Patents by Inventor Yongjun Wu

Yongjun Wu has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Publication number: 20190114499
    Abstract: An example preprocessor circuit for formatting image data into a plurality of streams of image samples includes: a first buffer configured to store a plurality of rows of the image data and output a row of the plurality of rows; a second buffer, coupled to the first buffer, including a plurality of storage locations to store a respective plurality of image samples of the row output by the first buffer; a plurality of shift registers; an interconnect network including a plurality of connections, each connection coupling a respective one of the plurality of shift registers to more than one of the plurality of storage locations, one or more of the plurality of storage locations being coupled to more than one of the plurality of connections; and a control circuit configured to load the plurality of shift registers with the plurality of image samples based on the plurality of connections and shift the plurality of shift registers to output the plurality of streams of image samples.
    Type: Application
    Filed: October 17, 2017
    Publication date: April 18, 2019
    Applicant: Xilinx, Inc.
    Inventors: Elliott Delaye, Ashish Sirasao, Aaron Ng, Yongjun Wu, Jindrich Zejda
  • Publication number: 20190114548
    Abstract: Embodiments herein describe techniques for static scheduling a neural network implemented in a massively parallel hardware system. The neural network may be scheduled using three different scheduling levels referred to herein as an upper level, an intermediate level, and a lower level. In one embodiment, the upper level includes a hardware or software model of the layers in the neural network that establishes a sequential order of functions that operate concurrently in the hardware system. In the intermediate level, identical processes in the functions defined in the upper level are connected to form a systolic array or mesh and balanced data flow channels are used to minimize latency. In the lower level, a compiler can assign the operations performed by the processing elements in the systolic array to different portions of the hardware system to provide a static schedule for the neural network.
    Type: Application
    Filed: October 17, 2017
    Publication date: April 18, 2019
    Applicant: Xilinx, Inc.
    Inventors: Yongjun Wu, Jindrich Zejda, Elliott Delaye, Ashish Sirasao
  • Publication number: 20190114529
    Abstract: In the disclosed methods and systems for processing in a neural network system, a host computer system writes a plurality of weight matrices associated with a plurality of layers of a neural network to a memory shared with a neural network accelerator. The host computer system further assembles a plurality of per-layer instructions into an instruction package. Each per-layer instruction specifies processing of a respective layer of the plurality of layers of the neural network, and respective offsets of weight matrices in a shared memory. The host computer system writes input data and the instruction package to the shared memory. The neural network accelerator reads the instruction package from the shared memory and processes the plurality of per-layer instructions of the instruction package.
    Type: Application
    Filed: October 17, 2017
    Publication date: April 18, 2019
    Applicant: Xilinx, Inc.
    Inventors: Aaron Ng, Elliott Delaye, Ehsan Ghasemi, Xiao Teng, Jindrich Zejda, Yongjun Wu, Sean Settle, Ashish Sirasao
  • Patent number: 10257421
    Abstract: Video image stabilization provides better performance on a generic platform for computing devices by evaluating available multimedia digital signal processing components, and selecting the available components to utilize according to a hierarchy structure for video stabilization performance for processing parts of the video stabilization. The video stabilization has improved motion vector estimation that employs refinement motion vector searching according to a pyramid block structure relationship starting from a downsampled resolution version of the video frames. The video stabilization also improves global motion transform estimation by performing a random sample consensus approach for processing the local motion vectors, and selection criteria for motion vector reliability. The video stabilization achieves the removal of hand shakiness smoothly by real-time one-pass or off-line two-pass temporal smoothing with error detection and correction.
    Type: Grant
    Filed: December 14, 2016
    Date of Patent: April 9, 2019
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Yongjun Wu, Nikola Borisov, Weidong Zhao, Shyam Sadhwani, Naveen Thumpudi
  • Patent number: 10244266
    Abstract: Techniques are described for encoding noisy media content. A residual coefficient matrix representing differences in image content between a portion of a target image frame and portions of one or more reference frames can include noise within a high frequency band. Some of the noise can be removed by removing isolated residual coefficients under some estimated threshold. Additionally, the remaining noise can be reduced by attenuating their values selectively.
