Abstract: Methods, apparatus, systems and articles of manufacture to perform audio sensor selection in an audience metering device are disclosed. An example apparatus includes at least two audio sensors to receive audio at an audience metering device and a selection tester to identify a plurality of audio sensor configurations supported by the audience metering device, the plurality of audio sensor configurations identifying respective gain values to be applied to the plurality of audio sensors. The selection tester is further to select one of the first one of the audio sensor configurations or the second one of the audio sensor configurations based on a comparison of a first quality metric and a second quality metric. The example apparatus further includes a media identifier to identify audio received at the audience metering device using the selected one of the audio sensor configurations.
Type:
Grant
Filed:
August 17, 2020
Date of Patent:
June 14, 2022
Assignee:
The Nielsen Company (US), LLC
Inventors:
Christen V. Nielsen, James J. Vitt, Timothy Scott Cooper, Douglas Brent Turnbow, Kenneth Paul Braman
Abstract: A vegetation index calculation apparatus (10) is provided with a specification unit (11) that collates height distribution data indicating a distribution of the height of plants that exist in a target region with predicted height data of a crop targeted for calculation of a vegetation index, and specifies a region where the crop exists within the target region, and a vegetation index calculation unit (12) that calculates the vegetation index of the crop that exists in the region specified by the specification unit (11).
Abstract: A method for training a chromosome recognition model includes: identifying objects on a karyotype image, obtaining a mask and a minimal bounding box of each of the chromosome objects, and obtaining an organized image that includes a set of organized chromosome objects; generating a simulated metaphase image in which the chromosome objects are randomly reorganized; detecting the plurality of chromosome objects on the simulated metaphase image; obtaining a recalibrated image in which the chromosome objects are separated from one another, so as to train the chromosome recognition model for identifying feature of chromosome objects included in an image.
Type:
Grant
Filed:
June 22, 2020
Date of Patent:
May 31, 2022
Assignee:
Ever Fortune.AI CO., Ltd.
Inventors:
Christian Pascal Tchou, Fuu-Jen Tsai, Ken Ying-Kai Liao, Tzung-Chi Huang
Abstract: A display device includes a first substrate having light transmitting portions, a plurality of pixels positioned on the first substrate and including light emitting devices, a light sensor layer overlapping the first substrate and including light receiving devices respectively corresponding to the light transmitting portions, and a light guide layer positioned between the display panel and the light sensor layer and including light guide paths respectively corresponding to the light transmitting portions.
Abstract: Embodiments of the present disclosure relate to a method and apparatus for outputting information. The method can include: acquiring an image of a to-be-inspected object; segmenting the image into at least one subimage; for a subimage in the at least one subimage, inputting the subimage into a pre-trained defect classification model to obtain a defect category corresponding to the subimage; and outputting defect information of the object based on a defect category corresponding to each subimage.
Type:
Grant
Filed:
October 28, 2019
Date of Patent:
May 24, 2022
Assignee:
Beijing Baidu Netcom Science and Technology Co., Ltd.
Inventors:
Yawei Wen, Jiabing Leng, Chengcheng Wang, Ye Su, Minghao Liu, Yulin Xu, Jiangliang Guo, Xu Li
Abstract: A large-scale point cloud having no limitation on the range or the number of points is set as an object, and labels are attached to the points constituting the object regardless of the type of object.
Type:
Grant
Filed:
April 16, 2019
Date of Patent:
May 17, 2022
Assignee:
NIPPON TELEGRAPH AND TELEPHONE CORPORATION
Inventors:
Yasuhiro Yao, Hitoshi Niigaki, Ken Tsutsuguchi, Tetsuya Kinebuchi
Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that generate refined segmentation masks for digital visual media items. For example, in one or more embodiments, the disclosed systems utilize a segmentation refinement neural network to generate an initial segmentation mask for a digital visual media item. The disclosed systems further utilize the segmentation refinement neural network to generate one or more refined segmentation masks based on uncertainly classified pixels identified from the initial segmentation mask. To illustrate, in some implementations, the disclosed systems utilize the segmentation refinement neural network to redetermine whether a set of uncertain pixels corresponds to one or more objects depicted in the digital visual media item based on low-level (e.g., local) feature values extracted from feature maps generated for the digital visual media item.
Type:
Grant
Filed:
August 7, 2020
Date of Patent:
May 17, 2022
Assignee:
Adobe Inc.
