Patents Examined by Vincent Rudolph
-
Patent number: 11862325Abstract: This disclosure provides a system and a method. The method may include: determining a processing instruction; acquiring image data based on the processing instruction; determining a configuration file based on the image data, in which the configuration file may be configured to guide implementation of the processing instruction; constructing a data processing pipeline based on the configuration file; executing the data processing process based on the data processing pipeline, in which the data processing process may be generated based on the data processing pipeline; generating a processing result of the image data based on the executed data processing process; and storing the processing result of the image data in a first storage space.Type: GrantFiled: July 26, 2022Date of Patent: January 2, 2024Assignee: SHANGHAI UNITED IMAGING HEALTHCARE CO., LTD.Inventors: Zhongqi Zhang, Anling Ma
-
Patent number: 11861917Abstract: Method and system for detecting vehicle occupant actions are disclosed. For example, the method includes receiving, by one or more processors, previously classified image data from a previously classified image database, the previously classified image data representing driver postures that are rotated and scaled to be standardized for a range of different drivers and different locations of a vehicle interior sensor within a given vehicle, wherein the previously classified image data is representative of previously classified vehicle occupant actions; receiving, by the one or more processors, current image data from the vehicle interior sensor subsequent to the vehicle interior sensor being registered within the given vehicle, wherein the current image data is representative of current vehicle occupant actions; and determining, by the one or more processors, a vehicle occupant action based at least in part upon a comparison of the current image data and the previously classified image data.Type: GrantFiled: July 29, 2022Date of Patent: January 2, 2024Assignee: STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANIESInventors: Aaron Scott Chan, Kenneth J. Sanchez
-
Patent number: 11854283Abstract: The present disclosure provides a method for visual question answering, which relates to fields of computer vision and natural language processing. The method includes: acquiring an input image and an input question; detecting visual information and position information of each of at least one text region in the input image; determining semantic information and attribute information of each of the at least one text region based on the visual information and the position information; determining a global feature of the input image based on the visual information, the position information, the semantic information, and the attribute information; determining a question feature based on the input question; and generating a predicted answer for the input image and the input question based on the global feature and the question feature. The present disclosure further provides a device for visual question answering, a computer device and a medium.Type: GrantFiled: February 5, 2021Date of Patent: December 26, 2023Assignee: Beijing Baidu Netcom Science Technology Co., Ltd.Inventors: Pengyuan Lv, Xiaoqiang Zhang, Shanshan Liu, Chengquan Zhang, Qiming Peng, Sijin Wu, Hua Lu, Yongfeng Chen
-
Method, apparatus, device and storage medium for extracting a cardiovascular vessel from a CTA image
Patent number: 11816840Abstract: A method, an apparatus, a device, and a storage medium for extracting a cardiovascular vessel from a CTA image, the method including the steps of: performing erosion operation and dilation operation on image data successively via a preset structural element to obtain a structure mask; performing a slice-by-slice transformation on the plane of section images of the structural mask to acquire the first ascending aortic structure in the structural mask, and acquiring an aortic center position and an aortic radius in the last slice of the plane of section image of the said structural mask; establishing a binarized sphere structure according to the aortic center position and the aortic radius, and synthesizing a second ascending aorta structure by combining the first ascending aorta structure with the structure mask and the binarized sphere structure.Type: GrantFiled: July 26, 2017Date of Patent: November 14, 2023Assignee: Shenzhen Institutes of Advanced TechnologyInventors: Shoujun Zhou, Baochang Zhang, Baolin Li, Cheng Wang, Pei Lu -
