system are disclosed. The system includes a data acquisition component, a power analytics server and a client terminal. The data acquisition component acquires real-time data output from the electrical system. The power analytics server is comprised of a virtual system modeling engine, an analytics engine, an adaptive prediction engine. The virtual system modeling engine generates predicted data output for the electrical system. The analytics engine monitors real-time data output and predicted data output of the electrical system. The adaptive prediction engine can be configured to forecast an aspect of the monitored system using a neural network algorithm.

Abstract: Semantic class localization techniques and systems are described. In one or more implementation, a technique is employed to back communicate relevancies of aggregations back through layers of a neural network. Through use of these relevancies, activation relevancy maps are created that describe relevancy of portions of the image to the classification of the image as corresponding to a semantic class. In this way, the semantic class is localized to portions of the image. This may be performed through communication of positive and not negative relevancies, use of contrastive attention maps to different between semantic classes and even within a same semantic class through use of a self-contrastive technique.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for predicting object identity using an ensemble of predictors. In one aspect, a method includes selecting candidate objects that likely match a received object that is to be identified, from a database of objects, and providing attributes of the received object compared with those of the candidates to an ensemble of predictors having respective properties. Based on previous training, each predictor can predict a most likely candidate. From among the most likely candidates, a previously trained support vector machine can select a potential match candidate. If a score that the support vector machine associates with the potential match candidate, that is representative of the potential match candidate's likelihood to match the received candidate satisfies a threshold, then the potential match candidate can be determined to be the received candidate.

Abstract: A method and system for predicting a next navigation event are described. Aspects of the disclosure minimize the delay between a navigation event and a network response by predicting the next navigation event. The system and method may then prerender content associated with the next navigation event. For example, the method and system may predict a likely next uniform resource locator during web browsing to preemptively request content from the network before the user selects the corresponding link on a web page. The methods describe a variety of manners of predicting the next navigation event, including examining individual and aggregate historical data, text entry prediction, and cursor input monitoring.

Abstract: Methods and systems for facilitating interactions between a robot and user are provided. The system may include a robot and an electronic device communicatively coupled to the robot.

Abstract: A computer-implemented method of evaluating information confidence based on a cognitive trait of a user, is provided, the method including receiving information from a user as an answer to a question in an active learning question and answer system; monitoring a user for a cognitive behavior indicator when the user is providing the information; determining a cognitive trait based on the cognitive behavior indicator; determining a quantified level of information confidence for the information based on the cognitive trait; and annotating the information with the cognitive trait and the quantified level of information confidence. A system and a computer program product for evaluating information confidence based on a cognitive behavior of a user are also provided.

Abstract: The disclosure provides an approach for recognizing and analyzing activities. In one embodiment, a learning application trains parameters of a hierarchical model which represents human (or object) activity at multiple levels of detail. Higher levels of detail may consider more context, and vice versa. Further, learning may be optimized for a user-preferred type of inference by adjusting a learning criterion. An inference application may use the trained model to answer queries about variable(s) at any level of detail. In one embodiment, the inference application may determine scores for each possible value of the query variable by finding the best hierarchical event representation that maximizes a scoring function while fixing the value of the query variable to its possible values. Here, the inference application may approximately determine the best hierarchical event representation by iteratively optimizing one level-of-detail variable at a time while fixing other level-of-detail variables, until convergence.

Abstract: A method, system and computer-readable medium for analyzing contact studies for a call service center is presented. The method includes the steps of: acquiring data instances of a Collector tool from all persons monitoring contacts at a call service center during a given study period; retrieving a study design from a Planner tool to verify that acquired data instances conform to the study design; selecting data parameters for the acquired data instances, wherein the data parameters describe multiple features of the acquired data; automatically selecting an appropriate chart format that is appropriate for measurement units used by the data parameters; and creating a chart using the appropriate chart format and the data parameters. The steps in the method may all be automatically performed by an Analyzer logic.

Abstract: A system including a centralized organizational information system in communication with a centralized organizational information database and an entitlement generator in communication with the centralized organizational information system, wherein the entitlement generator is configured to automatically generate at least one executable entitlement rule based on an input rule. The system also includes a federated set of entitlements engines in communication with the entitlement generator and a plurality of entitlement databases, wherein each of the entitlements engines is for determining whether a user is entitled to access secured resources requested by the user based on the executable entitlement rule.

Abstract: A method of exchanging water allocation credits comprises accessing data describing a water allocation credit reserved for a first user. An unused amount of the water allocation credit which will not be used by the first user is then determined. A sale is then brokered of the unused amount of the water allocation credit to another user.

Abstract: A system and method for providing an editor for use with a business process design environment. In accordance with an embodiment, the system provides an editor and framework that allows a user to create and edit business processes and business architecture projects. The editor can render or edit a model which is based on a metamodel or defined ontology, and can be provided, e.g., in computer applications, browsers and tablets. In accordance with an embodiment, the user can use the editor to define a business process and/or a business architecture project, including attributes such as goals, objectives, strategies, and value chains. Models can be synchronized as part of an overall business process development.