Inventors:
Zichuan Liu, Wentian Zhao, Shitong Wang, He Qin, Yumin Jia, Yeojin Kim, Xin Lu, Jen-Chan Chien
Abstract: A method of quantifying changes in a visceral organ comprises acquiring first (310) and second (410) medical scans of a visceral organ at first and second timepoints. At least part of the visceral organ in the first medical scan is parcellated into a first set of one or more subregions (420), based on image content, each subregion comprising a plurality of voxels. The first medical scan (310) is aligned to the second medical scan (410), before or after parcellating the first medical scan (310). Then the second medical scan is parcellated into a second set of one or more subregions. A metric is evaluated for a subregion in the first medical scan (310), and for the corresponding subregion in the second medical scan (410). A difference in the metric values provides a measure of a change that has occurred in the subregion, between the first and second timepoints.
Type:
Grant
Filed:
October 12, 2018
Date of Patent:
May 17, 2022
Assignee:
Perspectum Limited
Inventors:
Benjamin J Irving, Chloe Hutton, Brady Michael John
Abstract: Systems, apparatuses, and methods are provided herein that may be used to monitor a movable barrier operated by a movable barrier operator. In some embodiments, a system includes a camera configured to capture frames, and a control circuit. The camera has a field of view that defines a boundary of each of the frames. The control circuit is configured to receive a first frame, identify a stationary object in the first frame, and define a region of interest “ROI” relative to the stationary object in the first frame. The control circuit is further configured to receive a second frame, identify the stationary object in the second frame, determine whether at least a portion of the ROI is outside of the second frame, and cause the movable barrier operator to enter a failsafe mode upon the at least a portion of the ROI being outside of the second frame.
Abstract: A learning model preparation method includes: acquiring a non-specific binding specimen image representing a non-specific binding specimen that allows a reagent to act on a tissue containing the endogenous protein, the reagent developing a color in a non-specific binding region in which an endogenous protein exists; and preparing a first learning model by setting the non-specific binding specimen image to first learning data, and by allowing a learning device to learn the non-specific binding region, based on the first learning data.
Abstract: Described herein are biometric identification systems and methods that use a set of finely spaced analog sensors to generate and record a unique dynamic pressure user profile. The pressure profile is evaluated based on data from a trained model that comprises a number of personal biometric characteristics used to uniquely identify a person, e.g., for authentication purposes, such as granting access to sensitive, confidential information in connection with an electronic commercial transaction, an Internet of Things (IoT) device, an automotive device, an identity and access management (IAM), or a robotic or high functioning touch sensing device.
Abstract: Techniques for fracture detection are provided. A first image is received to be processed to identify rib fractures. A first set of regions of interest (ROIs) is identified by processing the first image using a first machine learning model, where each ROI in the first set of ROIs corresponds to a first potential fracture. Further, a first ROI of the first set of ROIs is upsampled, and the system attempts to verify the first potential fracture in the first ROI by processing the upsampled first ROI using a second machine learning model.
Type:
Grant
Filed:
April 10, 2019
Date of Patent:
April 26, 2022
Assignee:
International Business Machines Corporation
Inventors:
Amin Katouzian, Benedikt Werner Graf, Ahmed El Harouni, Yiting Xie, Arkadiusz Sitek, Vicky Guo, Arun Krishnan
Abstract: A circuit includes a transmitter, a transmission channel communicatively coupled with the transmitter, and a receiver communicatively coupled with the transmission channel. The circuit further includes a combiner on a transmitter-side of the transmission channel, a decoupler on a receiver-side of the transmission channel, and a channel loss compensation circuit communicatively coupled between the transmitter and the receiver. The combiner is coupled between the transmitter and the transmission channel. The decoupler is coupled between the receiver and the transmission channel.
Abstract: The present invention discloses methods and systems for configuring at least one radio frequency (RF) module by a wireless communication apparatus. The wireless communication apparatus sends a first message to the at least one RF module, and the first message comprises a request for at least one international mobile subscriber identity (IMSI) of at least one subscriber identity module (SIM) card. A second message is then received from the RF module, and the second message comprises the at least one IMSI. The wireless communication apparatus determines which wireless network service provider(s) the at least one SIM card is associated with. The wireless communication apparatus identifies at least one configuration information. The wireless communication apparatus then sends a third message to the at least one RF module, and the third message comprises the at least one configuration information. The at least one RF module is then configured based on the at least one configuration information.
