Abstract: A computer vision system includes a camera that captures a plurality of image frames in a target field. A user interface is coupled to the camera. The user interface is configured to perform accelerated parallel computations in real-time on the plurality of image frames acquired by the camera. The system provides an identification of where collisions regularly occur.
Type:
Grant
Filed:
June 26, 2019
Date of Patent:
July 13, 2021
Assignee:
RoundhouseOne Inc.
Inventors:
Mark Raymond Miller, Archana Ramachandran, Christopher C. Anderson
Abstract: A method of determining the position and orientation of an invasive medical device is described using altered devices and a machine learning algorithm for detecting the position and orientation of such devices from imagery. Such predictions can subsequently be displayed to an operator to improve the speed and accuracy by which they perform procedures.
Abstract: A reduced attention state estimation system includes an eyeball movement and eyelid activity measurement unit that measures an eyeball movement and an eyelid activity of a subject to obtain eyeball movement and eyelid activity data, a section determination unit that determines an eye opening section, an eye closing section, an eye-blinking section and a cluster section based on the eyeball movement and eyelid activity data, an eyeball movement and eyelid activity-related information calculation unit that calculates a sharpness of microsaccade or the like for each eye opening section based on the eyeball movement and eyelid activity data, and an attention assessment unit that determines an attention assessment or the like for an eye opening/cluster section, which is an eye opening section and cluster section, based on the sharpness of microsaccade or the like.
Type:
Grant
Filed:
November 22, 2017
Date of Patent:
July 13, 2021
Assignees:
Japan Aerospace Exploration Agency, National Center of Neurology and Psychiatry
Abstract: A computing system (126) includes a computer readable storage medium (130) with computer executable instructions (128), including: a segmentation standardizer (120) configured to determine a standardized vascular tree from a segmented vascular tree segmented of volumetric image data and a predetermined set of pruning rules (206), and a biophysical simulator (122) configured to perform a biophysical simulation based on the standardized vascular tree. The computing system further includes a processor (124) configured to execute the segmentation standardizer to determine the standardized vascular tree from the segmented vascular tree segmented of volumetric image data and the predetermined set of pruning rules, and configured to execute the biophysical simulator to perform a biophysical simulation based on the standardized vascular tree. The computing system further includes a display configured to display at least one of the standardized vascular tree and a result of the biophysical simulation.
Type:
Grant
Filed:
November 16, 2017
Date of Patent:
July 6, 2021
Assignee:
KONINKLIJKE PHILIPS N.V.
Inventors:
Hannes Nickisch, Holger Schmitt, Sven Prevrhal, Mordechay Pinchas Freiman, Liran Goshen
Abstract: A quantification system (300) is described that includes: at least one input (310) configured to provide at least one input medical image and provide a location of interest in the at least one input medical image; and a mapping circuit (325). The mapping circuit (325) is configured to: compute a direct quantification result from the location of interest of the at least one input medical image to a quantification of interest and output a direct first quantification result therefrom; generate a saliency map as part of the computation of the direct quantification result; and derive a segmentation from the saliency map, such that the segmentation independently generates a second quantification result that is within a result range of the direct first quantification result.
Abstract: Systems and methods including one or more processors and one or more non-transitory storage devices storing computing instructions configured to run on the one or more processors and perform acts of receiving one or more digital images from a repository of digital images; annotating the one or more digital images from the repository of digital images; digitally altering the one or more digital images, as annotated, from the repository of digital images; digitally combining the one or more digital images, as annotated and digitally altered, with at least one or more portions of one or more other digital images of the repository of digital images to create one or more combined digital images; training a machine learning algorithm on the one or more combined digital images; and storing the machine learning algorithm, as trained, in the one or more non-transitory computer readable storage devices.
Abstract: A method and system for locating a target object in a target scene. The method may include obtaining a depth image of the target scene. The depth image may include a plurality of pixels. The method may also include, for each of the plurality of pixels of the depth image, determining a first target coordinate under a target coordinate system. The method may further include generating a marking image according to the depth image and the first target coordinates of the plurality of pixels in the depth image. The marking image may represent potential target objects in the depth image. The method may also include determining a locating coordinate of the target object under the target coordinate system according to the marking image.
Abstract: A three-dimensional object imager uses infrared light at different wavelengths to triangulate depth information of the object from wavelength-dependent detection of the infrared image of the object. The depth information is obtained by determining wavelength of infrared light impinging on different pixels of the array. The wavelength may be determined by breaking each pixel into a plurality of sub-pixels, each sub-pixel having its own spectral selectivity to light at different infrared wavelength. For eye imaging or eye tracking applications, this enables the preservation of an unobstructed field of view of the eye while obtaining real-time, dynamic information about eye position and orientation in an non-intrusive, inconspicuous manner.
Abstract: Systems and methods are provided for classifying a tissue mass as malignant or benign. The method includes identifying a region of interest in the tissue mass in computed tomography (CT) imaging data, segmenting the CT imaging data to delimit at least a portion of the tissue mass into image segments, extracting a set of radiomic parameters indicative of the tissue mass. The set of radiomic parameters may include tissue mass location, tissue mass shape, tissue mass surface characteristic, or tissue mass texture distribution indicative of the amount of image segments identified. The method also includes generating a report classifying the indeterminate lung nodule as being malignant or benign based on the set of radiomic parameters of the indeterminate lung nodule.
Type:
Grant
Filed:
October 16, 2018
Date of Patent:
June 8, 2021
Assignees:
Mayo Foundation for Medical Education and Research, Vanderbilt University
Inventors:
Tobias Peikert, Ronald A. Karwoski, Fabien Maldonado, Srinivasan Rajagopalan, Brian J. Bartholmai
Abstract: A system and method and apparatus collect behavioral biometric and facial recognition data for biometric analysis by asking a user to type text to an electronic device. Fusion of knowledge based authentication, behavioral biometrics and facial recognition provides strong authentication and liveness detection, while keeping user experience to simply typing.
