公开(公告)号：US20180139463A1

公开(公告)日：2018-05-17

申请号：US15853191

申请日：2017-12-22

Applicant: Microsoft Technology Licensing, LLC

Inventor： Yongjun Wu ,  Chih-Lung Lin

IPC: H04N19/436 ,  H04N19/44

CPC classification number: H04N19/436 ,  H04N19/44

Abstract: A video decoding method is implemented by a computer having multiple parallel processing units. A stream of data elements is received, some of which encode video content. The stream comprises marker sequences, each marker sequence comprising a marker which does not encode video content. A known pattern of data elements occurs in each marker sequence. A respective part of the stream is supplied to each parallel processing unit. Each parallel processing unit processes the respective part of the stream, whereby multiple parts of the stream are processed in parallel, to detect whether any of the multiple parts matches the known pattern of data elements, thereby identifying the markers. The encoded video content is separated from the identified markers. The separated video content is decoded, and the decoded video content outputted on a display.

公开(公告)号：US09973562B2

公开(公告)日：2018-05-15

申请号：US14690058

申请日：2015-04-17

Applicant: Microsoft Technology Licensing, LLC

Inventor： Yongjun Wu ,  Shyam Sadhwani ,  Wenbo Zhang ,  Sudhakar V. Prabhu

IPC: H04N7/12 ,  H04N11/02 ,  H04N11/04 ,  H04L29/06 ,  H04L29/08 ,  H04N21/44 ,  H04N21/845 ,  H04N21/434

CPC classification number: H04L65/608 ,  H04L65/607 ,  H04L67/02 ,  H04N21/4341 ,  H04N21/44016 ,  H04N21/8456

Abstract: Techniques are described for split processing of streaming segments in which processing operations are split between a source component and a decoder component. For example, the source component can perform operations for receiving a streaming segment, demultiplexing the streaming segment to separate a video content bit stream, scanning the video content bit stream to find a location at which decoding can begin (e.g., scanning up to a first decodable I-picture, for which header parameter sets are available for decoding), and send the video content bit stream to the decoder component beginning at the location (e.g., the first decodable I-picture). The decoder component can begin decoding at the identified location (e.g., the first decodable I-picture). The decoder component can also discard subsequent pictures that reference a reference picture not present in the video content bit stream (e.g., when decoding starts with a new streaming segment).

公开(公告)号：US09883194B2

公开(公告)日：2018-01-30

申请号：US14739442

申请日：2015-06-15

Applicant: Microsoft Technology Licensing, LLC

Inventor： Yongjun Wu ,  Haoyun Wu ,  Shyam Sadhwani ,  Sudhakar Prabhu ,  Glenn Evans

IPC: H04N19/44 ,  H04N19/463 ,  H04N21/2343 ,  H04N21/2662 ,  H04N19/423 ,  H04N19/433 ,  H04N19/46

CPC classification number: H04N19/44 ,  H04N19/423 ,  H04N19/433 ,  H04N19/46 ,  H04N21/23439 ,  H04N21/2662

Abstract: In a video processing system including a video decoder, to handle frequent changes in the bit rate of an encoded bitstream, a video decoder can be configured to process a change in bit rates without reinitializing. The video decoder can be configured to reduce memory utilization. The video decoder can be configured both to process a change in bit rate without reinitializing while reducing memory utilization. In one implementation, the video processing system can include an interface between an application running on a host processor and the video decoder which allows the video decoder to communicate with the host application about the configuration of the video decoder.

公开(公告)号：US20180014033A1

公开(公告)日：2018-01-11

申请号：US15713414

申请日：2017-09-22

Applicant: Microsoft Technology Licensing, LLC

Inventor： Yongjun Wu ,  Lihua Zhu ,  Shyam Sadhwani ,  Gary J. Sullivan

IPC: H04N19/70 ,  H04N19/167 ,  H04N19/172 ,  H04N19/169 ,  H04N19/119 ,  H04N19/89 ,  H04N19/44

CPC classification number: H04N19/70 ,  H04N19/119 ,  H04N19/167 ,  H04N19/172 ,  H04N19/188 ,  H04N19/44 ,  H04N19/89

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.

公开(公告)号：US09854261B2

公开(公告)日：2017-12-26

申请号：US14590605

申请日：2015-01-06

Applicant: Microsoft Technology Licensing, LLC

Inventor： Yongjun Wu ,  Chih-Lung Lin

IPC: H04N19/436 ,  H04N19/513 ,  H04N19/43 ,  H04N19/44

CPC classification number: H04N19/436 ,  H04N19/44

Abstract: A video decoding method is implemented by a computer having multiple parallel processing units. A stream of data elements is received, some of which encode video content. The stream comprises marker sequences, each marker sequence comprising a marker which does not encode video content. A known pattern of data elements occurs in each marker sequence. A respective part of the stream is supplied to each parallel processing unit. Each parallel processing unit processes the respective part of the stream, whereby multiple parts of the stream are processed in parallel, to detect whether any of the multiple parts matches the known pattern of data elements, thereby identifying the markers. The encoded video content is separated from the identified markers. The separated video content is decoded, and the decoded video content outputted on a display.

公开(公告)号：US20170098088A1

公开(公告)日：2017-04-06

申请号：US15048181

申请日：2016-02-19

Applicant: Microsoft Technology Licensing, LLC

Inventor： Yongjun Wu ,  Shyam Sadhwani ,  Robert K. Hughes

IPC: G06F21/60 ,  H04N21/434 ,  H04N21/4405 ,  H04N21/2347 ,  H04N21/236

CPC classification number: G06F21/602 ,  H04N19/188 ,  H04N19/70 ,  H04N21/23476 ,  H04N21/235 ,  H04N21/23605 ,  H04N21/4343 ,  H04N21/435 ,  H04N21/44055

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.