    Type: Grant
    Filed: February 11, 2016
    Date of Patent: March 26, 2019
    Assignee: Amazon Technologies, Inc.
    Inventor: Yongjun Wu
  • Patent number: 10234123
    Abstract: An LED tube apparatus has a tube body with two opposite ends fixed to a first cap and a second cap. An LED module is placed in the tube body. The LED module has a driver circuit containing an electronic ballast that generates high frequency electric current. The first cap has two first metal pins to be inserted in a first socket end of a light tube bracket. The first metal pin clutches an end of a leading wire. The leading wire has a protective portion breaking off when the first metal pin is applied with a predetermined range of heat generated by the high frequency electric current when the LED tube apparatus is not operated properly.
    Type: Grant
    Filed: April 25, 2018
    Date of Patent: March 19, 2019
    Assignee: XIAMEN ECO LIGHTING CO. LTD.
    Inventors: Qiyuan Wang, Yongjun Bao, Wengui Wu, Qi Liu
  • Patent number: 10217200
    Abstract: In one embodiment, a video processing system 300 may filter a video data set to correct skew and wobble using a central processing unit 220 and a graphical processing unit 230. The video processing system 300 may apply a rolling shutter effect correction filter to an initial version of a video data set. The video processing system 300 may simultaneously apply a video stabilization filter to the initial version to produce a final version video data set.
    Type: Grant
    Filed: October 3, 2016
    Date of Patent: February 26, 2019
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Yongjun Wu, Matthew Wozniak, Simon Baker, Catalin Alexandru Negrila, Venkata S. K. Kamal Lanka, Kevin Chin, Brian Kohlwey
  • Patent number: 10205966
    Abstract: Syntax structures that indicate the completion of coded regions of pictures are described. For example, a syntax structure in an elementary bitstream indicates the completion of a coded region of a picture. The syntax structure can be a type of network abstraction layer unit, a type of supplemental enhancement information message or another syntax structure. For example, a media processing tool such as an encoder can detect completion of a coded region of a picture, then output, in a predefined order in an elementary bitstream, syntax structure(s) that contain the coded region as well as a different syntax structure that indicates the completion of the coded region. Another media processing tool such as a decoder can receive, in a predefined order in an elementary bitstream, syntax structure(s) that contain a coded region of a picture as well as a different syntax structure that indicates the completion of the coded region.
    Type: Grant
    Filed: September 22, 2017
    Date of Patent: February 12, 2019
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Yongjun Wu, Lihua Zhu, Shyam Sadhwani, Gary J. Sullivan
  • Publication number: 20190045237
    Abstract: A media processing tool adds custom data to an elementary media bitstream or media container. The custom data indicates nominal range of samples of media content, but the meaning of the custom data is not defined in the codec format or media container format. For example, the custom data indicates the nominal range is full range or limited range. For playback, a media processing tool parses the custom data and determines an indication of media content type. A rendering engine performs color conversion operations whose logic changes based at least in part on the media content type. In this way, a codec format or media container format can in effect be extended to support full nominal range media content as well as limited nominal range media content, and hence preserve full or correct color fidelity, while maintaining backward compatibility and conformance with the codec format or media container format.
    Type: Application
    Filed: August 10, 2018
    Publication date: February 7, 2019
    Applicant: Microsoft Technology Licensing, LLC
    Inventors: Yongjun Wu, Naveen Thumpudi, Shyam Sadhwani
  • Patent number: 10200707
    Abstract: Aspects extend to methods, systems, and computer program products for video bit stream decoding. Aspects include flexible definition and detection of surface alignment requirements for decoding hardware. Surface alignment requirements can be handled by render cropping (e.g., cropping at a video output device), through adjustment and modification of original syntax values in a video bit stream and relaxed media type negotiation in a software (host) decoder. Resolution changes can be hidden with the aligned surface allocation when applicable. Performance can be improved and power consumption reduced by using hidden resolution changes.
