Abstract: One or more images of a sample may be split into image data split according to dyes. The sample has at least two different dyes, in particular fluorescent dyes. The method for splitting the one or more images includes providing the one or more images of the sample and inputting the one or more images into a machine learning system. The method then includes generating the image data split according to dyes from the image or the images, using the machine learning system. The machine learning system removes at least one partial structure of the sample that is present in the image data split according to dyes of more than one dye from the image data of one or more dyes.
Type:
Grant
Filed:
February 25, 2019
Date of Patent:
August 30, 2022
Assignee:
Carl Zeiss Microscopy GmbH
Inventors:
Manuel Amthor, Daniel Haase, Ingo Kleppe
Abstract: An image processing device includes circuitry. The circuitry is configured to process a background image into which a latent image is embedded, to obtain an effect to conceal the latent image. The circuitry is configured to perform color conversion of the background image to obtain a color-matching masking effect to conceal the latent image. The circuitry is configured to embed the latent image in the background image processed and converted, to generate an image embedded with the latent image.
Abstract: A digital watermarking system and method for embedding information in and extracting information from content items, such as video signals, are described. In a method for encoding or embedding information in a content item, a content item including a plurality of frames is accessed in which each of a number of elements within the frames is associated with an inter-frame difference measure representing changes in the element between two frames. Information for embedding in the content item is accessed. Symbols of the information are embedded in the content item by manipulating the inter-frame difference measure of a selected element through a number of frames using an algorithm and the information. The information is used by the algorithm to control the manipulation. The manipulated content item is output as a watermarked content item having the information embedded therein.
Abstract: The technology disclosed herein enables user guidance from gaze information obtained during a communication session while viewing a webpage. In a particular embodiment, a method includes, during a communication session between a first endpoint operated by a first user and a second endpoint operated by a second user, receiving gaze information indicating a location where the second user is looking relative to a webpage being presented to the second user at the second endpoint. The method further includes determining that the second user has been looking at the location for longer than a threshold amount of time. In response to determining that the second user has been looking at the location for longer than the threshold amount of time, the method includes notifying the first user about the second location.
Abstract: A local object classifier using a set of object definitions to perform object classification in image frames. The local object classifier is arranged to detect an object in an image frame and determine whether to transmit image data for the detected object to a remote object classifier. In response to said determining, the local object classifier is arranged to transmit image data, derived from the image data representative of the image frame, to the remote object classifier. The local object classifier is also arranged to receive object data, representative of the detected object, from the remote object classifier.
Abstract: Example methods and apparatus to detect audio engineering problems using identification of isolated watermarks are disclosed herein. Disclosed example methods include identifying, by executing an instruction with a processor, isolated watermarks in a first set of detected watermarks obtained from first media monitored at a first site. Disclosed example methods further include determining, by executing an instruction with the processor, a problem has been detected with the first media associated with the first set of detected watermarks in response to a first number of isolated watermarks identified in the first set of detected watermarks satisfying a first threshold.
Abstract: A method and device for determining a tower clearance of a wind turbine. The method includes: acquiring an image of a wind turbine in operation (S10), the image comprising the tips of blades (2) and a tower (1) of the wind turbine; determining the positions of the tips of the blades (2) of the wind turbine in the image acquired (S20); identifying the edges of the tower (1) in the image acquired (30); and calculating, on the basis of the positions of the tips of the blades (2) and the edges of the tower (1) that have been determined, the distance from the tips (2) of the blades (2) to the edges of the tower (1) to acquire a tower clearance (S40).
Abstract: An imaging system and method compensate lens distortion for an image. The system identifies lens distortion among one or more distortions, and extracts a Point Spread Function (PSF) for the lens distortion. Additionally, the system extracts a total PSF associated with total distortion in the input image and separates a PSF for the lens distortion from the total PSF. The system updates the pre-estimated kernel with the PSF of the lens distortion when a rank of the PSF matches with the predefined rank value, and one or more difference values determined between one or more singular values of the PSF and one or more singular values of the pre-estimated kernel is within a pre-defined threshold limit. Thus, quality of each output image obtained from the system may be maintained irrespective of error introduced by wear and tear on the lens of the system over a period of time.
