Patents Examined by Allen C. Wong
  • Patent number: 11361450
    Abstract: A method for continuously determining mutually corresponding pixels between a first camera image and a second camera image. The method includes recording the first camera image; recording the second camera image; ascertaining at least one first signature matrix element of a first signature matrix as a function of the first camera image; assigning first coordinates to an ascertained signature value of the first signature matrix element in a signature value position table; ascertaining at least one signature value of a second signature matrix element having second coordinates of a second signature matrix as a function of the second camera image; and determining at least one element of a correspondence matrix as a function of the signature value position table, of the cyclically ascertained signature value of the second signature matrix element and of the second coordinates of this second signature matrix element.
    Type: Grant
    Filed: May 9, 2019
    Date of Patent: June 14, 2022
    Assignee: Robert Bosch GmbH
    Inventor: Stephan Simon
  • Patent number: 11356694
    Abstract: By the moving picture coding method and the moving picture decoding method, it is possible to improve coding efficiency. The moving picture coding apparatus includes a merge block candidate calculation unit that (i) specifies merge block candidates at merge mode, by using colpic information such as motion vectors and reference picture index values of neighbor blocks of a current block to be coded and a motion vector and the like of a collocated block of the current block which are stored in a colPic memory, and (ii) generates a combined merge block by using the merge block candidates.
    Type: Grant
    Filed: April 14, 2021
    Date of Patent: June 7, 2022
    Assignee: SUN PATENT TRUST
    Inventors: Toshiyasu Sugio, Takahiro Nishi, Youji Shibahara, Hisao Sasai
  • Patent number: 11348340
    Abstract: Navigation systems can identify objects in an environment and generate representations of those objects. A representation of an articulated vehicle can include two segments rotated relative to each other about a pivot, with a first segment corresponding to a first portion of the articulated vehicle and the second segment corresponding to a second portion of the articulated vehicle. The articulated object can be tracked in the environment by generating estimated updated states of the articulated agent based on previous states and/or measured states of the object using differing motion model updates for the differing portions. The estimated updated states may be determined using one or more filtering algorithms, which may be constrained using pseudo-observables.
    Type: Grant
    Filed: February 28, 2020
    Date of Patent: May 31, 2022
    Assignee: Zoox, Inc.
    Inventors: Shiwei Sheng, Subhasis Das, Yassen Ivanchev Dobrev, Chuang Wang
  • Patent number: 11350104
    Abstract: Disclosed is a method, implemented by computer, for processing a video sequence including a set of images, which method includes: obtaining information indicating at least one image in the set of images to be encoded using a spatial correlation-based predictive coding mode, determining consecutive subsets of images in the set of images, and encoding the video sequence on the basis of the determined consecutive subsets of images, wherein the respective sizes of at least some of the subsets of images are dependent on the at least one image to be encoded using the spatial correlation-based predictive coding mode.
    Type: Grant
    Filed: June 26, 2020
    Date of Patent: May 31, 2022
    Assignee: ATEME
    Inventor: Anne-Lyse Lavaud
  • Patent number: 11338920
    Abstract: A method for guiding an autonomously movable machine by means of an optical communication device having associated identification, location and orientation information.
    Type: Grant
    Filed: November 4, 2020
    Date of Patent: May 24, 2022
    Assignee: BEIJING WHYHOW INFORMATION TECHNOLOGY CO., LTD.
    Inventors: Jun Fang, Xuheng Niu, Jiangliang Li
  • Patent number: 11341617
    Abstract: An inspection apparatus includes a specimen stage, one or more imaging devices and a set of lights, all controllable by a control system. By translating or rotating the one or more imaging devices or specimen stage, the inspection apparatus can capture a first image of the specimen that includes a first imaging artifact to a first side of a reference point and then capture a second image of the specimen that includes a second imaging artifact to a second side of the reference point. The first and second imaging artifacts can be cropped from the first image and the second image respectively, and the first image and the second image can be digitally stitched together to generate a composite image of the specimen that lacks the first and second imaging artifacts.