Patent number: 11810387Abstract: Example implementations involve a location system, which can involve associating each location of one or more unidentified targets detected from sensor data of the one or more sensors with identifiers corresponding to the transmitter of each of the one or more pairs of electronic devices, by calculating first distance relationships indicative of relationships of distances between the each location of the one or more unidentified targets detected from the sensor data of the one or more sensors and a reference point; calculating second distance relationships indicative of relationships of distances between the transmitter and the receiver of each of the one or more pairs of electronic devices; and associating the identifiers corresponding to the transmitter of the each of the one or more pairs of electronic devices with the each location of the one or more unidentified targets based on the first distance relationships and the second distance relationships.Type: GrantFiled: May 6, 2021Date of Patent: November 7, 2023Assignee: HITACHI, LTD.Inventors: Daisuke Maeda, Sudhanshu Gaur
-
Patent number: 11803958Abstract: The disclosure relates to methods and systems for determining muscle fascicle fracturing in a meat sample. In one embodiment, the methods and systems disclosed herein use automated methods to determine muscle fascicle fracturing. Methods and systems disclosed herein comprise imaging a meat sample with an imaging device to obtain one or more images; and using an iteratively trained training detection model to determine an objective classification, including the presence or absence of muscle fascicle fracturing in the images of the meat sample.Type: GrantFiled: October 21, 2022Date of Patent: October 31, 2023Assignee: TRIUMPH FOODS LLCInventors: Emily Arkfeld, Barry Wiseman, Matt England
-
System of vehicles equipped with imaging equipment for high-definition near real-time map generation
Patent number: 11802968Abstract: Described are street level intelligence platforms, systems, and methods that can include a fleet of swarm vehicles having imaging devices. Images captured by the imaging devices can be used to produce and/or be integrated into maps of the area to produce high-definition maps in near real-time. Such maps may provide enhanced street level intelligence useful for fleet management, navigation, traffic monitoring, and/or so forth.Type: GrantFiled: May 31, 2018Date of Patent: October 31, 2023Assignee: Woven by Toyota, U.S., Inc.Inventors: Ro Gupta, Justin Day, Chase Nicholl, Max Henstell, Ioannis Stamos, David Boyle, Ethan Sorrelgreen, Huong Dinh -
Patent number: 11783635Abstract: A system for motion detection may include at least one storage medium that includes a set of instructions, and at least one processor in communication with the at least one storage medium. When executing the set of instructions, the at least one processor may be configured to cause the system to obtain data related to a video scene of a space from at least one video camera; detect an object in the video scene; classify the object as a human object or a non-human object; when the object is classified as a human object, track movements of the human object; and determine a posture of the human object in the video scene based on the movements of the human object.Type: GrantFiled: September 30, 2020Date of Patent: October 10, 2023Assignee: SHANGHAI TRUTHVISION INFORMATION TECHNOLOGY CO., LTD.Inventor: Zhong Zhang
-
Patent number: 11768932Abstract: Described herein are embodiments for fast training of adversarially robust models against adversarial attacks. Embodiments for model training by perturbing both the image and the label, which may be referred to as Bilateral Adversarial Training (BAT), are disclosed. To generate the adversarial label, one or more closed-form heuristic solutions are derived. One-step targeted attack is used with the target label being the most confusing class. It is shown in various experiments that random start and the most confusing target attack effectively prevent the label leaking and gradient masking problem. Coupled with the adversarial label part, embodiments of presented models significantly improve the state-of-the-art results. Experiments on one or more computationally challenging dataset also demonstrate the effectiveness of the presented BAT method embodiments.Type: GrantFiled: June 28, 2019Date of Patent: September 26, 2023Assignee: Baidu USA LLCInventors: Jianyu Wang, Haichao Zhang
-
Patent number: 11769228Abstract: A method includes receiving, by a computing device, training data comprising a plurality of pairs of images, wherein each pair comprises an image and at least one corresponding target version of the image. The method also includes training a neural network based on the training data to predict an enhanced version of an input image, wherein the training of the neural network comprises applying a forward Gaussian diffusion process that adds Gaussian noise to the at least one corresponding target version of each of the plurality of pairs of images to enable iterative denoising of the input image, wherein the iterative denoising is based on a reverse Markov chain associated with the forward Gaussian diffusion process. The method additionally includes outputting the trained neural network.Type: GrantFiled: August 2, 2021Date of Patent: September 26, 2023Assignee: Google LLCInventors: Chitwan Saharia, Jonathan Ho, William Chan, Tim Salimans, David Fleet, Mohammad Norouzi
-
Patent number: 11769583Abstract: In a method for generating at least one medical result image from a plurality of single-frame images, the plurality of single-frame images referring to a medical image acquisition procedure conducted with a medical imaging system, at least one first parameter representative for the medical image acquisition procedure is acquired, and the at least one first parameter is evaluated to generate an evaluation result. Based on the evaluation result, it is decided whether to: (i) combine at least partially the plurality of single-frame images to generate the result image before permanently storing the result image, or (ii) permanently store the plurality of single-frame images before combining them to generate the result image.Type: GrantFiled: March 20, 2020Date of Patent: September 26, 2023Assignee: Siemens Healthcare GmbHInventor: Armin Stranjak
-
Patent number: 11763583Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating and providing matching fonts by utilizing a glyph-based machine learning model. For example, the disclosed systems can generate a glyph image by arranging glyphs from a digital document according to an ordering rule. The disclosed systems can further identify target fonts as fonts that include the glyphs within the glyph image. The disclosed systems can further generate target glyph images by arranging glyphs of the target fonts according to the ordering rule. Based on the glyph image and the target glyph images, the disclosed systems can utilize a glyph-based machine learning model to generate and compare glyph image feature vectors. By comparing a glyph image feature vector with a target glyph image feature vector, the font matching system can identify one or more matching glyphs.Type: GrantFiled: November 29, 2021Date of Patent: September 19, 2023Assignee: Adobe Inc.Inventors: Monica Singh, Prateek Gaurav, Amish Kumar Bedi
-
Patent number: 11756166Abstract: A method includes receiving, by a computing device, training data comprising a plurality of pairs of images, wherein each pair comprises an image and at least one corresponding target version of the image. The method also includes training a neural network based on the training data to predict an enhanced version of an input image, wherein the training of the neural network comprises applying a forward Gaussian diffusion process that adds Gaussian noise to the at least one corresponding target version of each of the plurality of pairs of images to enable iterative denoising of the input image, wherein the iterative denoising is based on a reverse Markov chain associated with the forward Gaussian diffusion process. The method additionally includes outputting the trained neural network.Type: GrantFiled: January 17, 2023Date of Patent: September 12, 2023Assignee: Google LLCInventors: Chitwan Saharia, Jonathan Ho, William Chan, Tim Salimans, David Fleet, Mohammad Norouzi
-
Patent number: 11756213Abstract: An image sensor is positioned such that a field-of-view of the image sensor encompasses at least a portion of a rack storing items. The image sensor generates images of the items stored on the rack. Over a period of time, a tracking subsystem tracks a pixel position of the wrist of a person interacting with items stored on the rack, receives image frames of the angled-view images. The tracking subsystem determines whether an item was interacted with by a person and, if so, the identified item is assigned to the person.Type: GrantFiled: June 15, 2022Date of Patent: September 12, 2023Assignee: 7-ELEVEN, INC.Inventors: Sumedh Vilas Datar, Sailesh Bharathwaaj Krishnamurthy, Shahmeer Ali Mirza
-
Patent number: 11741599Abstract: Disclosed herein is a method of treating a subject having arterial stenosis. The method comprises: (a) providing a plurality of image frames of an artery of the subject taken in sequence; (b) in a plurality of cross-sections of the artery, determining a maximum diameter and a minimum diameter of each of the plurality of cross-sections of the artery among the plurality of image frames of the step (a); (c) calculating an average vasodilation ratio of the artery base on the maximum diameter and the minimum diameter determined in the step (b); and (d) treating the subject based on the average vasodilation ratio calculated in the step (c), by implanting a stent to the subject when the average vasodilation ratio is equal to or greater than 0.2; or administering to the subject an effective amount of a vasodilator when the average vasodilation ratio is less than 0.2.Type: GrantFiled: August 10, 2020Date of Patent: August 29, 2023Assignees: MacKay Memorial Hospital, National Chiao Tung UniversityInventors: Shen Chi, Po-Lin Lin, Ying-Hsiang Lee, Yu-Min Liu, Long Hsu, Ruo-Jing Ho, Chang Francis Hsu, Han-Ping Huang
-
Patent number: 11704773Abstract: Disclosed is an automatic reorientation method from an SPECT three-dimensional reconstructed image to a standard view, wherein a rigid registration parameter P between a SPECT three-dimensional reconstructed image A and a standard SPECT image R is extracted by using a rigid registration algorithm to form a mapping database of A and P; features of the image A are extracted by using a three-layer convolution module, and are converted into a 6-dimensional feature vector T after three times of full connection, and T is applied to A through a spatial transformer network to form an orientation result predicted by the network, thus establishing the automatic reorientation model of the SPECT three-dimensional reconstructed image. The SPECT three-dimensional reconstructed image to be orientated is taken as an input. A standard view can be obtained by using the automatic reorientation model of the SPECT three-dimensional reconstructed image for automatic turning.Type: GrantFiled: April 2, 2022Date of Patent: July 18, 2023Assignee: ZHEJIANG LABInventors: Duo Zhang, Wentao Zhu, Ling Chen, Fan Rao, Bao Yang, Hui Shen
-
Re-training a model for abnormality detection in medical scans based on a re-contrasted training set
Patent number: 11694137Abstract: A method includes generating first contrast significance data for a first computer vision model generated from a first training set of medical scans. First significant contrast parameters are identified based on the first contrast significance data. A first re-contrasted training set is generated based on performing a first intensity transformation function on the first training set of medical scans, where the first intensity transformation function utilizes the first significant contrast parameters. A first re-trained model is generated from the first re-contrasted training set, which is associated with corresponding output labels based on abnormality data for the first training set of medical scans. Re-contrasted image data of a new medical scan is generated based on performing the first intensity transformation function. Inference data indicating at least one abnormality detected in the new medical scan is generated based on utilizing the first re-trained model on the re-contrasted image data.Type: GrantFiled: March 25, 2022Date of Patent: July 4, 2023Assignee: Enlitic, Inc.Inventors: Li Yao, Jordan Prosky, Eric C. Poblenz, Kevin Lyman, Ben Covington, Anthony Upton -
Patent number: 11690701Abstract: A method of scanning an oral cavity including: acquiring, using an intraoral scanner (IOS) head, without changing a position of the IOS head, a first image of a first region of interest (ROI) and a second image of a second ROI where the first and the second ROIs are of different portions of a dental arch of the oral cavity and do not overlap; reconstructing depth information for the first and the second ROI; and generating a single model of the dental arch by combing the depth information.Type: GrantFiled: July 24, 2018Date of Patent: July 4, 2023Assignee: DENTLYTEC G.P.L. LTD.Inventors: Benny Pesach, Amitai Reuvenny
-
Patent number: 11694340Abstract: A display method including the steps of: acquiring, at a first predetermined frequency, a first series of one-spatial-dimensional instant images of the finish line of a race; simultaneously acquiring a second series of two spatial-dimensional instant images of the same finish line (19) at a second predetermined frequency; forming a temporal image (10) of the photo finish type from the first series of instant images; choosing an instant (15, 22) of the temporal image (10); analysing a two-spatial-dimensional image of the second series, the image being correlated with the selected instant (15, 22) to determine at least one distance; and displaying the analysed two-dimensional image with the determined distance or distances. Also, a display system for implementing the method.Type: GrantFiled: December 3, 2019Date of Patent: July 4, 2023Assignee: SWISS TIMING LTDInventors: Fabien Blondeau, Pascal Richard
-
Patent number: 11694136Abstract: A method includes generating a longitudinal lesion model by performing a training step on a plurality of sets of longitudinal data. Dates of medical scans of different ones of the plurality of sets of longitudinal data have relative time differences corresponding to different time spans, and each set of the plurality of sets of longitudinal data corresponds to one of a plurality of different patients. The longitudinal lesion model is utilized to perform an inference step on a received medical scan to generate, for a lesion detected in the received medical scan, a plurality of lesion change prediction data for a corresponding plurality of different projected time spans ending after the current date. At least one of the plurality of lesion change prediction data is transmitted for display.Type: GrantFiled: March 24, 2022Date of Patent: July 4, 2023Assignee: Enlitic, Inc.Inventors: Kevin Lyman, Anthony Upton, Ben Covington, Li Yao, Keith Lui