Abstract: Cancer can be an aggressive disease. It is critical to determine the most effective patient-specific treatment quickly. Exemplary embodiments use a data-driven approach to extracting tumor information from data obtain from Whole Slide Image that is uploaded through an interface. Exemplary embodiments generate the following information about a tumor from a biopsy slide using neural networks: annotated areas of relevant tissues, molecular subtype, and expression status of an important gene and include three steps: the segmentation of tumor features; prediction of molecular subtype; and prediction of gene methylation status from a WSI.
Abstract: A method for preventing image modification, an image capturing device and an image verification method are disclosed. The image modification method includes: processing a compressed image of at least one frame to obtain feature data of the compressed image of the at least one frame; encrypting the feature data to generate a checksum; generating supplemental enhancement information, which at least includes a time parameter and the checksum; and transmitting and/or storing the supplemental enhancement information and the compressed image of the at least one frame together so as to verify authenticity of the compressed image of the at least one frame by using the supplemental enhancement information. The time parameter is a counter value of a counter in the image capturing device and the counter value continuously increases. With the above method, authenticity of image data can be verified.
Abstract: Embodiments described herein involve an auxiliary zone contributing audio to a primary zone. In an example implementation, a network media system determines that a first zone in the network media system is playing back a first type of audio content and that a second zone in the network media system is not playing back audio content. While the first zone is playing back the first type of audio content and the second zone is not playing back audio content, the network media system forms a temporarily playback configuration. In the temporary playback configuration, the first zone plays back primary audio content including full frequency range audio content and the second playback device of the second zone plays back auxiliary audio content including low frequency range audio content.
Abstract: A method for determining the validity of a parallax image, including: receiving a parallax image's captured two-dimensional image having at least three target identifiers, where at least two target identifiers are located at different depth planes in the parallax image; identifying at least three target identifiers in the parallax image's captured two-dimensional image and determining spatial relationship between at least three target identifiers in the two-dimensional image of the parallax image; comparing the spatial relationship of at least three target identifiers in the parallax image's captured two-dimensional image against a predetermined spatial relationship of at least three target identifiers that indicates authenticity; and adjudicating the authenticity of the parallax image based on the degree of difference between spatial relationship of at least three target identifiers in the parallax image's captured two-dimensional image and the predetermined spatial relationship of at least three target iden
Abstract: Methods for image segmentation, computer devices, and storage mediums. The method includes acquiring a to-be-segmented image, inputting the to-be-segmented image into an input variable of a full convolution neural network and outputting a convolution characteristic pattern; inputting the convolution characteristic pattern into an input variable of a context-switchable neural network and outputting context expression information; and generating an intermediate characteristic pattern for image segmentation according to the convolution characteristic pattern and the context expression information.
Abstract: Methods, apparatus, systems and articles of manufacture are disclosed for watermark outage detection. Example methods include evaluating an onset time and duration of a detected watermark outage based on a model of expected watermark outages to determine whether the detected watermark outage corresponds to at least one of the expected watermark outages represented in the model. Example methods further include generating an alert in response to determining the detected watermark outage does not correspond to at least one of the expected watermark outages included in the model, and suppressing the alert in response to determining the detected watermark outage corresponds to the at least one of the expected watermark outages represented in the model.
Abstract: An example operation includes one or more of generating a data frame for transmission via a controller area network (CAN) bus of a transport, the data frame comprising data stored in a plurality of fields, encoding at least one authentication bit into a value within a data field of the generated data frame, wherein the at least one authentication bit comprises a digital signature based on a predefined key for the at least one authentication bit, and transmitting the generated data frame with the at least one authentication bit that comprises the digital signature via the CAN bus.
Type:
Grant
Filed:
January 8, 2021
Date of Patent:
August 9, 2022
Assignee:
TOYOTA MOTOR NORTH AMERICA, INC.
Inventors:
Satyajit P. Patne, Edward Allen Cain, Jr., Adam Loyd Parker, Jonathan Burnham, Stephen Paul McFarland, Jr.
