Abstract: Disclosed embodiments provide systems and methods for transforming real-world images for augmentation of image data for improvement of training data sets utilized by machine learning algorithms to provide autonomous and/or assistive driving functionality.
Abstract: A computer enabled method for locating a misplaced object that includes receiving at an object locating system a request defining an object to be located, the input data request being received audibly by a digital assistant. The method may include analyzing the request with the object locating system by classifying the object to be located with an image search of a corpus of images correlated to comparison objects; and receiving images from Internet of Thing devices (IoT) devices of search objects. The method further includes comparing the images correlated to comparison objects from the image search with images of the search objects to identify retrieval objects that match the object classified by the object locating system that analyzed the request. The location of the retrieval object is then identified.
Type:
Grant
Filed:
June 11, 2019
Date of Patent:
June 29, 2021
Assignee:
International Business Machines Corporation
Inventors:
Sarbajit K. Rakshit, Martin G. Keen, James E. Bostick, John M. Ganci, Jr.
Abstract: A method performed by an electronic device is described. The method includes receiving an image. The image depicts a face. The method also includes detecting at least one facial landmark of the face in the image. The method further includes receiving a depth image of the face and determining at least one landmark depth by mapping the at least one facial landmark to the depth image. The method also includes determining a plurality of scales of depth image pixels based on the at least one landmark depth and determining a scale smoothness measure for each of the plurality of scales of depth image pixels. The method additionally includes determining facial liveness based on at least two of the scale smoothness measures. Determining the facial liveness may be based on a depth-adaptive smoothness threshold and/or may be based on a natural face size criterion.
Type:
Grant
Filed:
December 1, 2017
Date of Patent:
June 29, 2021
Assignee:
QUALCOMM Incorporated
Inventors:
Xuan Zou, Ke-li Cheng, Michel Adib Sarkis, Matthew Fischler, Ning Bi, Yingyong Qi
Abstract: A method for determining an object comprises: determining a reference representation based on positions of a first reference point and a second reference point of a first object in a reference image, which indicates a distance and a relative direction between the first and second reference points in the reference image; determining a detection representation based on positions of the first and second reference points in a detection frame including the first object in a video, which indicates a distance and a relative direction between the first and second reference points in the detection frame; determining rotation parameters associated with a first predetermined point and a second predetermined point in a second object associated with the first object based on the reference representation and the detection representation; and adjusting a target representation between the first and second predetermined points in the second object based on the rotation parameter.
Abstract: This application provides a phase tracking reference signal (PTRS) sending method and apparatus. The method includes: implicitly determining, by a terminal device based on obtained uplink grant information and a preset rule, a to-be-sent PTRS and an antenna port for carrying the to-be-sent PTRS, where the antenna port is selected from an antenna port set, and the to-be-sent PTRS is one or more of all available PTRSs; and putting the to-be-sent PTRS on the antenna port, and sending the to-be-sent PTRS on the antenna port. This implicit indication method can effectively reduce air interface signaling overheads and improve air interface efficiency.
Abstract: A data transmission method of a source node in a cooperative communication system includes: performing a beamforming to a relay node; transmitting data to the relay node; performing a beamforming to a destination node; and transmitting data to the destination node.
Type:
Grant
Filed:
May 22, 2020
Date of Patent:
June 15, 2021
Assignee:
ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE
Abstract: A distributed beamforming system including a platform terminal and a plurality of user terminals is disclosed. An individual user terminal includes a receiver configured to receive a plurality of individual wireless signals, where the plurality of individual wireless signals are transmitted by the platform terminal and are orthogonal with respect to one another. The individual user terminal also includes one or more frequency converters configured to transform each of the plurality of individual wireless signals to an intermediate frequency. The individual user terminal is configured to coherently combine the plurality of individual wireless signals together to form a beamformed signal.
