Patents Examined by Qun Shen
-
Patent number: 11977675Abstract: A computer-implemented method of detecting distracted driving comprises: determining, by one or more processors, a primary preview region (PPR) in a representation of an environment; determining, by the one or more processors, a gaze point for a driver based on a sequence of images of the driver; determining, by the one or more processors, that the gaze point is outside of the PPR; based on the determined gaze point being outside of the PPR, decreasing, by the one or more processors, an attention level for the PPR; based on the attention level for the PPR, generating, by the one or more processors, an alert.Type: GrantFiled: April 9, 2021Date of Patent: May 7, 2024Assignee: Futurewei Technologies, Inc.Inventors: Hai Yu, Fatih Porikli, Yuzhu Wu
-
Patent number: 11978213Abstract: Illustrative embodiments are directed to a method and apparatus for evaluating boundary detection in an image. A processed image is received, wherein a detected boundary of an image of an object is identified in the processed image. A Radon transform is applied to the processed image for a plurality of angles to form a processed image histogram corresponding to the detected boundary for each of the plurality of angles. The processed image histogram for each of the plurality of angles and a corresponding ground truth histogram for each of the plurality of angles is normalized to provide a normalized processed image histogram and a normalized ground truth histogram for each of the plurality of angles, wherein the ground truth histogram corresponds to a ground truth boundary of the object for a corresponding angle. An indication of the edges of the normalized processed image histogram for each of the plurality of angles is plotted to form a boundary detection evaluation visualization.Type: GrantFiled: May 18, 2021Date of Patent: May 7, 2024Assignee: National Technology & Engineering Solutions of Sandia, LLCInventors: Andrew C. Wantuch, Kyle Saxberg, Edward Steven Jimenez, Jr., Jaxon Gittinger, Srivathsan Koundinyan
-
Patent number: 11954919Abstract: Systems and methods are provided for developing/updating training datasets for traffic light detection/perception models. V2I-based information may indicate a particular traffic light state/state of transition. This information can be compared to a traffic light perception prediction. When the prediction is inconsistent with the V2I-based information, data regarding the condition(s)/traffic light(s)/etc. can be saved and uploaded to a training database to update/refine the training dataset(s) maintained therein. In this way, an existing traffic light perception model can be updated/improved and/or a better traffic light perception model can be developed.Type: GrantFiled: October 8, 2020Date of Patent: April 9, 2024Assignee: TOYOTA RESEARCH INSTITUTE, INC.Inventors: Kun-Hsin Chen, Peiyan Gong, Shunsho Kaku, Sudeep Pillai, Hai Jin, Sarah Yoo, David L. Garber, Ryan W. Wolcott
-
Patent number: 11947628Abstract: A messaging system that extracts accompaniment portions from songs. Methods of accompaniment extraction from songs includes receiving an input song that includes a vocal portion and an accompaniment portion, transforming the input song to an input image, where the input image represents the frequencies and intensities of the input song, processing the input image using a convolutional neural network (CNN) to generate an output image, and transforming the output image to an output accompaniment, where the output accompaniment includes the accompaniment of the input song.Type: GrantFiled: March 30, 2021Date of Patent: April 2, 2024Assignee: Snap Inc.Inventor: Gurunandan Krishnan Gorumkonda
-
Patent number: 11948080Abstract: An object of the present invention is to provide an image processing method and an image processing apparatus that make it possible to efficiently learn images having different identities. In learning and recognition using a hierarchical network, it is known that, based on experiences, a layer near the input functions as a feature extractor for extracting a feature that is necessary for recognition, and a layer near the output performs recognition by combining extracted features. Thus, performing learning by setting a higher learning rate to a layer near the input side of the hierarchical network than a learning rate in a layer near the output side in second learning processing as in an aspect of the present invention corresponds to mainly relearning (adjusting) a feature extraction portion in data sets having different identities. Accordingly, the difference between data sets can be absorbed, and learning can be performed more efficiently than in the case of simply performing transfer learning.Type: GrantFiled: January 27, 2021Date of Patent: April 2, 2024Assignee: FUJIFILM CorporationInventor: Shumpei Kamon
-
Patent number: 11934487Abstract: One example method includes a pipeline for a distributed neural network. The pipeline includes a first phase that identifies intersecting identifiers across datasets of multiple clients in a privacy preserving manner. The second phase includes a distributed neural network that includes a data receiving portion at each of the clients and an orchestrator portion at an orchestrator. The data receiving portions and the orchestrator portions communicate forward and backward passes to perform training without revealing the raw training data.Type: GrantFiled: September 30, 2020Date of Patent: March 19, 2024Assignee: EMC IP HOLDING COMPANY LLCInventors: Mohamed Abouzeid, Osama Taha Mohamed, AbdulRahman Diaa
-
Patent number: 11935313Abstract: Computer servers configured to perform digital image processing are discloses herein. In one embodiment, upon receiving a transcription command, a computer server performs text recognition based on patterns in a digital image to generate digital text data corresponding to the digital image. The computer server can then determine a content format of the digital text data based on the imported digital image and automatically apply the determined content format to the generated digital text data. The digital data can then be inserted into an electronic document.Type: GrantFiled: February 26, 2021Date of Patent: March 19, 2024Assignee: Microsoft Technology Licensing, LLCInventors: Tiancong Zhou, Yong Xie, Honghao Qiu