公开(公告)号：US20170094172A1

公开(公告)日：2017-03-30

申请号：US15378942

申请日：2016-12-14

Applicant: Microsoft Technology Licensing, LLC

Inventor： Yongjun Wu ,  Nikola Borisov ,  Weidong Zhao ,  Shyam Sadhwani ,  Naveen Thumpudi

IPC: H04N5/232 ,  H04N21/44 ,  H04N21/4223 ,  G06T3/00

CPC classification number: H04N5/23267 ,  G06T3/0093 ,  G06T7/207 ,  H04L67/10 ,  H04N5/145 ,  H04N5/23248 ,  H04N5/23254 ,  H04N21/4223 ,  H04N21/44

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.

公开(公告)号：US20170064320A1

公开(公告)日：2017-03-02

申请号：US14842823

申请日：2015-09-01

Applicant: Microsoft Technology Licensing, LLC

Inventor： Shyam Sadhwani ,  Sudhakar Prabhu ,  Carol Greenbaum ,  Saswata Mandal ,  Yongjun Wu

IPC: H04N19/436 ,  G06T1/20

CPC classification number: H04N19/436 ,  G06T1/20 ,  G06T2200/28 ,  H04N19/423

Abstract: A graphics pipeline with components that process frames by portions (e.g., pixels or rows) or slices to reduce end-to-end latency. Components of a pipeline process portions of a same frame at the same time. For example, as graphics data for a frame is being generated and fills a framebuffer, once a certain portion of video data less than the whole frame (slice or sub-frame) becomes available, before the corresponding frame is finished filling the framebuffer, the next pipeline component after the framebuffer, for instance a video processor for color conversion or an encoder, begins to process the portion of the frame. While one portion of a frame is accumulating in the frame buffer, another portion of the same frame is being encoded by an encoder, and another portion of the frame might be being packaged by a multiplexer, and a network socket might start streaming the multiplexed portion.

Abstract translation: 一个图形流水线，其中具有按部分（例如，像素或行）或切片进行处理的组件，以减少端到端的延迟。 管道的组件同时处理同一帧的部分。 例如，当正在生成帧的图形数据并且填充帧缓冲器时，一旦小于整个帧（片或子帧）的视频数据的某一部分变得可用，则在对应的帧完成填充帧缓冲器之前， 帧缓冲器之后的下一个流水线部件，例如用于颜色转换的视频处理器或编码器，开始处理该帧的部分。 虽然帧的一部分正在帧缓冲器中累积，但是同一帧的另一部分正由编码器编码，并且帧的另一部分可能被多路复用器打包，并且网络套接字可能开始流传输多路复用部分 。

公开(公告)号：US09549196B2

公开(公告)日：2017-01-17

申请号：US14172595

申请日：2014-02-04

Applicant: Microsoft Technology Licensing, LLC

Inventor： Yongjun Wu ,  Sudhakar Visweswara Prabhu

IPC: H04N19/46

CPC classification number: H04N19/46

Abstract: Data unit identification for compressed video streams is described. In one or more implementations, a compressed video stream is received at a computing device and a determination is made as to whether prior knowledge is available that relates to the compressed video stream. Responsive to the determination that prior knowledge is available that relates to the compressed video stream, the prior knowledge is employed by the computing device to perform data unit identification for the compressed video stream. In one or more implementations, SIMD instructions are utilized to perform pattern (0x00 00) search in a batch mode. Then a byte-by-byte search is performed to confirm whether the pattern, 0x00 00, found is part of a start code, 0x00 00 01, or not.

Abstract translation: 描述压缩视频流的数据单元识别。 在一个或多个实现中，在计算设备处接收压缩视频流，并且确定与压缩视频流相关的先验知识是否可用。 响应于与压缩视频流相关的先验知识可用的确定，计算设备采用先验知识来对压缩视频流执行数据单元识别。 在一个或多个实现中，使用SIMD指令以批处理模式执行模式（0x00 00）搜索。 然后执行逐字节搜索以确认发现的模式0x00 00是否是起始码0x00 00 01的一部分。

公开(公告)号：US20170013286A1

公开(公告)日：2017-01-12

申请号：US15272661

申请日：2016-09-22

Applicant: Microsoft Technology Licensing, LLC

Inventor： Yongjun Wu ,  Naveen Thumpudi ,  Shyam Sadhwani

IPC: H04N21/2383 ,  H04N21/438 ,  H04N21/2343

CPC classification number: H04N21/2383 ,  H04N21/234309 ,  H04N21/2351 ,  H04N21/23614 ,  H04N21/4382 ,  H04N21/440218 ,  H04N21/84

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.

Abstract translation: 媒体处理工具将自定义数据添加到基本媒体比特流或媒体容器。 自定义数据表示媒体内容的样本的标称范围，但自定义数据的含义未以编解码器格式或媒体容器格式定义。 例如，自定义数据表示标称范围是全范围或有限范围。 对于播放，媒体处理工具解析定制数据并确定媒体内容类型的指示。 渲染引擎执行颜色转换操作，其逻辑至少部分地基于媒体内容类型而改变。 以这种方式，编解码器格式或媒体容器格式实际上可以被扩展以支持完整的标称范围的媒体内容以及有限的标称范围的媒体内容，并因此保持完全或正确的色彩保真度，同时保持向后的兼容性和与编解码器的一致性 格式或媒体容器格式。