    Type: Grant
    Filed: October 29, 2015
    Date of Patent: February 5, 2019
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Yongjun Wu, Shyam Sadhwani, Bakkama Srinath Reddy
  • Patent number: 10176622
    Abstract: Techniques are described for low-pass filtering image data of virtual reality content before compression based on an understanding of the relationship of the image data to a cylindrical or polygonal projection space and the resulting compression of that image data when mapped to a playback projection space.
    Type: Grant
    Filed: January 24, 2017
    Date of Patent: January 8, 2019
    Assignee: Amazon Technologies, Inc.
    Inventors: Charles Benjamin Franklin Waggoner, Yongjun Wu
  • Publication number: 20180373563
    Abstract: There is provided a method and a system for processing a communication channel. including a heartbeat channel and a data channel between a master process and a worker process. The method includes determining at least one data channel associated with a heartbeat channel, detecting the determined at least one data channel, disconnecting the heartbeat channel when it is detected that any data channel is in a disconnected state to cause a heartbeat to time out, and ending a current task after it is determined that the heartbeat times out.
    Type: Application
    Filed: September 10, 2018
    Publication date: December 27, 2018
    Inventors: Yongjun WU, Zhipeng TANG, Yangyu TAO, Chao LI, Yihui FENG
  • Publication number: 20180373760
    Abstract: Embodiments herein describe techniques for preparing and executing tasks related to a database query in a database accelerator. In one embodiment, the database accelerator is separate from a host CPU. A database management system (DBMS) can offload tasks corresponding to a database query to the database accelerator. The DBMS can request data from the database relevant to the query and then convert that data into one or more data blocks that are suitable for processing by the database accelerator. In one embodiment, the database accelerator contains individual hardware processing units (PUs) that can process data in parallel or concurrently. In order to process the data concurrently, the data block includes individual PU data blocks that are each intended for a respective PU in the database accelerator.
    Type: Application
    Filed: June 23, 2017
    Publication date: December 27, 2018
    Applicant: Xilinx, Inc.
    Inventors: Hare K. Verma, Sonal Santan, Yongjun Wu
  • Publication number: 20180341777
    Abstract: Techniques are described for communicating encoded data using start code emulation prevention. The described techniques include obtaining at least one partially encrypted packet, identifying at least one portion of the packet that is unencrypted, and determining that the identified unencrypted portion(s) emulates a start code. Start code emulation prevention data or emulation prevention bytes (EPBs) may be inserted into only the encrypted portion of the packet. The modified packet may be communicated to another device/storage, along with an indication of which portion(s) of the packet are unencrypted. Upon receiving the packet and indication, the receiving device may identify and remove the EPBs in the identified unencrypted portion(s) of the packet, and decrypt the packet to recover the data. In some aspects, upon identifying the indication, the receiving device may only search for EPBs in the unencrypted portion(s) of the packet, thus yielding a more efficient start code emulation prevention process.
    Type: Application
    Filed: July 18, 2018
    Publication date: November 29, 2018
    Inventors: Yongjun WU, Shyam SADHWANI, Robert K. HUGHES
  • Patent number: 10136146
    Abstract: Techniques for encoding media content are described that reduce the overhead associated with metadata when the encoded content is streamed over a network. Some of these techniques involve the selection of parameters or consolidation of information to ensure consistency or uniformity of metadata values. Others relate to the recognition and removal of redundancies or optional information. Still others take advantage of characteristics of specific bit rate scenarios to more efficiently represent information.
    Type: Grant
    Filed: March 23, 2016
    Date of Patent: November 20, 2018
    Assignee: Amazon Technologies, Inc.