    Type: Grant
    Filed: February 8, 2021
    Date of Patent: May 24, 2022
    Assignee: Nanotronics Imaging, Inc.
    Inventors: Matthew C. Putman, John B. Putman, John Moffitt, Michael Moskie, Jeffrey Andresen, Scott Pozzi-Loyola, Julie Orlando
  • Patent number: 11341688
    Abstract: Optimization of a neural network, for example in a video codec at the decoder side, may be guided to limit overfitting. The encoder may encode video(s) with different qualities for different frames in the video. Low-quality frames may be used as both input and ground-truth during optimization. High-quality frames may be used to optimize the neural network so that higher-quality versions of lower-quality inputs may be predicted. The neural network may be trained to make such predictions by making a prediction based on a constructed low-quality input for which the corresponding high-quality version is known, comparing the prediction to the high-quality version, and fine-tuning the neural network to improve its ability to predict a high-quality version of a low-quality input. To limit overfitting, the neural network may be concurrently or in an alternating fashion trained with low-quality input for which a higher-quality version of the low-quality input is known.
    Type: Grant
    Filed: September 30, 2020
    Date of Patent: May 24, 2022
    Assignee: Nokia Technologies Oy
    Inventors: Alireza Zare, Francesco Cricri, Yat Hong Lam, Miska Matias Hannuksela, Jani Olavi Lainema
  • Patent number: 11336965
    Abstract: Provided are a method and apparatus for processing a video bitstream, a network device and a readable storage medium. The method includes: parsing a bitstream to be extracted, and acquiring parameter information about an extractable sub-bitstream from a data unit of the bitstream to be extracted; determining a picture type parameter value of a random access picture in the sub-bitstream according to the parameter information; and configuring, in a process of extracting the sub-bitstream from the bitstream to be extracted, a picture type parameter value in a data unit of the sub-bitstream according to the picture type parameter value of the random access picture.
    Type: Grant
    Filed: December 6, 2018
    Date of Patent: May 17, 2022
    Assignee: Xi'An Zhongxing New Software Co., Ltd.
    Inventors: Ming Li, Zhao Wu, Ping Wu, Xiaoquan Hua
  • Patent number: 11327285
    Abstract: An optical imaging equipment and method. The optical imaging equipment includes an optical microscope, an objective table, a light source module and an objective lens.
    Type: Grant
    Filed: April 12, 2021
    Date of Patent: May 10, 2022
    Assignee: Beijing Yapu Optical Instrument Technology Co., Ltd.
    Inventors: Hong Xiang, Anpei Ye
  • Patent number: 11330263
    Abstract: Techniques for machine learning based coded size estimation in rate control of video encoding are described. An encoder in accordance with various embodiments uses one or more machine learning approaches to facilitate the rate control of video encoding. When training one or more neural network models, the relationship between the coded size and unit characteristics (e.g., picture pixels and/or picture features) is learned from past encoding. The encoder then uses the trained model(s) to estimate the coded size through model inference with improved accuracy. In some embodiments, the trained model(s) are integrated into the encoder for direct model inference. The direct model inference reduces the overhead of referencing application programming interfaces (APIs) provided by a separate machine learning platform, thus making the rate control methods and systems described herein useful in real time video encoding.
    Type: Grant
    Filed: February 16, 2021
    Date of Patent: May 10, 2022
    Assignee: Synamedia Limited
    Inventors: Longji Wang, Cheng-Yu Pai, Stephen Warrington
  • Patent number: 11317104
    Abstract: Aspects of the disclosure provide methods, apparatuses, and non-transitory computer-readable storage mediums for video encoding/decoding. In a method, prediction information for a current picture that is a part of a coded video sequence is decoded. The prediction information indicates that the current picture includes a plurality of sub-pictures corresponding to different regions of the current picture. The plurality of sub-pictures includes (i) a first sub-picture that is associated with a first number of layers, and (ii) a second sub-picture that is associated with a second number of layers that is different from the first number of layers. One of the plurality of sub-pictures is reconstructed based on one or more layers associated with the one of the plurality of sub-pictures.