Abstract: Differential modulation schemes encode a data channel within host signal or noisy environment in a manner that is robust, flexible to achieve perceptual quality constraints, and provides improved data capacity. Differential arrangements enable a decoder to suppress host signal or other background signal interference when detecting, synchronizing and extracting an encoded data channel. They also enable the incorporation of implicit or explicit synchronization components, which are either formed from the data signal or are complementary to it.
Abstract: An occupant protection device for a vehicle includes a collision predictor, a main airbag, and a deployment controller. The collision predictor is configured to predict a collision of the vehicle. The main airbag is configured to deploy toward an occupant from a front of the vehicle when a collision of the vehicle is predicted by the collision predictor. The main airbag includes a first deployment part, an arm-push-away deployment part, and a second deployment part. The controller is configured to cause the main airbag to deploy toward the occupant when a collision of the vehicle is predicted by the collision predictor. The controller is configured to, when a collision of the vehicle is predicted by the collision predictor, cause the first deployment part to deploy, subsequently cause the arm-push-away deployment part to deploy to push an arm of the occupant away, and thereafter, cause the second deployment part to deploy.
Abstract: A method includes generating, by a computing device, a unique identifier (ID) based on copyright information associated with digital content, wherein the copyright information and the digital content are recorded on a blockchain of a blockchain network; identifying a plurality of color values associated with one or more color attributes of at least a portion of the digital content; and embedding the unique ID in the digital content by changing one or more color values of the plurality of color values to be representative of the unique ID, wherein the embedding produces information-embedded digital content that enables retrieval of the copyright information from the blockchain based on the unique ID, and wherein a visual difference between the digital content and the information-embedded digital content is not apparent to an unaided human eye.
Abstract: A method for assembling a computing device including initiating a board management controller of the computing device, the board management controller having at least one fuse, forming data to control a video display operatively connected to the computing device to show an image of a watermark, and modifying the computing device. The method also includes blowing the at least one fuse in response to modifying the computing device and adjusting the watermark in response to blowing the at least one fuse.
Type:
Grant
Filed:
August 21, 2019
Date of Patent:
August 9, 2022
Assignee:
Hewlett Packard Enterprise Development LP
Inventors:
Theodore F. Emerson, Luis E. Luciani, Jr., Kevin E. Boyum, Christopher M. Wesneski
Abstract: The present invention provides a function capable of detecting, with a higher degree of precision, a region that has a high probability of not having been recognized. An image processing apparatus according to the present invention is provided with: a recognition means for recognizing a product from a captured image obtained by capturing an image of a displayed product; and a detection means for detecting a region of a product that is included in the captured image but is not recognized by the recognition means, on the basis of furniture information related to furniture in which the product is displayed.
Abstract: A computer-implemented method is described. The method includes a computing system receiving an item of digital content from a user device. The computing system generates one or more labels that indicate attributes of the item of digital content. The computing system also generates one or more conversational replies to the item of digital content based on the one or more labels that indicate attributes of the item of digital content. The method also includes the computing system selecting a conversational reply from among the one or more conversational replies and providing the conversational reply for output to the user device.
Type:
Grant
Filed:
September 14, 2020
Date of Patent:
August 2, 2022
Assignee:
GOOGLE LLC
Inventors:
Ibrahim Badr, Aayush Kumar, Goekhan Hasan Bakir, Nils Grimsmo, Bianca Madalina Buisman
Abstract: A video encoding and decoding method includes determining an image block set based on one or more similar image blocks of an image block to be processed, generating an initial structure matrix of the image block set based on a pixel value of each image block in the image block set, and performing a filtering process on the initial structure matrix to obtain a reconstructed structure matrix. The reconstructed structure matrix corresponds to a reconstructed pixel value of the each image block. The filtering process includes one or more point-fixing processes. The method further includes reconstructing the each image block based on the reconstructed pixel value of the each image block.
Abstract: A control method performs a learning loop and includes acquiring first layout data generated based on a first album creation parameter from a server to which layout data generated by a user is uploaded, outputting an estimated feature value based on the first layout data, generating a second album creation parameter based on the output estimated feature value, generating third layout data based on the generated second album creation parameter and an image used for second layout data acquired from the server, and updating the first album creation parameter and the third album creation parameter based on a feature value based on the generated third layout data and a feature value based on the second layout data. When the updated album creation parameter satisfies a predetermined condition, the updated album creation parameter becomes downloadable to a terminal device of a first user.