Type:
Grant
Filed:
February 19, 2020
Date of Patent:
June 15, 2021
Assignee:
The Boeing Company
Inventors:
Christopher Jason Foster, Daniel Roukos, Kyle William Jewett, Christ Tzelepis
Abstract: The application discloses a multi-task learning incorporating dependencies method for bionic eye's face attribute recognition, which is as follows: Determine the first face attribute and the second face attribute for attribute recognition of facial image. Obtain the first recognition task branch and the second recognition task branch. Establish the task dependency between the first recognition task branch and the second recognition task branch to obtain the first transformed face attribute fully connected layer related to the second face attribute. and the second transformed face attribute fully connected layer related to the first face attribute. Feed the first transformed face attribute fully connected layer into the prediction layer to predict the first face attribute of facial image. And feed the second transformed face attribute fully connected layer into the prediction layer to predict the second face attribute of facial image.
Type:
Grant
Filed:
June 4, 2019
Date of Patent:
June 15, 2021
Assignee:
BEIJING INSTITUTE OF TECHNOLOGY
Inventors:
Qiang Huang, Xiaopeng Chen, Di Fan, Hyunwoo Kim, Xuechao Chen
Abstract: Calibration and distance prediction for driving assistance is provided. A camera of a vehicle is calibrated to obtain a distance data set. The distance data set includes a distance of each row of pixels of a first image captured by the camera. The distance data set may be further utilized in real-time to predict a distance of an object from the vehicle. Based on the predicted distance, a warning message for an impending collision may be generated and communicated to a driver of the vehicle, thereby facilitating driving assistance to the driver in the real-time.
Abstract: Front end systems and related devices, integrated circuits, modules, and methods are disclosed. One such packaged module includes a low noise amplifier in an interior of a radio frequency shielding structure and an antenna external to the radio frequency shielding structure. The low noise amplifier includes a first inductor, an amplification circuit, and a second inductor magnetically coupled to the first inductor to provide negative feedback to linearize the low noise amplifier. The radio frequency shielding structure can extend above a package substrate. The antenna can be on the package substrate. Other embodiments of front end systems are disclosed, along with related devices, integrated circuits, modules, methods, and components thereof.
Abstract: Disclosed is an approach of on-device partial recognition that includes performing partial recognition on an image of a document captured by a mobile device to detect and/or recognize a specific area (e.g., barcodes, non-relevant text, etc.) and filling the recognized area with a solid color. Because the solid color area has a maximum compression ratio, this approach can lead to image size reduction and increased network throughput for client-server based data recognition where further processing such as advanced data extraction is performed at the server side. The approach can be enforced with neural network algorithms to exclude non-relevant information (e.g., logos, phrases, words, etc.).
Type:
Grant
Filed:
August 24, 2020
Date of Patent:
June 8, 2021
Assignee:
OPEN TEXT CORPORATION
Inventors:
Mikhail Yurievitch Zakharov, Kirill Vaniukov, Christopher Dale Lund
Abstract: The present disclosure provides an optical flow tracking device. The device includes an image pyramid establishing circuit configured to establish a first image pyramid of a first image and a second image pyramid of a second image. The first image pyramid includes one or more image layers, and the second image pyramid includes one or more image layers. The device further includes an optical flow tracking circuit configured to perform an optical flow tracking processing on a kth image layer in the first image pyramid and a kth image layer in the second image pyramid to acquire an optical flow estimator of the second image in the kth image layer. K is an integer. The optical flow tracking circuit is configured to calculate an optical flow of the second image by using the optical flow estimator of the second image in the kth image layer.
Abstract: A system for document parsing includes an interface and a processor. The interface is configured to receive an image. The processor is configured to determine text boxes. Determining text boxes uses multiple zoom levels of the image. The processor is further configured to determine labels from the strings and provide the labels.
Type:
Grant
Filed:
October 30, 2018
Date of Patent:
June 1, 2021
Assignee:
Workday, Inc.
