Abstract: An image distribution apparatus includes an acquisition unit configured to acquire information about a gazing area specified by a user in a first image, and a transmission unit configured to transmit, from a second image having resolution higher than resolution of the first image and divided into a plurality of tile images, a first tile image where the gazing area belongs and a second tile image adjacent to the first tile image.
Abstract: An information processing system, an information processing method, and a recording medium, which implement effective information presentation by presentation of information when a user is in a situation where information is easily acceptable, are to be provide. An information processing system including a control unit that controls a presentation unit to present a message to a user when the user is presumed, based on sensing data related to the user, to be in a situation where a message is easily acceptable.
Abstract: A method is provided that includes generating a visual environment for interactive development of a machine learning (ML) model. The method includes accessing observations of data each of which includes values of independent variables and a dependent variable, and performing an interactive exploratory data analysis (EDA) of the values of a set of the independent variables. The method includes performing a feature construction and selection based on the interactive EDA, and in which select independent variables are selected as or transformed into a set of features for use in building a ML model to predict the dependent variable. The method includes building the ML model using a ML algorithm, the set of features, and a training set produced from the set of features and observations of the data. And the method includes outputting the ML model for deployment to predict the dependent variable for additional observations of the data.
Abstract: Methods and systems are provided for data-driven network roll-out planning. A mobile network that includes at least one sector with a plurality of cells may be rolled-out using carrier aggregation. The carrier aggregation based rolling out includes gathering data from a plurality of network counters associated with two or more cells of the at least one sector; detecting a network congestion situation (Cs), based on a minimal throughput level and an aggregate cumulative distribution function (CDF), where the aggregate CDF is based on the plurality of network counters; identifying one or more cells effecting the congestion situation among the two or more cells; and determining for each of the identified one or more cells whether a capacity or coverage pain point is associated with the congestion situation.
Abstract: Disclosed are a weight data storage method and a convolution computation method that may be implemented in a neural network. The weight data storage method comprises searching for effective weights in a weight convolution kernel matrix and acquiring an index of effective weights. The effective weights are non-zero weights, and the index of effective weights is used to mark the position of the effective weights in the weight convolution kernel matrix. The weight data storage method further comprises storing the effective weights and the index of effective weights. According to the weight data storage method and the convolution computation method of the present disclosure, storage space can be saved, and computation efficiency can be improved.
Type:
Grant
Filed:
February 28, 2018
Date of Patent:
December 20, 2022
Assignee:
INSTITUTE OF COMPUTING TECHNOLOGY, CHINESE ACADEMY OF SCIENCES
Inventors:
Yinhe Han, Feng Min, Haobo Xu, Ying Wang
Abstract: According to one embodiment, a method for displaying an index value in generation of a mask pattern verification model includes: calculating a first index value using a plurality of images; estimating a model on the basis of the first index value and pattern information; calculating a second index value using the model; and displaying at least one of the first index value and the second index value.
Abstract: A method for separating an image can include: acquiring a foreground pixel value and a background pixel value, where the foreground pixel value and the background pixel value are configured to separate a target area from an original image; acquiring a foreground geodesic distance and a background geodesic distance, where the foreground geodesic distance is a distance between a pixel value of each of pixel points and the foreground pixel value in the original image, and the background geodesic distance is a distance between a pixel value of each of the pixel points and the background pixel value; determining a transparency based on the foreground geodesic distance and the background geodesic distance; and separating the target area based on the transparency.
Type:
Grant
Filed:
December 23, 2020
Date of Patent:
November 8, 2022
Assignee:
BEIJING DAJIA INTERNET INFORMATION TECHNOLOGY CO., LTD.
Abstract: A opioid overdose treatment assembly for treating an opioid overdose includes a housing that can be worn on a user. An inhaler is coupled to the housing and the inhaler contains an aerosolized medication for treating an opioid overdose. The inhaler is actuatable to release a pre-determined amount of the aerosolized medication for inhalation by the user when the user is suffering from an opioid overdose. A communicator is coupled to the housing and the communicator is in wireless communication with a communication network. In this way the communicator can be placed in communication with emergency responders.