Type:
Grant
Filed:
June 5, 2020
Date of Patent:
July 19, 2022
Assignee:
Canon Kabushiki Kaisha
Inventors:
Hiroyasu Kunieda, Shinjiro Hori, Takayuki Yamada
Abstract: A story album display method and apparatus, and relate to the field of communications technologies, so that a thematic story album can be generated. The method includes: aggregating, by a terminal, N images in a gallery based on a first dimension, where the first dimension includes a photographing time and/or a photographing location, and N>1; and removing, by the terminal, an invalid image from the N images, to obtain the story album comprising the M images, wherein the invalid image comprises an image with an invalid label, or one or more images with an image similarity greater than a threshold; and displaying, by the terminal, an album cover of a story album, where the story album includes M images in the N images, the M images are associated with a theme of the story album, and M<N.
Abstract: An artificial intelligence server for controlling a plurality of robots includes a communication unit and a processor. The communication unit is configured to communicate with the plurality of robots. The processor is configured to receive information including an operation and a deployment area corresponding to each of the plurality of robots, determine a first route corresponding to a first operation corresponding to a first robot among the plurality of robots, if the first operation corresponding to the first robot includes an operation for moving out of a first deployment area corresponding to the first robot, determine an area on the determined first route, in which at least one robot is deployed, determine an associated operation between the first robot and a second robot, wherein the second robot is deployed in the determined area, and update a second operation corresponding to the second robot or a second deployment area corresponding to the second robot, based on the determined associated operation.
Abstract: An example system to measure strain in an article includes a camera, a processor, and memory. The camera is to capture a plurality of images of the article. The processor and the memory are in selective communication with the camera. The processor and the memory are configured to determine strain in a region of the article based on a plurality of reference marks shown in the plurality of images.
Abstract: Digital watermarking is adapted for the variable data printing. A reference signal serves as a proxy for optimizing the embedding a watermark in a host image to be printed. Using the reference signal, embedding parameters are generated, which are a function of constraints such as visual quality and robustness of the machine readable data. Adjustments needed to embed a unique payload in each printed piece are generated using the embedding parameters. These adjustments are stored in a manner that enables them to be efficiently obtained and applied within the raster image processor or press during operation of the press. Various other methods, system configurations and applications are also detailed.
Type:
Grant
Filed:
February 13, 2020
Date of Patent:
July 12, 2022
Assignee:
Digimarc Corporation
Inventors:
Tomas Filler, Matthew M. Weaver, Tony F. Rodriguez, Donald Haaga
Abstract: A hair colorant selection and formulation system including one or more of a hair color analyzer operable to determine hair color of a hair sample and match the determined hair color to a color in a color space, a hair color selector operable in combination with a fiber optic hair sample to generate the color selected in a color space in the optical fibers of a fiber optic hair sample, and a hair colorant mixer which operates to mix a hair colorant, which can be individually, or in various combinations, operably coupled to one or more computing devices through one or more server computers via a network which supports a hair colorant selection and hair colorant formulation program accessible by the one or more computing devices.
Abstract: A user interface (UI) generating apparatus includes: an object recognition device configured to photograph a front or surroundings of a moving device and to recognize a real object from a photographed image; an image generator configured to create a virtual object for driving guidance of the moving device to generate an augmented real image obtained by composing the virtual object with the photographed image; and a display device configured to display the augmented reality image, wherein the image generator creates a virtual object that is changed in conjunction with a speed of the moving device, and creates a reinforcement virtual object capable of compensating the real object based on characteristics of the real object.
Type:
Grant
Filed:
September 2, 2020
Date of Patent:
July 5, 2022
Assignees:
Hyundai Motor Company, Kia Motors Corporation
Inventors:
Tae Hyun Sung, Bum Hee Chung, Paul Choo
Abstract: A computer includes a processor and a memory, the memory storing instructions executable by the processor to collect a digital image that includes a plurality of pixels with a first sensor, input a reference data string, a key data string, and a set of collected data from a second sensor into a permutation generator that outputs a watermark data string, and embed the watermark data string in the digital image at specified pixels in the plurality of pixels.