Abstract: Various facial recognition systems may benefit from appropriate use of computer systems. For example, certain face analysis systems may benefit from an all-in-one convolutional neural network that has been appropriately configured. A method can include obtaining an image of a face. The method can also include processing the image of the face using a first set of convolutional network layers configured to perform subject-independent tasks. The method can further include subsequently processing the image of the face using a second set of convolutional network layers configured to perform subject-dependent tasks. The second set of convolutional network layers can be integrated with the first set of convolutional network layers to form a single convolutional neural network. The method can additionally include outputting facial image detection results based on the processing and subsequent processing.
Type:
Grant
Filed:
October 10, 2017
Date of Patent:
June 1, 2021
Assignee:
UNIVERSITY OF MARYLAND, COLLEGE PARK
Inventors:
Rajeev Ranjan, Swaminathan Sankaranarayanan, Carlos Castillo, Ramalingam Chellappa
Abstract: A communication apparatus includes: signal generation circuitry which, in operation, generates a control signal including a target reception power value regarding a target value of a reception power for the communication apparatus to receive an uplink (UL) response frame transmitted by each of one or more terminal stations, the control signal being a trigger frame that solicits transmission of the UL response frame from each of the one or more terminal stations; and transmission circuitry which, in operation, transmits the generated signal.
Abstract: A parking assist apparatus includes: a setting unit that sets, within a captured image in which objects surrounding a moving vehicle have been imaged, a first search area for searching for a pair of partition lines disposed between parking spaces that are adjacent to each other; and a detecting unit that searches the first search area to detect a first partition line out of the pair of partition lines. When the detecting unit detects the first partition line, the setting unit sets a second search area for searching for a second partition line out of the pair of partition lines on the basis of the first partition line.
Abstract: The present disclosure relates generally to vegetation management and control, in particular, to vegetation data capture, maintenance workflow generation, prioritization, passive and continuous monitoring of vegetation, and predictive analysis for vegetation that may be within or adjacent to clearance zones for railway, transportation, utility, pipeline, range & pasture, and industrial sites.
Type:
Grant
Filed:
May 22, 2019
Date of Patent:
May 18, 2021
Assignee:
Bayer CropScience LP
Inventors:
Kevin Adam, Kris C. Matson, Mathew C. Nespeca, Michael Owen, J. Brent Slone, John M. Ridgeway, Roland Maynard
Abstract: A device for searching for a lane on which a vehicle can drive, wherein the device is configured to receive an image captured by a camera, the image showing an area in front of the vehicle, detect lane markings in the image, determine for each of the lane markings if the respective lane marking is of a first type indicating a road condition of a first type or a second type indicating a road condition of a second type, create lane candidates from the lane markings, divide the lane candidates into classes of lane candidates depending on the type of the lane markings of the lane candidates, and search the classes of lane candidates for a lane on which the vehicle can drive.
Abstract: Disclosed are a wireless communication device and a wireless communication method. The wireless communication device according to one embodiment comprises one or more processors. The processors are configured so as to: on the basis of auxiliary dissemination limitation information about a source device as an information dissemination source, acquire device information about candidate devices capable of establishing direct communication with the source device; on the basis of the locations of the source device and the candidate devices, select a target device for establishing direct communication with the source device from the candidate devices; and determine a transmission resource for direct communication with the target device and generate a transmission resource scheduling indication.
Abstract: A server includes a virtual machine to execute a remote graphics generation protocol. Execution of the remote graphics generation protocol determines a protection label to be inserted within a bitmap that is to be transmitted for display on a client machine associated with the virtual machine, and determines at least one optimization technique to be performed on the bitmap. A determination is made on if the at least one optimization technique, if performed, alters the at least one protection label when inserted within the bitmap. The protection label is inserted within the bitmap.
Abstract: A communication system including a network of stickers in transit such that the spatial relationship between the stickers is changing, each sticker including a processor, a storage storing operation code and messages, a message including addresses of source and destination devices, and data sent from the source device to the destination device, and a wireless communicator, and devices that send and receive messages to and from stickers, whereby the operation code of each sticker causes its processor to sporadically receive data stored within other stickers that are currently within range of its communicator, to receive messages from source devices that are within range of its communicator, to store received messages within its storage, to sporadically transmit messages to other stickers that are within range of its communicator, and to transmit messages to the message's respective destination device, when the destination device is within range of its communicator.
Abstract: A method is described for ways to generate a Fraction of Sand (Fsand) estimate and net-to-gross (NTG) estimate of sand in a formation using a machine-learning algorithm such as a neural network based on borehole image logs. The method may use the Fsand and other information to estimate hydrocarbons in place in a subsurface formation. The method may be executed by a computer system.
Type:
Grant
Filed:
October 15, 2019
Date of Patent:
May 4, 2021
Assignee:
Chevron U.S.A. Inc.
Inventors:
Bo Gong, Dustin J. Keele, Emmanuel Toumelin, Simon Clinch
Abstract: A monitoring system includes an imaging device and a control device. The control device includes a device communication section, a device controller, and device storage. The device controller includes an assignment section and a count section. The imaging device captures an image of an imaging area to generate captured image data indicating the captured image. The device controller acquires the captured image data from the imaging device through the device communication section. The assignment section assigns a plurality of candidate detection ranges to the captured image. The count section counts the number of occurrences of a specific event in each of the candidate detection ranges. The device storage stores therein the number of occurrences of the specific event in association with each of the candidate detection ranges.