    Inventors: Yongjun Wu, Lei Li, Amarsingh Buckthasingh Winston
  • Publication number: 20180329978
    Abstract: Innovations for category-prefixed data batching (“CPDB”) of entropy-coded data or other payload data for coded media data, as well as innovations for corresponding recovery of the entropy-coded data (or other payload data) formatted with CPDB. The CPDB can be used in conjunction with coding/decoding for video content, image content, audio content or another type of content. For example, after receiving coded media data in multiple categories from encoding units, a formatting tool formats payload data with CPDB, generating a batch prefix for a batch of the CPDB-formatted payload data. The batch prefix includes a category identifier and a data quantity indicator. The formatting tool outputs the CPDB-formatted payload data to a bitstream. At the decoder side, a formatting tool receives the CPDB-formatted payload data in a bitstream, recovers the payload data from the CPDB-formatted payload data, and outputs the payload data (e.g., to decoding units).
    Type: Application
    Filed: January 5, 2018
    Publication date: November 15, 2018
    Applicant: Microsoft Technology Licensing, LLC
    Inventors: Gary J. Sullivan, Leon Bottou, Sandeep Kanumuri, Yongjun Wu
  • Patent number: 10129566
    Abstract: Disclosed herein are innovations in decoding compressed video media data. The disclosed innovations facilitate decoding operations with improved computational efficiency, faster speeds, reduced power, reduced memory usage, and/or reduced latency. In one embodiment, for example, an encoded bitstream of video media data is input from an external video content provider, the encoded bitstream being encoded according to a video codec standard. A decoder is then configured to decode the encoded bitstream based at least in part on supplemental information that identifies a property of the encoded bitstream but that is supplemental to the encoded bitstream (e.g., supplemental information that is not part of the encoded bitstream or its associated media container and that is specific (or related) to the application for which the bitstream is used and/or the standard by which the bitstream is encoded and/or encrypted).
    Type: Grant
    Filed: May 22, 2015
    Date of Patent: November 13, 2018
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Shyam Sadhwani, Yongjun Wu, Wenbo Zhang, Sudhakar V. Prabhu
  • Patent number: 10075748
    Abstract: A media processing tool adds custom data to an elementary media bitstream or media container. The custom data indicates nominal range of samples of media content, but the meaning of the custom data is not defined in the codec format or media container format. For example, the custom data indicates the nominal range is full range or limited range. For playback, a media processing tool parses the custom data and determines an indication of media content type. A rendering engine performs color conversion operations whose logic changes based at least in part on the media content type. In this way, a codec format or media container format can in effect be extended to support full nominal range media content as well as limited nominal range media content, and hence preserve full or correct color fidelity, while maintaining backward compatibility and conformance with the codec format or media container format.
    Type: Grant
    Filed: September 22, 2016
    Date of Patent: September 11, 2018
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Yongjun Wu, Naveen Thumpudi, Shyam Sadhwani
  • Publication number: 20180234691
    Abstract: Techniques are described for optimizing video decoder operations.
    Type: Application
    Filed: April 16, 2018
    Publication date: August 16, 2018
    Inventors: Yongjun Wu, Charles Benjamin Franklin Waggoner, Amarsingh Buckthasingh Winston
  • Publication number: 20180234686
    Abstract: Video frames of a higher-resolution chroma sampling format such as YUV 4:4:4 are packed into video frames of a lower-resolution chroma sampling format such as YUV 4:2:0 for purposes of video encoding. For example, sample values for a frame in YUV 4:4:4 format are packed into two frames in YUV 4:2:0 format. After decoding, the video frames of the lower-resolution chroma sampling format can be unpacked to reconstruct the video frames of the higher-resolution chroma sampling format. In this way, available encoders and decoders operating at the lower-resolution chroma sampling format can be used, while still retaining higher resolution chroma information. In example implementations, frames in YUV 4:4:4 format are packed into frames in YUV 4:2:0 format such that geometric correspondence is maintained between Y, U and V components for the frames in YUV 4:2:0 format.
    Type: Application
    Filed: April 17, 2018
    Publication date: August 16, 2018
    Applicant: Microsoft Technology Licensing, LLC
    Inventors: Lihua Zhu, Sridhar Sankuratri, B. Anil Kumar, Yongjun Wu, Sandeep Kanumuri, Shyam Sadhwani, Gary J. Sullivan