Type:
Grant
Filed:
April 1, 2020
Date of Patent:
July 5, 2022
Assignees:
Ford Global Technologies, LLC, The Regents Of The University Of Michigan
Inventors:
John Moore, Francis Obiagwu, Hafiz Malik
Abstract: An optical film including a recording surface on which a plurality of unit blocks is disposed at regular intervals. For these unit blocks, phase components of light from a reconstruction point are calculated. The recording surface includes a calculated element region provided with an array of the unit blocks for which phase components of light from the reconstruction point are calculated for reproduction of an image. A first image is a monotone reconstruction image having even brightness, and a second image is a grayscale image having brightness gradation.
Abstract: A smart control system may determine whether a user is engaged with an electronic device, capture a lip sequence of the user for a period of time in response to determining that user is engaged with the electronic device, generate reduce sequence based on the captured lip sequence, determining an application with which the user is engaged, determine a current operating state of the application with which the user is engaged, determine commands that are applicable to the current operating state of the application, and determine whether the generated reduction sequence matches a comparison sequence associated with one of the determined commands. The smart control system may send a command associated with a matching comparison sequence to the application/electronic device in response to determining that the generated reduction sequence matches a comparison sequence associated with one of the determined commands.
Abstract: Disclosed is a method for determining an authenticity of at least a portion of an audio stream of a voice call connection. In the method it is received a request for confirming an authenticity of at least portion of an audio stream of a voice call connection; detected a number of voice call connection specific watermark patterns included in the portion of the audio stream in question; and set, in accordance with a detection of the number of the voice call connection specific watermark patterns included in the portion of the audio stream, a detection result to express one of the following: i) the portion of the audio stream is authentic, ii) the portion of the audio stream is nonauthentic. Also disclosed is a network node, a computer program product and a system.
Abstract: The present invention proposes a method and associated device for inserting tuples into a watermarked database without having to remove the watermarking from all or a part of the database before inserting each tuple. To achieve this, the invention consists of storing, in watermarking metadata, the type of group or class wherein the tuples of the database have been distributed during the watermarking of the database. For each type of group or class, a rule defining a modification of the value of at least one property on which the watermarking is carried is also stored in the watermarking metadata, depending on an insertion force parameter. Each tuple to be inserted is watermarked by applying the modification rule according to the group to which the tuple belongs. Due to the rule used, the insertion of the watermarked tuple does not modify the type of group it belongs to.
Type:
Grant
Filed:
November 24, 2017
Date of Patent:
June 28, 2022
Assignee:
Institut Mines Telecom
Inventors:
Gouenou Coatrieux, Javier Franco Contreras
Abstract: A method for addressing tactical situations via tactical devices may include (i) observing, via a device associated with an operator, a tactical situation involving the operator, (ii) retrieving, from a set of data about the operator, at least one attribute of the operator that is relevant to the tactical situation, (iii) gathering at least one attribute of the environment of the tactical situation from at least one sensor device monitoring the environment, and (iv) calculating a success probability for a by the operator the addresses the tactical situation based on the at least one attribute of the operator that is relevant to the tactical situation and the at least one attribute of the environment of the tactical situation. Various other systems, and methods are also disclosed.
Abstract: An example computing system comprises a processor and a storage device holding instructions executable by the processor to receive a thermal image acquired via a thermal imaging system, each pixel of the thermal image comprising an intensity level, and generate a histogram via binning pixels by intensity level. The instructions are further executable to, based at least on the histogram, determine a subset of pixels to colorize, colorize the subset of pixels to produce a selectively colorized image, and output the selectively colorized image.
Type:
Grant
Filed:
September 21, 2020
Date of Patent:
June 28, 2022
Assignee:
Microsoft Technology Licensing, LLC
Inventors:
Erick Joseph Paul, Sean Andrew McGlynn, Raymond Kirk Price
Abstract: Method and system of automatically extracting information of a predefined type from a document is provided. The method comprises using an object detection algorithm to identify at least one segment of the document that is likely to comprise the information of the predefined type. The method further comprises building at least one bounding box corresponding to the at least one segment and if the bounding box is likely to comprise the information of the predefined type extracting the information comprised by the bounding box from the at least one bounding box.