Abstract: An electronic device and method for human skin detection based on a human body-prior is provided. A color image of a person is acquired, and a 3D body model of the person is estimated based on the color image. One or more unclothed parts of the 3D body model are identified. The one or more unclothed parts correspond to one or more body parts, of which at least a portion of skin remains uncovered by clothes. From the color image, pixel information corresponding to the one or more unclothed parts is extracted and classification information is determined based on the pixel information. The classification information includes a set of values, each indicating a likelihood of whether a corresponding pixel of the color image is part of an unclothed skin portion of the person. The unclothed skin portion is detected in the color image based on the classification information.
Abstract: System and methods for automated incident identification and reporting while operating a vehicle on the road using a device. The device identifies incidents using artificial intelligence neural networks trained to detect, classify, segment, and/or extract other information pertaining to objects of interest representing incidents. Additionally, a system and method for further storing, transmitting, processing, organizing and accessing the information graphically with respect to incident type, location, date and time during operation of the vehicle along the road.
Type:
Grant
Filed:
July 15, 2020
Date of Patent:
October 25, 2022
Assignee:
VISUAL DEFENCE INC.
Inventors:
Royi Tal, Thomas Bakonyi, Ximing Wang, Omri Artman, Redenthor Ibana, David Curry, Suthakaran Kandasamy
Abstract: A computing device for dimensioning an object includes: a dimensioning subsystem configured to execute a default dimensioning method and a backup dimensioning method; a memory storing quality evaluation rules; a processor connected with the dimensioning subsystem and the memory, the processor configured to: control the dimensioning subsystem to execute a default dimensioning method to obtain default dimensioning data; compare a quality metric for the default dimensioning data to a threshold condition defined in the quality evaluation rules; when the quality metric exceeds the threshold condition, compute dimensions of the object based on the default dimensioning data; and when the quality metric does not exceed the threshold condition, control the dimensioning subsystem to execute the backup dimensioning method to obtain backup dimensioning data and compute the dimensions of the object based on the backup dimensioning data.
Type:
Grant
Filed:
May 28, 2020
Date of Patent:
October 18, 2022
Assignee:
Zebra Technologies Corporation
Inventors:
Patrick B. Tilley, Seth David Silk, Raghavendra Tenkasi Shankar
Abstract: A mobile virtual network operator is provided. The operator includes a server that is communicatively coupled to a mobile device. The mobile device includes application software provided by the virtual network operator for allowing phone call and data connectivity.
Abstract: A method and apparatus for detecting an obstacle, an electronic device, and a storage medium. A specific implementation of the method includes: detecting, by a millimeter-wave radar, position points of candidate obstacles in front of a vehicle; detecting, by a camera, a left road boundary line and a right road boundary line of a road on which a vehicle is located; separating the position points of the candidate obstacles according to the left road boundary line and the right road boundary line of the road on which the vehicle is located, and extracting position points between the left road boundary line and the right road boundary line; projecting the position points between the left road boundary line and the right road boundary line onto an image; and detecting, based on projection points of the position points on the image, a target obstacle in front of the vehicle.
Type:
Grant
Filed:
September 10, 2020
Date of Patent:
October 11, 2022
Assignee:
APOLLO INTELLIGENT DRIVING TECHNOLOGY (BEIJING) CO., LTD.
Abstract: An exemplary computer vision system implemented by a multi-access edge computing (“MEC”) server integrated within a provider network accesses an image captured by an image capture device coupled with the MEC server via the provider network. The image depicts a product that is to comply with a predefined product standard. The computer vision system identifies a criterion that is associated with the predefined product standard, and a region of the image that is associated with a product condition that is to be verified for compliance with the criterion. The computer vision system determines whether the product condition complies with the identified criterion for the identified region of the image, and, based on this determination, generates compliance verification data indicative of whether the product complies with the predefined product standard. The computer vision system also provides the compliance verification data to a monitoring system separate from the MEC server.