    Type: Grant
    Filed: May 11, 2020
    Date of Patent: April 26, 2022
    Assignee: TENCENT AMERICA LLC
    Inventors: Byeongdoo Choi, Iraj Sodagar, Shan Liu
  • Patent number: 11310418
    Abstract: A computer-implemented method is provided for automated detection of a moving area of interest, such as a ball, in a video stream of filed sports with a common object of interest encompassing a plurality of players and the object of interest. Images of a sports ground are captured by means of a video camera system producing a video stream which is digitally processed to continuously identify a detected concentration of action within the boundaries of the field. The concentration of action in the field is determined based on an estimated position of the object of interest in at least one frame of the video stream. Players' postures or orientations may be detected to improve the accuracy of the determination of the object of interest.
    Type: Grant
    Filed: January 18, 2019
    Date of Patent: April 19, 2022
    Assignee: VEO TECHNOLOGIES APS
    Inventors: Jesper Molbech Taxbol, Henrik Bjorn Teisbæk, Keld Reinicke
  • Patent number: 11303888
    Abstract: A picture encoding/decoding method and a related apparatus are provided. The picture decoding method includes obtaining a current picture; selecting, from a knowledge base, K reference pictures of the current picture, where at least one picture in the knowledge base does not belong to a random access segment in which the current picture is located and wherein K is an integer greater than or equal to 1; and decoding the current picture according to the K reference pictures.
    Type: Grant
    Filed: February 3, 2021
    Date of Patent: April 12, 2022
    Assignee: HUAWEI TECHNOLOGIES CO., LTD.
    Inventors: Lu Yu, Xuguang Zuo, Yin Zhao, Haitao Yang
  • Patent number: 11301986
    Abstract: A method for monitoring a plant health state relates to the technical field of intelligent agriculture. The method is used for intelligently determining the plant health state and timely prompting farmland managers to perform control for at least one plant in a poor plant health state. The method for monitoring the plant health state includes: performing first determination according to plant health state information; when a determination result is that there is a risk of poor plant health, performing second determination according to second plant health state information in an orientation where at least one plant at risk of poor plant health is located, so as to accurately obtain plant health state information, such that farmland managers can learn the current situation of the plant in a field timely and perform control timely. An apparatus applying the method for monitoring the plant health state is provided. The apparatus is used for monitoring the plant health state.
    Type: Grant
    Filed: August 15, 2018
    Date of Patent: April 12, 2022
    Assignee: GUANGZHOU XAIRCRAFT TECHNOLOGY CO., LTD
    Inventor: Bo Liu
  • Patent number: 11294623
    Abstract: Systems and methods for personalized quality assurance of inference models are provided. For example, data items associated with a group of devices may be obtained, results of applying the data items to inference models may be obtained, the results of applying the data items to a first inference model may be compared with the results of applying the data items to a second inference model, and the compatibility of the second inference model to the group of devices may be assessed, for example based on the comparison results. In some examples, when the second inference model is found compatible, the second inference model may be utilized in tasks associated with the group of devices. In some examples, when the second inference model is found incompatible, the system may forgo the usage of the second inference model in one or more tasks associated with the group of devices.
    Type: Grant
    Filed: July 30, 2018
    Date of Patent: April 5, 2022
    Assignee: ALLERO ARTIFICIAL INTELLIGENCE LTD
    Inventors: Moshe Guttmann, Ariel Yossef Biller, Dan Iosef Malowany
  • Patent number: 11287262
    Abstract: A visual positioning system for mobile devices includes at least one infrared camera, at least one infrared illumination source, and a processor that coordinates operation of the at least one camera and illumination sources. A flood IR infrared illumination source illuminates environmental objects for localization of the mobile device during a first camera exposure window, and a structured IR illumination source illuminate environmental objects for detection and mapping of obstacles during a second camera exposure window. A visual SLAM map is constructed with images obtained from a first camera, with a single map being useable for positioning and navigation across a variety of environmental lighting conditions.
    Type: Grant
    Filed: July 15, 2019
    Date of Patent: March 29, 2022
    Assignee: Labrador Systems, Inc.
    Inventors: Michael Dooley, Nikolai Romanov, James Philip Case
  • Patent number: 11276180
    Abstract: This disclosure describes, in part, techniques for selecting encoding parameters for an electronic device. For instance, remote system(s) may receive, from the electronic device, video data representing a video. The remote system(s) may then analyze the video data to identify portions of the video that represented different areas located within the field of view (FOV) of the electronic device. The areas may include static areas, which do not include recurring motion, and/or dynamic areas, which include recurring motion. Additionally, the remote system(s) may analyze the video data to select encoding parameters for encoding the video data and/or for encoding the portions of the video data that represent the identified areas. The electronic device may then receive the encoding parameters from the remote system(s) and use the encoding parameters to encode additional video data that is generated by the electronic device.
    Type: Grant
    Filed: September 27, 2019
    Date of Patent: March 15, 2022
    Assignee: Amazon Technologies, Inc.
    Inventors: Jason Gluckman, Ilya Vladimirovich Brailovskiy
  • Patent number: 11277631
    Abstract: Innovations in flexible reference picture management are described. For example, a video encoder and video decoder use a global reference picture set (“GRPS”) of reference pictures that remain in memory, and hence are available for use in video encoding/decoding, longer than conventional reference pictures. In particular, reference pictures of the GRPS remain available across random access boundaries. Or, as another example, a video encoder and video decoder clip a reference picture so that useful regions of the reference picture are retained in memory, while unhelpful or redundant regions of the reference picture are discarded. Reference picture clipping can reduce the amount of memory needed to store reference pictures or improve the utilization of available memory by providing better options for motion compensation. Or, as still another example, a video encoder and video decoder filter a reference picture to remove random noise (e.g., capture noise due to camera imperfections during capture).
    Type: Grant
    Filed: March 2, 2021
    Date of Patent: March 15, 2022
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Bin Li, Jizheng Xu
  • Patent number: 11262766
    Abstract: A pool cleaning system for cleaning debris from a submerged surface of a swimming pool includes a self-propelled pool cleaner having rotatably-mounted supports for supporting and guiding the cleaner on the pool surface; an electric motor for enabling the rotation of the rotatably-mounted supports on the pool surface; at least one camera to capture imagery of the pool surface; a controller, in electronic communication with the at least one camera, to determine a cleanliness characteristic of the pool surface on which the cleaner has passed based on the camera imagery and generate a control signal to direct movement of the cleaner based on the cleanliness characteristic of the pool surface, and a portable electronic device configured to present a graphic on a display, the graphic depicting the submerged surface of the pool and those portions of the surface that remain uncleaned as the cleaner traverses the pool surface.
    Type: Grant
    Filed: January 7, 2021
    Date of Patent: March 1, 2022
    Assignee: ZODIAC POOL SYSTEMS LLC
    Inventors: Kameshwar Durvasula, William Londono Correa
  • Patent number: 11265568
    Abstract: A method and system for decoding a coded video sequence may include obtaining the coded video sequence, and decoding the coded video sequence. A value of a temporal sublayer identifier of a video coding layer (VCL) network abstraction layer (NAL) unit in the coded video sequence is constrained to be less than or equal to a value of vps_max_sublayers_minus1, that specifies a maximum number of temporal sublayers that may be present in a layer in each coded video sequence referring to the video parameter set (VPS), in the VPS referred to by the VCL NAL unit.
    Type: Grant
    Filed: November 13, 2020
    Date of Patent: March 1, 2022
    Assignee: TENCENT AMERICA LLC
    Inventors: Byeongdoo Choi, Shan Liu, Stephan Wenger