Type:
Grant
Filed:
June 22, 2020
Date of Patent:
June 21, 2022
Assignee:
Amadeus S.A.S.
Inventors:
Sebastian Andreas Bildner, Paul Krion, Thomas Stark, Martin Christopher Stämmler, Martin Von Schledorn, Jürgen Oesterle, Renjith Karimattathil Sasidharan
Abstract: A method of extracting price text from an image set includes: obtaining input data comprising (i) a plurality of images depicting shelves supporting products, and (ii) for each of the images, a set of text regions and corresponding price text strings; registering the images to a common frame of reference; identifying a subset of the text regions having overlapping locations in the common frame of reference; selecting one of the text regions from the subset; and presenting the price text string corresponding to the one of the text regions for further processing.
Type:
Grant
Filed:
May 1, 2017
Date of Patent:
June 21, 2022
Assignee:
Symbol Technologies, LLC
Inventors:
Yan Zhang, Robert E. Beach, Bo Fu, Yan-Ming Cheng, Jordan Varley, Iaacov Coby Segall
Abstract: A method, computer-readable storage medium, and device for generating a character model. The method comprises: receiving an input image of a reference subject; processing the input image to generate a normalized image; identifying a set of features present in the normalized image, wherein each feature in the set of features corresponds to a portion of a head or body of the reference subject; for each feature in the set of features, processing at least a portion of the normalized image including the feature by a neural network model corresponding to the feature to generate a parameter vector corresponding to the feature; and combining the parameter vectors output by respective neural network models corresponding to respective features in the set of features to generate a parameterized character model corresponding to reference subject in the input image.
Type:
Grant
Filed:
April 21, 2020
Date of Patent:
June 21, 2022
Assignee:
Electronic Arts Inc.
Inventors:
Igor Borovikov, Pawel Piotr Wrotek, Mohsen Sardari, Harold Chaput, Navid Aghdaie, Kazi Zaman
Abstract: Systems and methods for generating crop yield maps are provided. In one example embodiment, a method comprises accessing data indicative of crop yield for a field area; accessing one or more data types associated with the field area, each of the data types providing a geospatial distribution of data associated with vegetation across the field area; determining a crop yield distribution for the field area; and generating a yield map for the field area based at least partially on the crop yield distribution.
Abstract: In one aspect, an illustrative methodology implementing the disclosed techniques includes, by a computing device, determining that an application process includes use of a first image and a second image, one of the first and second images being generated as part of the application process, and detecting a difference in content of the first image or the second image based on a comparison of the first and second images. The method also includes, by the computing device, revoking access to a file that includes at least one of the first and second images based on the detection of the difference in content of one of the first and second images.
Abstract: A method includes receiving data in an electronic format that describes an item, and assigning a unique identifier to the item. The data is normalized across one or more data sets of data that describe other items. The normalizing includes deriving functional and aesthetic attributes of the item based at least in part on the data that describes the item, where at least one of the derived attributes is not included in the data. The normalizing also includes programmatically mapping the attributes to a defined set of taxonomies for pre-defined attribute types. At least one other item is located in the one or more data sets having attributes that coordinate with the attributes of the item. A user interface that includes a styleboard with an image of the item and an image of the at least one other item having attributes that coordinate with attributes of the item.
Type:
Grant
Filed:
November 17, 2017
Date of Patent:
June 14, 2022
Assignee:
THE NEIMAN MARCUS GROUP LLC
Inventors:
Kristen A. Miller, Lisa M. Perrone, Sophie M. Huang
Abstract: Systems and methods are provided for impervious surface mapping of a target geographic area. The impervious surface mapping utilizes four-band imagery data and light detection and ranging (LIDAR) data collected from the target geographic area. The identified impervious surfaces can be attributed to parcels within the target geographic area for purposes of generating bills for storm water runoff to parcel owners.