-
Patent number: 11924001Abstract: A system for adapting a water softener for wireless communication is disclosed. In some embodiments, a system for adapting a water softener with a serial communication port for communication with a user via a remote server, an internet connection, and internet enabled device is provided, the system comprising: a wireless gateway device connected to a router; and a wireless adapter connected to the serial communication port, comprising: a gateway node; a transceiver; and a processor programmed to: establish a wireless connection with the wireless gateway; receive a first message from the water softener; cause the gateway node to modify the first message; cause the first modified message to be transmitted to the remote server via the wireless gateway; receive a second message from the remote server; modify the second message for output to the water softener; and transmit the second modified message to the water softener.Type: GrantFiled: August 3, 2021Date of Patent: March 5, 2024Assignee: PENTAIR RESIDENTIAL FILTRATION, LLCInventors: Hassan Khalid, Micheal Pasche, Brian Broga, Robert Westphal, Brian Boothe
-
Patent number: 11921815Abstract: A server system can receive an input identifying a problem to generate a solution using a machine-learning application. The method selects a machine-learning model template from a plurality of templates based at least in part on the input. The method analyzes one or more formats of the customer data to generate a customer data schema based at least in part a data ontology that applies to the identified problem. The method determines whether the customer data schema is misaligned with one or more key features of the selected machine-learning model template. Based on this determination, the method analyzes the metadata for the selected machine-learning model template to determine what additional information is required to re-align the customer data with the data expectations. The method can include gathering the addition information required to re-align the customer data with the data expectations of the selected machine-learning model template.Type: GrantFiled: September 13, 2020Date of Patent: March 5, 2024Assignee: Oracle International CorporationInventors: Alberto Polleri, Sergio Aldea Lopez, Marc Michiel Bron, Dan David Golding, Alexander Ioannides, Maria del Rosario Mestre, Hugo Alexandre Pereira Monteiro, Oleg Gennadievich Shevelev, Larissa Cristina Dos Santos Romualdo Suzuki, Xiaoxue Zhao, Matthew Charles Rowe
-
Patent number: 11907841Abstract: A machine learning based system and method for automated recognition of consumer products in images and video using a camera system, a neural network using a ranked tagging system, a two-stage recognition application, and a training module. Training image sets of items captured by the camera system are assigned identification tags through template matches to training sets within the neural network. Tags are assigned from various levels of specificity to identify exact product matches. A user recognition application captures images and generates bounding boxes for detected objects and assigns a general classification within the image using a single, fast, convolutional neural network (CNN) layer. General classification narrows subsets for each generated bounding box and multi-scale template matching is applied to achieve detailed identification of single or multiple items detected within single images or video. The training module adjusts smart camera systems and the neural network based on accuracy feedback.Type: GrantFiled: May 1, 2023Date of Patent: February 20, 2024Inventor: Ian Truitner
-
Patent number: 11910203Abstract: A communications device inputs channel state information to an artificial neural network. The communications device predicts weather conditions with the artificial neural network based on the channel state information. The communications device further adjusts communications based on the predicted weather conditions.Type: GrantFiled: September 24, 2020Date of Patent: February 20, 2024Assignee: QUALCOMM IncorporatedInventors: Shay Landis, Assaf Touboul, Guy Wolf, Peer Berger, David Yunusov, Ran Berliner, Michael Levitsky, Sharon Levy, Noam Zach
-
Patent number: 11907334Abstract: A first classification is received from a neural network regarding a training dataset sent to the neural network. A modified training dataset with a perturbation of the training dataset is identified, where this modified training dataset causes the neural network to return a second classification. The perturbation is analyzed to identify a negative rule of the neural network.Type: GrantFiled: December 8, 2020Date of Patent: February 20, 2024Assignee: International Business Machines CorporationInventors: Franck Vinh Le, Mudhakar Srivatsa
-
Patent number: 11900658Abstract: Embodiments of the present disclosure are directed towards systems and methods for automated stratigraphy interpretation from borehole images. Embodiments may include constructing, using at least one processor, a training set of synthetic images corresponding to a borehole, wherein the training set includes one or more of synthetic images, real images, and modified images. Embodiments may further include automatically classifying, using the at least one processor, the training set into one or more individual sedimentary geometries using one or machine learning techniques. Embodiments may also include automatically classifying, using the at least one processor, the training set into one or more priors for depositional environments.Type: GrantFiled: March 11, 2020Date of Patent: February 13, 2024Assignee: SCHLUMBERGER TECHNOLOGY CORPORATIONInventors: Marie LeFranc, Zikri Bayraktar, Morten Kristensen, Philippe Marza, Isabelle Le Nir, Michael Prange, Josselin Kherroubi
-
Patent number: 11893783Abstract: A neural processing unit (NPU) for decoding video or feature map is provided. The NPU may comprise at least one processing element (PE) to perform an inference using an artificial neural network. The at least one PE may be configured to receive and decode data included in a bitstream. The data included in the bitstream may comprise data of a base layer. Alternatively, the data included in the bitstream may comprise data of the base layer and data of at least one enhancement layer. The data of the base layer included in the bitstream may include a first feature map. The data of the at least one enhancement layer included in the bitstream may include a second feature map.Type: GrantFiled: May 15, 2023Date of Patent: February 6, 2024Assignee: DEEPX CO., LTD.Inventors: Lok Won Kim, Ha Joon Yu