Inventors:
Milan Desai, Vivien Leong, Vivek Srivastava, Xuan Tan, Sergei Winitzki, Yunxing Zhang
Abstract: In a general aspect, MIMO transmissions are elicited from wireless communication devices for wireless sensing. A first wireless communication device may be configured to generate network or transport layer messages addressed to a second wireless communication device in a wireless communication network, and wirelessly transmit the network or transport layer messages to the second wireless communication device to elicit MIMO transmissions from the second wireless communication device. The first wireless communication device may further be configured to receive MIMO transmissions from the second wireless communication device, where the MIMO transmissions traverse a space between the first wireless communication device and the second wireless communication device.
Abstract: Disclosed herein are an apparatus and method for analyzing a cephalometric image. The apparatus for analyzing a cephalometric image includes a control unit configured to extract a landmark point on a cephalometric image and to generate an analysis image, and memory configured to store the generated analysis image.
Type:
Grant
Filed:
June 4, 2019
Date of Patent:
May 25, 2021
Assignee:
LAONPEOPLE INC.
Inventors:
Moon seop Yum, Tae Woong Kim, Jae Min Park, Suk Joong Lee, Sung Bae Park
Abstract: A system for inspecting objects includes an imaging assembly, a detection module, an analysis module, and a memory. The imagining assembly can be a borescope that enters an unlit, closed conduit to inspect objects that are components of a turbine engine. Using an artificial light source to illuminate the conduit and one or more objects of the turbine engine, the borescope can obtain a video image of the one or more objects of the turbine engine. The video image can be used to determine a rank of distress for the one or more objects.
Abstract: An improved method of performing object segmentation and classification that reduces the memory required to perform these tasks, while increasing predictive accuracy. The improved method utilizes a capsule network with dynamic routing. Capsule networks allow for the preservation of information about the input by replacing max-pooling layers with convolutional strides and dynamic routing, allowing for the reconstruction of an input image from output capsule vectors. The present invention expands the use of capsule networks to the task of object segmentation and medical image-based cancer diagnosis for the first time in the literature; extends the idea of convolutional capsules with locally-connected routing and propose the concept of deconvolutional capsules; extends the masked reconstruction to reconstruct the positive input class; and proposes a capsule-based pooling operation for diagnosis.
Type:
Grant
Filed:
June 4, 2019
Date of Patent:
May 18, 2021
Assignee:
University of Central Florida Research Foundation, Inc.
Abstract: The method includes indentifying the beer keg to a brewery which fills the keg and for identifying the date on which the beer keg is filled. A sensor system is attachable to or built into the beer keg for identifying the temperature of the beer and for locating the keg. A communication system directly transmits information between the brewery and the sensor system on the keg.
Abstract: Embodiments generally relate to action detection in a video based on image analysis. In some embodiments, a method includes obtaining a plurality of images associated with an activity between a first object and a second object. The method further includes performing image analysis on the plurality of images to identify one or more portions of the first object and one or more portions of the second object. The method further includes, based on the image analysis, detecting at least one interaction between a given portion of the first object with a given portion of the second object in one or more images of the plurality of images. The method further includes, based on one or more positions of the given portion of the first object and the given portion of the second object in the one or more images of the plurality of images, determining one or more characteristics of the interaction.
Type:
Grant
Filed:
September 11, 2019
Date of Patent:
May 11, 2021
Assignee:
International Business Machines Corporation
Inventors:
Trent W. Boyer, Steve McDuff, Ethan S. Headings
Abstract: The object of the present invention is to assess the driving aptitude of a target person. Provided is a driving aptitude assessment apparatus 200 including: functional impairment degree assessment means configured to assess the degree of functional impairment of a brain of a target person on the basis of test result information indicating a result of a neuropsychological test administered to the target person and head image data obtained by tomography of a head of the target person; and driving aptitude assessment means configured to assess the driving aptitude of the target person on the basis of an assessment result by the functional impairment degree assessment means.