Abstract: Monitoring of an environmental location to detect waste disposal includes receiving, by a computer, a collection of images from aerial data acquisition sources, the collection of images corresponding to the environmental location and the waste disposed in the environmental location. The collection of images are processed by the computer to extract properties of the waste and first properties of the environmental location. Subsequently, the properties of the waste disposed in the environmental location are classified according to a class. Additional information from external data sources including second properties of the environmental location is received by the computer. The computer determines a behavior of waste disposal in the environmental location over a period of time based on the classified properties of the disposed waste and the first and second properties of the environmental location, and generated a remediation plan based on the determined behavior.
Type:
Grant
Filed:
August 12, 2020
Date of Patent:
April 19, 2022
Assignee:
International Business Machines Corporation
Inventors:
Na Liu, Mei Rui Su, Pei Jian Liu, Bing Hua Zhao, Yan Liu, Zhong Fang Yuan, Wen Wang
Abstract: A property inspection service hosted on a web-based server system. The server system receives a list of physical addresses each corresponding to different parcels. For each address, the server system obtains multiple images including overhead images and perspective view images. A first trained model analyzes selected overhead images individually to identify one or more building structures. A second trained model analyzes selected perspective view images individually to identify a primary building structure. A third trained model analyzes the selected overhead images and the perspective view images together in an integrated approach to identify attributes associated with identified building structure. A digital report is generated as a graphical user interface configured to display the selected images and the attributes associated the identified building structure.
Type:
Grant
Filed:
July 9, 2020
Date of Patent:
April 12, 2022
Assignee:
Tensorflight, Inc.
Inventors:
Robert Kozikowski, Zbigniew Wojna, Lukasz Jocz, Rafal Tybor, Robert Paluba, Wladyslaw Surala, Piotr Jarosz
Abstract: A method for training neural networks of an automated workflow performed by a software component executing on a server in communication with remote computers at respective laboratories includes downloading and installing a client and a set of neural networks to a first remote computer of a first laboratory, the client accessing the echocardiogram image files of the first laboratory to train the set of neural networks and to upload a first trained set of neural networks to the server. The process continues until the client and the second trained set of neural networks is downloaded and installed to a last remote computer of a last laboratory, the client accessing the echocardiogram image files of the last laboratory to continue to train the second trained set of neural networks and to upload a final trained set of neural networks to the server.
Type:
Grant
Filed:
March 27, 2020
Date of Patent:
April 12, 2022
Assignee:
EKO.AI PTE. LTD.
Inventors:
James Otis Hare, II, Paul James Seekings, Su Ping Carolyn Lam, Yoran Hummel, Jasper Tromp, Wouter Ouwerkerk, Zhubo Jiang
Abstract: A method for image processing, which comprises the following steps: Generating a first histogram from a first image; Calculating a first parameter profile from the first image indicative of the quality of the first image; Adjusting the first parameter profile to generate a second parameter profile; Using the second parameter profile to generate a statistical distribution via a statistical distribution generator, wherein the statistical distribution is characterized by at least three parameters; Using the statistical distribution to perform a histogram specification to the first histogram of the first image to generate a second histogram; Generating a second image based on the first image and the second histogram.
Type:
Grant
Filed:
February 21, 2020
Date of Patent:
March 29, 2022
Assignee:
CHONGQING UNIVERSITY OF POSTS AND TELECOMMUNICATIONS
Abstract: A fingerprint sensor, a fingerprint recognition module and a fingerprint recognition system. The fingerprint sensor includes: a sensor die configured to collect fingerprint information; a package structure configured to package the sensor die, where the sensor die or the package structure includes a first metal electrode, which is connected with a touch detection module, and the touch detection module is connected with a control module and is configured to feed back a touch signal to the control module, so as to enable the control module to supply power to the fingerprint sensor according to the touch signal, and then enable the sensor die to collect fingerprint information. Under the premise of ensuring low standby power consumption of the fingerprint recognition system, the anti-interference ability and the ESD performance of the fingerprint recognition module are improved, and the flexibility of the touch detection scheme is improved.
Abstract: This invention concerns an automatic segmentation method of a medical image making use of a knowledge database containing information about the anatomical and pathological structures or instruments, that can be seen in a 3D medical image of a×b×n dimension, i.e. composed of n different 2D images each of a×b dimension. Said method being characterised in that it mainly comprises three process steps, namely: a first step consisting in extracting from said medical image nine sub-images (1 to 9) of a/2×b/2×n dimensions, i.e.
Type:
Grant
Filed:
January 10, 2019
Date of Patent:
March 29, 2022
Assignees:
INSTITUT DE RECHERCHE SUR LES CANCERS DE I, VISIBLE PATIENT
Inventors:
Luc Soler, Nicolas Thome, Alexandre Hostettler, Jacques Marescaux