Type:
Grant
Filed:
July 25, 2019
Date of Patent:
September 27, 2022
Assignee:
Verizon Patent and Licensing Inc.
Inventors:
Aleo Nobel Mok, Sean Hsu, Christian Guirnalda, Zachary Drossman, Joshua Christopher Ness, Khurram Nasir Gore, Jessica Sobel
Abstract: A method and system for integrating multiple measurement hypotheses in an efficient labeled multi-Bernoulli (LMB) filter. The LMB filter estimates a plurality of tracks for a plurality of objects, each track of the plurality of tracks having a unique label, a probability, and a state, wherein each track of the plurality of tracks is associated to an object of a plurality of objects to be tracked, each object having an object state.
Type:
Grant
Filed:
July 6, 2018
Date of Patent:
September 27, 2022
Assignee:
Bayerische Motoren Werke Aktiengesellschaft
Abstract: Disclosed are portable containers for delivering food products from a central location to a remote location. More specifically, the disclosure relates to portable containers for delivering food products operable to maintain an environment for the food product during the delivery process.
Type:
Grant
Filed:
August 4, 2021
Date of Patent:
September 20, 2022
Assignee:
PAVEL & SPRAUVE LLC
Inventors:
Steven S. Escobar, Michael Sprauve, Michael Pavel
Abstract: This application discloses a target object recognition method and apparatus, a storage medium, and an electronic device. The method includes: obtaining a first image and a second image, the first image being an image obtained by shooting a target scene under visible light, and the second image being an image obtained by shooting the target scene under infrared; determining a predicted infrared intensity value corresponding to a pixel point in the first image through a prediction model; obtaining a difference between an actual infrared intensity value of a pixel point in the second image and the infrared intensity value corresponding to the pixel point at the same location in the first image; and determining a pixel point in the second image of which the difference is greater than a first threshold as a pixel point at which the target object in the target scene is located.
Type:
Grant
Filed:
October 19, 2020
Date of Patent:
September 13, 2022
Assignee:
TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
Abstract: An image processing apparatus includes an acquisition unit configured to acquire images each of which is an image having a first data amount acquired through image-capturing, a detection unit configured to detect an attention target in each of the images, a specification unit configured to specify a geographical range based on a geographical position where the detected attention target exists, and a conversion unit configured to convert an image of at least a part of the images into an image having a second data amount that is smaller than the first data amount according to an inclusion relationship between the specified geographical range and a geographical position where each of the images having the first data amount is acquired.
Abstract: An object detection device comprising a first detecting part detecting types and positions of objects including a road mirror in an image and a presence of a movable object reflected in the road mirror based on image data of a low resolution image and a second detecting part detecting a type of the movable object in the road mirror and a position of the movable object in the road mirror based on high resolution partial image data obtained by extracting the part of the road mirror from the image if there is a movable object reflected in the road mirror.
Type:
Grant
Filed:
September 16, 2019
Date of Patent:
August 23, 2022
Assignee:
TOYOTA JIDOSHA KABUSHIKI KAISHA
Inventors:
Daisuke Hashimoto, Satoshi Takeyasu, Kota Hirano
Abstract: The present disclosure describes methods, device, and storage medium for obtaining lane line data of a road. The method includes obtaining and dividing, by a device, road-image data of a road into at least one segment. The device includes a memory storing instructions and a processor in communication with the memory. The method includes processing, by the device, each segment to obtain a two-dimensional grayscale image of each segment; extracting, by the device using a pre-trained deep neural network model, a lane line area and a lane line attribute in each two-dimensional grayscale image, to obtain a lane line area image of each segment; and splicing, by the device, each lane line area image based on corresponding road-image data and the lane line attribute, to obtain lane line data of the road.
Type:
Grant
Filed:
June 5, 2020
Date of Patent:
August 16, 2022
Assignee:
TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED