Patents Examined by Leon-Viet Q. Nguyen
-
Patent number: 12136185Abstract: Systems and methods for image processing are described. The systems and methods include receiving a low-resolution image; generating a feature map based on the low-resolution image using an encoder of a student network, wherein the encoder of the student network is trained based on comparing a predicted feature map from the encoder of the student network and a fused feature map from a teacher network, and wherein the fused feature map represents a combination of first feature map from a high-resolution encoder of the teacher network and a second feature map from a low-resolution encoder of the teacher network; and decoding the feature map to obtain prediction information for the low-resolution image.Type: GrantFiled: November 16, 2021Date of Patent: November 5, 2024Assignee: ADOBE INC.Inventors: Jason Kuen, Jiuxiang Gu, Zhe Lin
-
Patent number: 12133725Abstract: A gait analysis apparatus 10 includes, a data acquisition unit 11 that acquires a three-dimensional point cloud data of a human to be analyzed, a center of gravity location calculation unit 12 that calculates coordinates of a center of gravity location on the three-dimensional point cloud data of the human to be analyzed by using coordinates of each point constituting the acquired three-dimensional point cloud data, and a gait index calculation unit 13 that calculates a gait index of the human to be analyzed by using the calculated center of gravity location.Type: GrantFiled: February 12, 2020Date of Patent: November 5, 2024Assignee: NEC Solution Innovators, Ltd.Inventors: Hiroki Terashima, Katsuyuki Nagai
-
Patent number: 12136146Abstract: A system for reconstructing a magnetic particle image based on a pre-trained model aims to address the influence by point spread function and reduce the computational and time costs, which results in low reconstruction accuracy, or high acquisition time and computational costs for high-precision images. The system is implemented by: generating a simulation system matrix; pre-training a pre-constructed neural network model, and fine-tuning a pre-trained neural network model by performing a downstream task; and inputting real data corresponding to the downstream task into the pre-trained neural network model after fine-tuning, thereby playing an auxiliary role to acquire a high-quality reconstructed MPI image. The system fits the relationship between different harmonics, which helps enhance frequency-domain information.Type: GrantFiled: June 24, 2024Date of Patent: November 5, 2024Assignee: INSTITUTE OF AUTOMATION, CHINESE ACADEMY OF SCIENCESInventors: Jie Tian, Zechen Wei, Hui Hui, Xin Yang
-
Patent number: 12131401Abstract: A dual watermarking method for trajectory data based on robust watermarking and fragile watermarking uses an encryption algorithm to construct robust watermark information, and then a farthest pair of feature points in a minimum convex hull of is set as constant points. Further quantization index modulation technology is used to embed robust watermark information into angles constructed from feature points and constant points. Finally, the angles and distance ratios constructed by trajectory points and constant points are used to group trajectory points. Within each group, spatiotemporal attributes of the trajectory points are taken as fragile watermark bits to be embedded in the distance ratios constructed by the trajectory points. A process of watermark detection is consistent with the embedding of watermark information. Watermarks embedded in the trajectory data based on the dual watermarking method have high robustness against translation, rotation, and scaling attacks.Type: GrantFiled: June 3, 2024Date of Patent: October 29, 2024Assignee: Nanjing Normal UniversityInventors: Na Ren, Yuchen Hu, Changqing Zhu, Qianwen Zhou
-
Patent number: 12122420Abstract: A raycaster performs a raycasting algorithm, where the raycasting algorithm takes, as an input, a sparse hierarchical volumetric data structure. Performing the raycasting algorithm includes casting a plurality of rays from a reference point into the 3D volume, and, for each of the plurality of rays, traversing the ray to determine whether voxels in the set of voxels are intersected by the ray and are occupied, where the ray is to be traversed according to an approximate traversal algorithm.Type: GrantFiled: August 29, 2019Date of Patent: October 22, 2024Assignee: Intel CorporationInventors: Dexmont Alejandro Carillo Peña, Luis Manuel Rodríguez Martin de la Sierra, Carlos Marquez Rodriguez-Peral, Luca Sarti, David Macdara Moloney, Sam Caulfield, Jonathan David Byrne
-
Patent number: 12119091Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for training and utilizing generative machine learning models to generate embeddings from phenomic images (or other microscopy representations). For example, the disclosed systems can train a generative machine learning model (e.g., a masked autoencoder generative model) to generate predicted (or reconstructed) phenomic images from masked version of ground truth training phenomic images. In some cases, the disclosed systems utilize a momentum-tracking optimizer while reducing a loss of the generative machine learning model to enable efficient training on large scale training image batches. Furthermore, the disclosed systems can utilize Fourier transformation losses with multi-stage weighting to improve the accuracy of the generative machine learning model on the phenomic images during training.Type: GrantFiled: December 19, 2023Date of Patent: October 15, 2024Assignee: Recursion Pharmaceuticals, Inc.Inventors: Oren Zeev Kraus, Kian Runnels Kenyon-Dean, Mohammadsadegh Saberian, Maryam Fallah, Peter Foster McLean, Jessica Wai Yin Leung, Vasudev Sharma, Ayla Yasmin Khan, Jaichitra Balakrishnan, Safiye Celik, Dominique Beaini, Maciej Sypetkowski, Chi Cheng, Kristen Rose Morse, Maureen Katherine Makes, Benjamin John Mabey, Berton Allen Earnshaw
-
Patent number: 12112485Abstract: Disclosed herein is a system and method for obtaining and generating motion capture datasets relating to various working activities for ergonomic risk assessment. An example system may comprise a computing device that obtains first data from multiple motion capture cameras, obtains second data from multiple visible light imaging sensors, calculates 3D positions of multiple reflective markers positioned on several subjects performing various working activities based on the first data, labels each marker to generate marker trajectories, performs gap filing and smoothing functions on the marker trajectories to generate global marker positions, transforms the global marker positions into a corresponding image coordinate system of each sensor to generate 3D pose data of the subjects at each sensor viewpoint, projects the 3D pose data into frames of the second data to generate 2D pose data, and generates a dataset comprising the second data, the 2D pose data, and the 3D pose data.Type: GrantFiled: January 22, 2024Date of Patent: October 8, 2024Assignee: VelocityEHS Holdings Inc.Inventors: Julia Penfield, Leyang Wen, Veeru Talreja, Daeho Kim, Meiyin Liu, Richard Thomas Barker, SangHyun Lee
-
Patent number: 12106486Abstract: Methods and systems are disclosed for performing operations comprising: receiving a monocular image that includes a depiction of a whole body of a user; generating a segmentation of the whole body of the user based on the monocular image by applying one or more machine learning techniques; receiving input that selects a visualization mode; and applying one or more visual effects corresponding to the visualization mode to the monocular image based on the segmentation.Type: GrantFiled: February 24, 2021Date of Patent: October 1, 2024Assignee: SNAP INC.Inventors: Gal Dudovitch, Peleg Harel, Chia-Hao Hsieh, Sergei Korolev, Ma'ayan Shuvi
-
Patent number: 12094572Abstract: The present disclosure provides methods, systems, and computer program products that use deep learning models to classify candidate mutations detected in sequencing data, particularly suboptimal sequencing data. The methods, systems, and programs provide for increased efficiency, accuracy, and speed in identifying mutations from a wide range of sequencing data.Type: GrantFiled: August 5, 2022Date of Patent: September 17, 2024Assignee: NVIDIA CorporationInventors: Johnny Israeli, Avantika Lal, Michael Vella, Nikolai Yakovenko, Zhen Hu
-
Patent number: 12094096Abstract: In a method for defecting surface defects, a weighting generated when defect-free training samples are used to train an autoencoder and pixel convolutional neural network is obtained. A test encoding feature is obtained by inputting the weighting into the autoencoder and pixel convolutional neural network and encoding a test sample with a weighted autoencoder of the weighted autoencoder and pixel convolutional neural network. The test encoding feature is divided into many sub-test encoding features. The sub-test encoding features are input into a weighted pixel convolution neural network of the weighted autoencoder and pixel convolutional neural network one by one to output a result of test, the test result being either no defect in the test sample or at least one defect in the test sample. Inaccurate defect determinations are avoided, and accurate determinations even of fine defects improved. An electronic device and a non-transitory storage medium are also disclosed.Type: GrantFiled: December 29, 2021Date of Patent: September 17, 2024Assignee: HON HAI PRECISION INDUSTRY CO., LTD.Inventors: Tung-Tso Tsai, Chin-Pin Kuo, Tzu-Chen Lin, Shih-Chao Chien
-
Patent number: 12087002Abstract: Embodiments of systems and methods to determine depth of soil coverage for an underground feature along a right-of-way are disclosed. In an embodiment, the method may include receiving a depth of cover measurement for the right-of-way. The method may include capturing baseline images of the right-of-way within a first selected time of the depth of cover measurement. The method may include rendering a three dimensional elevation model of the right-of-way from the baseline images. The method may include georeferencing the three dimensional elevation model to generate a georeferenced three dimensional elevation model. The method may include adding the depth of cover measurement to the georeferenced three dimensional elevation model. The method may include rendering an updated three dimensional elevation model of the right-of-way from subsequently captured images. The method may include determining a delta depth of coverage based on the georeferenced and the updated three dimensional elevation model.Type: GrantFiled: February 28, 2024Date of Patent: September 10, 2024Assignee: MARATHON PETROLEUM COMPANY LPInventors: Luke R. Miller, Joshua J. Beard, Brittan Battles
-
Patent number: 12080080Abstract: Systems, methods, and computer program products that are configured to identify or otherwise detect the presence of bacteria, classify the identified or detected bacteria, and also predict the growth of the classified bacteria on various touchable surfaces within a vehicle passenger cabin or compartment. Such systems, methods, and computer program products are configured to identify/detect, classify, and predict the presence and/or growth of bacteria, and transmit one or more alerts, warnings, and/or reports to vehicle owners, service providers, and/or occupants based on the identification/detection, classification, and prediction.Type: GrantFiled: July 12, 2021Date of Patent: September 3, 2024Assignee: TOYOTA MOTOR ENGINEERING & MANUFACTURING NORTH AMERICA, INC.Inventors: Rohit Gupta, Ziran Wang, Yanbing Wang, Kyungtae Han, Prashant Tiwari
-
Patent number: 12079580Abstract: An information extraction method, an extraction model training method, an apparatus and an electronic device all relate to knowledge graphs. A specific implementation includes acquiring an input text and determining a semantic vector of the input text according to the input text. Such implementation also includes inputting the semantic vector of the input text to a pre-acquired extraction model to obtain a first enhanced text of the input text. The first enhanced text is a text with a text score greater than a preset threshold output by the extraction model. The extraction model performs text extraction based on the semantic vector of the input text. Since the semantic vector has rich context semantics, the enhanced text extracted by the extraction model can be more in line with the context of the input text.Type: GrantFiled: June 15, 2021Date of Patent: September 3, 2024Assignee: Beijing Baidu Netcom Science Technology Co., Ltd.Inventors: Tao Huang, Baohui Wang, Li Liu, Litao Zheng
-
Patent number: 12073594Abstract: A sequence of three-dimension scenes is encoded as a video by an encoder and transmitted to a decoder which retrieves the sequence of 3D scenes. Points of a 3D scene visible from a determined point of view are encoded as a color image in a first track of the stream in order to be decodable independently from other tracks of the stream. The color image is compatible with a three degrees of freedom rendering. Depth information and depth and color of residual points of the scene are encoded in separate tracks of the stream and are decoded only in case the decoder is configured to decode the scene for a volumetric rendering.Type: GrantFiled: June 24, 2019Date of Patent: August 27, 2024Assignee: INTERDIGITAL VC HOLDINGS, INC.Inventors: Julien Fleureau, Bertrand Chupeau, Gerard Briand, Renaud Dore, Thierry Tapie, Franck Thudor
-
Patent number: 12073638Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for utilizing machine learning and digital embedding processes to generate digital maps of biology and user interfaces for evaluating map efficacy. In particular, in one or more embodiments, the disclosed systems receive perturbation data for a plurality of perturbation experiment units corresponding to a plurality of perturbation classes. Further, the systems generate, utilizing a machine learning model, a plurality of perturbation experiment unit embeddings from the perturbation data. Additionally, the systems align, utilizing an alignment model, the plurality of perturbation experiment unit embeddings to generate aligned perturbation unit embeddings. Moreover, the systems aggregate the aligned perturbation unit embeddings to generate aggregated embeddings. Furthermore, the systems generate perturbation comparisons utilizing the perturbation-level embeddings.Type: GrantFiled: December 21, 2023Date of Patent: August 27, 2024Assignee: Recursion Pharmaceuticals, Inc.Inventors: Nathan Henry Lazar, Conor Austin Forsman Tillinghast, James Douglas Jensen, James Benjamin Taylor, Berton Allen Earnshaw, Marta Marie Fay, Renat Nailevich Khaliullin, Jacob Carter Cooper, Imran Saeedul Haque, Seyhmus Guler, Kyle Rollins Hansen, Safiye Celik
-
Patent number: 12067732Abstract: A computer-implemented neural network system for decomposing input video data. A video data input receives a sequence of video image frames. The sequence is encoded, using a 3D spatio-temporal encoder neural network, into a set of latent variables representing a compressed version of the sequence. A 3D spatio-temporal decoder neural network processes the set of latent variables to generate two or more sets of decomposed video data; these may be stored, communicated, and/or made available to a user interface. Input video including undesired features such as reflections, shadows, and occlusions may thus be decomposed into two or more video sequences, one in which the undesired features are suppressed, and another containing the undesired features.Type: GrantFiled: November 20, 2019Date of Patent: August 20, 2024Assignee: DeepMind Technologies LimitedInventors: Joao Carreira, Jean-Baptiste Alayrac, Andrew Zisserman
-
Patent number: 12062154Abstract: An image correcting method of the present invention includes: a step of performing a preprocessing process on an original image to generate a mask image including only an erased area of the original image; a step of predicting, by using generative adversarial networks, an image which is to be synthesized with the erased area in the mask image; and a step of synthesizing the predicted image with the erased area of the original image to generate a new image.Type: GrantFiled: March 5, 2020Date of Patent: August 13, 2024Assignee: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTEInventors: Young Joo Jo, Jong Youl Park, Yu Seok Bae
-
Patent number: 12058448Abstract: An adaptive approach to image bracket determination and a more memory-efficient approach to image fusion, which are designed to generate low noise and high dynamic range (HDR) images in a wide variety of capturing conditions, are described. An incoming preview image stream may be obtained from an image capture device. When a capture request is received, an analysis may be performed on an image from the preview image stream that has a predetermined temporal relationship to the image capture request. Based on the analysis, a set of images (and their respective capture parameters, e.g., exposure time) may be determined for the image capture device to capture. As the determined set of images are captured, they may be registered and fused in a memory-efficient manner that, e.g., places an upper limit on the overall memory footprint of the registration and fusion operations—regardless of how many images are captured in total.Type: GrantFiled: September 9, 2019Date of Patent: August 6, 2024Assignee: Apple Inc.Inventors: Hao Sun, Gijesh Varghese, Tak Shing Wong, Farhan A. Bagai, Morten Poulsen, Wu Cheng, Su Wang, Alok Deshpande
-
Patent number: 12056898Abstract: The disclosure relates to assessing operation of a camera. In one instance, a volume of space corresponding to a first vehicle in an environment of a second vehicle may be identified using sensor data generated by a LIDAR system of the second vehicle. An image captured by a camera of the second vehicle may be identified. The camera may have an overlapping field of view of the LIDAR system at a time when the sensor data was generated. An area of the image corresponding to the volume of space may be identified and processed in order to identify a vehicle light. The operation of the camera may be assessed based on the processing.Type: GrantFiled: December 13, 2021Date of Patent: August 6, 2024Assignee: Waymo LLCInventors: Chen Wu, Carl Warren Craddock, Andreas Wendel
-
Patent number: 12047614Abstract: A method and apparatus for sample adaptive offset without sign coding. The method includes selecting an edge offset type for at least a portion of an image, classifying at least one pixel of at least the portion of the image into edge shape category, calculating an offset of the pixel, determining the offset is larger or smaller than a predetermined threshold, changing a sign of the offset based on the threshold determination; and performing entropy coding accounting for the sign of the offset and the value of the offset.Type: GrantFiled: December 19, 2023Date of Patent: July 23, 2024Assignee: Texas Instruments IncorporatedInventors: Woo-Shik Kim, Do-Kyoung Kwon