Abstract: The present application discloses a method, device, and system for testing an image to assess whether the image was subject to tampering. The method includes obtaining an image, extracting residual data of the image from the image, obtaining a feature map of at least two neural layers based at least in part on the residual data of the image, obtaining a tamper probability map of the image based at least in part on the feature map, and outputting the tamper probability map or providing an indication of whether the image was subject to tampering based at least in part on the tamper probability map.
Abstract: An integrated three-dimensional display includes a recording surface which includes a calculated element region in which phase components of light from light converging points of a holographic reconstructed image are calculated, and a phase angle recorded area for recording a phase angle calculated based on the phase components. The phase angle recorded area includes a plurality of monochromatic regions having a uneven structure surface. The phase angle is recorded in an overlap area in which the calculated element region and the phase angle recorded area overlap each other. Light converges on the light converging points at specific distances from the recording surface, the specific distances being determined for the respective light converging points even when light reflected from the plurality of monochromatic regions converges.
Abstract: Methods and apparatus to generate reference signatures are disclosed. An example method includes collecting a first signature for media being presented to a plurality of households; crediting the media when the first signature matches a reference signature in a reference signature database; in response to determining that the first signature does not match a reference signature in the reference signature database and the first signature does not match an unidentified signature in an unknown signature database, storing the first signature in the unknown signature database; in response to determining that a second signature does not match the reference signature in the reference signature database and the second signature matches the unidentified signature in the unknown signature database, and increasing a count associated with the unidentified signature.
Type:
Grant
Filed:
February 1, 2021
Date of Patent:
June 7, 2022
Assignee:
THE NIELSEN COMPANY (US), LLC
Inventors:
Sandeep Tapse, Albert T. Borawski, Daniel Nelson
Abstract: Performing a geo-visual search is disclosed. A query feature vector associated with a query tile is obtained. A lookup is performed at least in part by using a key derived from the query feature vector. A list of candidate feature vectors is obtained based at least in part on the lookup. Based at least in part on a comparison of the query feature vector against at least some of the candidate feature vectors in the obtained list, a tile that is visually similar to the query tile is determined. The determined tile is provided as output.
Type:
Grant
Filed:
February 25, 2019
Date of Patent:
June 7, 2022
Assignee:
Descartes Labs, Inc.
Inventors:
Ryan S. Keisler, Samuel W. Skillman, Michael S. Warren
Abstract: The present disclosure describes a system and method for a marker-based augmented reality system. The method includes acquiring image data from a camera, analyzing the image data to identify at least one marker, the at least one marker being associated with a physical location in a real-world environment, determining information represented via the at least one marker, the information represented via the at least one marker including at least one of content data, metadata, or server data, generating content based on the at least one of the content data, the metadata, or the server data, and presenting, via a display, the content overlaying a displayed representation of the real-world environment, the content being presented at one or more locations in the displayed representation of the real-world environment relative to the physical location associated with the at least one marker.
Abstract: A computer-implemented method for analyzing a survivability of a structure is presented. A distance extending radially from the structure defining an area surrounding the structure may be determined. The area surrounding the structure may be scanned to identify surrounding objects. The area surrounding the structure may then be segmented to create a plurality of area segments. A density of surrounding objects in each of the plurality of area segments may be determined. A risk score for each of the plurality of area segments may then be determined based on the density of surrounding objects in each of the plurality of area segments. An overall wind exposure risk value may be provided for further use.
Type:
Grant
Filed:
August 18, 2020
Date of Patent:
May 31, 2022
Assignee:
STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY
Abstract: Portable terminals 100-1 to 100-N of a plurality of users have roles divided into one portable terminal 100-1 functioning as a host and other portable terminals 100-2 to 100-N (one or more second portable terminals) functioning as a client, and communication needed for creation of a collage image can be performed between the portable terminal 100-1 and other portable terminals 100-2 to 100-N. Accordingly, even though a plurality of users participate in creation of a collage image, it is possible to allow the user of each portable terminal to perform operations for selection of an image for use in the creation of the collage image, edition of the selected image, and the like in parallel with operations of other users for selection, edition, and the like of images without waiting for the operations of other users, and to create the collage image in a comparatively short time.