Abstract: Subject matter described herein is related to providing a consolidated schedule having event entries that originate from disparate systems. For example, a central repository receives event entries from a plurality of disparate systems and aggregates entries associated with a particular clinician. The aggregated entries are transformed into a consolidated schedule, which is provided to a client device (e.g., mobile computing device or desktop computing device) used by the healthcare clinician (e.g., doctor, nurse, physician assistant, nurse practitioner, etc.). The consolidated schedule includes events scheduled to take place at different healthcare facilities or different departments within a healthcare facility. When viewing the consolidated schedule, the clinician can request patient information (e.g., vital statistics) relevant to a selected entry and execute other actions (e.g., rescheduling, note entry, event creation, etc.) relevant to the entry.

Abstract: A user interface guides an interview of a print service provider (PSP) to generate interview data regarding the PSP. The interview data regarding the PSP is translated into simulation experiments regarding printing production services offerable by the PSP. The simulation results are concurrently executed to generate simulation results. The simulation results are synthesized to generate capacity planning analyses and recommendations for the PSP reviewable within the user interface.

Abstract: A product delivery inspection system includes an ordering-side terminal, an order-receiving-side terminal, an order-receiving-side handy terminal, a container, and an ordering-side handy terminal. The order-receiving-side handy terminal has an order-receiving-side reception means, a barcode reading means, a tag writing means, an order-receiving-side comparison means, and an order-receiving-side display instruction means that transmits to a display unit an instruction to display a message or a symbol indicative of the completion of an order-receiving-side product inspection. The ordering-side handy terminal has an ordering-side reception means, a tag reading means, an ordering-side comparison means, and an ordering-side display instruction means that transmits to the display unit an instruction to display a message or a symbol indicative of the completion of an ordering-side product inspection.

Abstract: A system and method that combines content with one or more canvas products to provide finished products for dissemination to end customers is provided. More specifically, a system and method are provided to enable a content provider to select one or more canvas products to which content would be applied, whereby the content provider may then provide web links on any of a multitude of locations to redirect an end customer to a canvas product center and/or fulfillment center to acquire finished products having content thereon. The finished product is customizable for and by any one or more content providers for a unique appearance and offering to end customers. Content providers are able to leverage the infrastructure, network and benefits of a third party while enjoying the ease of setup, minimal up-front costs and eliminate the need to invest in or carry an inventory of finished products.

Abstract: Systems, methods, and computer-readable media are disclosed for optimizing power consumption for smart electronic tracking tags. Example methods may include determining a destination address for a package, determining a shipping timeline for the package, the shipping timeline having a first segment and a second segment, and determining a transmission profile with a first frequency of package information data transmissions during the first segment and a second frequency of package information data transmissions during the second segment. Example methods may include sending the transmission profile to an electronic shipping tag associated with the package.

Abstract: Tracking and associating consumable components with the respective pieces of wellbore servicing equipment to which they are coupled may include using identifier tags coupled to each piece of wellbore servicing equipment and to each consumable component. An identifier tag reader may be used to read both the identifier tag of the piece of wellbore servicing equipment and the identifier tag of the consumable component, thereby enabling association of the consumable component to the piece of wellbore servicing equipment to which it is coupled, for the duration of such coupling. Such association may be carried out and/or tracked in one or more databases, wherein other information pertaining to either piece of equipment may be associated with both pieces of equipment. In addition, usable life spans of consumable components may be more easily determined based at least in part on such association.

Abstract: The present disclosure is directed at systems, methods, and apparatus for precisely inventorying items placed within a user-portable container. The system may comprise one or more interrogators configured to repeatedly send interrogation signals to detect tagged items placed within the portable container by a user. The system may also comprise one or more readers configured to detect response signals produced by the tagged items in response to the repeated interrogation signals. The system may also comprise a communication interface configured to provide information regarding the detected response signals to an adjunct processor configured to analyze the signals and determine whether they originate from items within the user-portable container, as well as to maintain an inventory of items within the portable container.

Abstract: A barcode scanner device 200 is formed as a wrist watch with a main body 210 and strap 220 and includes a camera 211 to capture an image of a barcode 11. The scanner 200 generates an inventory request message sent by a communication interface 215 to a local server 30 based on the captured barcode. In a capture mode, live camera images may be displayed on touch-screen display 212 while capturing the barcode with guides and feedback for the user. In a display mode, inventory data from database 32 may be accessed in a large data field on the touch screen display 212.

Abstract: A system and method for facilitating the transfer of contact information between network subscribers said system including at least one server coupled to the network; at least one database coupled to the server; a plurality of subscriber terminals coupled to the network wherein each subscriber's terminal is configured to send contact information associated with a subscriber to the server in response to a request by said subscriber; wherein the request causes the subscriber's terminal to compile the contact information into an electronic business card object having one or more textual fields and map the one or more textual fields of the electronic business card to one or more object attributes contained in an electronic business card object and transmit the electronic business card object to the server for storage in the database is disclosed.

Abstract: Systems and methods for remote huddle collaboration are disclosed. The huddle collaboration system may include a huddle management system which may include an authentication module, a data processing module, and a module manager, among other components. Huddle collaboration system may allow huddle members of a company to fully engage in remote huddle sessions through different kind of client computing devices, in a consistent way regardless of their location. The system may act as an alternative to traditional whiteboards, displaying, collecting, and storing information during an active huddle session, where this information may be available to the users in the form of one or more standard and/or custom sub-applications, according to the user's and/or project's requirements.