-
Patent number: 11880430Abstract: A computer-implemented method for predicting a cropland data layer (CDL) for a current year includes: retrieving a first set of records from a historical CDL database, where the first set corresponds to sampled areas of a region taken over a period for a number of years; retrieving a second set of records from a historical imagery database, where the second set corresponds to the sampled areas of the region, the period, and the number of years; employing the second set as inputs to train a deep learning network to generate the first set; retrieving a third set of records from a current imagery database, where the third set corresponds to a prescribed region, and where the third set corresponds to the time period and the current year; and using the third set as inputs and executing the trained deep learning network to generate a predicted CDL for the current year.Type: GrantFiled: May 31, 2021Date of Patent: January 23, 2024Assignee: CIBO Technologies, Inc.Inventors: Ernesto Brau, R. Shane Bussmann, Ethan Sargent
-
Patent number: 11856276Abstract: Methods and systems are disclosed for automatic generation of content distribution images that include receiving user input corresponding to a content-distribution operation. The user input may be parsed to identify keywords. Image data corresponding to the keywords can be identified. Image-processing operations may be executed on the image data. Executing a generative adversarial network on the processed image data, which includes: executing a first neural network on the processed-image data to generate first images that correspond to the keywords, the first images generated based on a likelihood that each image of the first images would not be detected as having been generated by the first neural network. A user interface can display the first images with second images that include images that were previously part of content-distribution operations or images that were designated by an entity as being available for content-distribution operations.Type: GrantFiled: September 10, 2020Date of Patent: December 26, 2023Assignee: Oracle International CorporationInventor: Abhik Banerjee
-
Patent number: 11829442Abstract: Some embodiments of the current disclosure disclose methods and systems for batch active learning using the Shapley values of data points. In some embodiments, Shapley values of a first subset of labeled data are used to measure the contributions of the first subset of data to the performance of neural network. Further, a regression model that correlates the first subset of data to their Shapley values is trained to predict the Shapley values of a second subset of data that are unlabeled. A portion of the second subset of data may then be selected for labeling based on the predicted Shapley values.Type: GrantFiled: January 18, 2021Date of Patent: November 28, 2023Assignee: salesforce.com, inc.Inventors: Amirata Ghorbani, Carlos Andres Esteva
-
Patent number: 11830103Abstract: A method, apparatus and computer program product train a signature encoding module (SEM) and a query processing module (QPM). The method generates a digital signature of an object of interest in a reference image provided to the SEM, and provides the SEM with at least one additional reference image that comprises a variation of the reference image and generates a digital signature for the at least one additional reference images. The method also provides the QPM with a query image and a digital signature set comprising the digital signature and the at least one additional digital signature, identifies the object of interest within the query image using the digital signature set, and modifies the SEM or QPM based upon a difference between the object of interest identified within the query image and the object of interest in the reference image or the at least one additional reference image.Type: GrantFiled: December 23, 2020Date of Patent: November 28, 2023Assignee: HERE GLOBAL B.V.Inventors: Ofer Melnik, Alastair Sutherland
-
Patent number: 11822456Abstract: The present disclosure relates to a system and a method for model control platform stack. The method includes, at an input layer of a model control platform stack, receiving input data. At a governance layer of the model control platform stack, the method includes maintaining a probe and model inventories; selecting a model, a monitoring location point, and a probe; and deploying, based on the selections of the probe and the model, a container to an orchestration layer of the model control platform stack. At the orchestration layer of the model control platform stack, the method includes accessing the container; using the container to deploy the probe and the model; scheduling an execution of the model to determine inference associated with the input data; during the execution, extracting probe data, using the probe, from the monitoring location point; and adjusting, based on the probe data and the inference, the model.Type: GrantFiled: June 9, 2020Date of Patent: November 21, 2023Assignee: ACCENTURE GLOBAL SOLUTIONS LIMITEDInventors: Jean-Luc Chatelain, Louis Gerald Farfan, Teresa Sheausan Tung, Fabio Bucci
-
Patent number: 11816570Abstract: A method for accelerated detection of objects in videos, a server, and a non-transitory computer readable storage medium are provided. The method realizes the detection of a target object in a video by dividing all frame images in video images into preset groups of frame images, each group of frame images including a keyframe image and a non-keyframe image, using a detection box of a target in the keyframe image to generate a preselection box in the non-keyframe image, and detecting the location of the target in the preselection box.Type: GrantFiled: February 4, 2021Date of Patent: November 14, 2023Assignee: Ping An Technology (Shenzhen) Co., Ltd.Inventor: Ming Ye