Broadcom Corporation

Avago Technologies International Sales Pte. Limited

Avago Technologies General IP (singapore) Pte. Ltd.

Zhijie Yang

Xuemin Chen

Wade Keith Wan

Brian Allan Heng

Minhua Zhou

Peisong Chen

Timothy Moore Hellman

Ba-Zhong Shen

Daniel William English

Jiang Fu

Bhaskar Sherigar Mala Sherigar

A method includes accessing a video comprising a set of frames; receiving a command to identify a target displayed in a first frame; generating a first target data based on the target; generating a first confidence level between the first target data and a second target data stored in a remote database, wherein the second target data comprises identity data; in response to the first confidence level being at or above a confidence level threshold, outputting the identity data of the second target data; otherwise, generating a third target data based on the target displayed in a second frame of the set of frames; generating a second confidence level of similarity between the third target data and the second target data stored in the remote database; in response to the second confidence level being at or above the confidence level threshold, outputting the identity data of the second target data.

Face recognition systems and methods for media playback devices

Systems, methods and apparatus for processing video can include a processor. The processor can be configured to perform object detection to detect visual indications of potential objects of interest in a video scene, to receive a selection of an object of interest from the potential objects of interest, and to provide enhanced video content within the video scene for the object of interest indicated by the selection.

Object or region of interest video processing system and method

A device implementing the subject video coding system may include at least one processor to determine an x-tap filter for horizontal interpolation of a N&#xd7;M block. The processor further determines a y-tap filter for vertical interpolation of the N&#xd7;M block, and encodes the N&#xd7;M block using the x-tap filter and the y-tap filter. The value of x is proportional to N and the value of y is proportional to M.

Block size dependent interpolation filter selection and mapping

The present disclosure describes a video communication environment for encoding and/or decoding video frames in accordance with various video coding formats utilizing various coding parameters. The video communication environment can include one or more encoding verification circuit and/or decoding verification circuit throughout which utilizes the various coding parameters to model dynamics of decoding various encoded video frames and/or display timing for displaying various decoded video frames. This modeling of the dynamics of decoding and/or display timing can be used to verify whether these various encoded video frames, once decoded, can be displayed smoothly, for example, without jitter. In some situations, the modeling of the dynamics of decoding and/or display timing can be used to guide decoding and/or display process to display the various decoded video frames smoothly.

Video decoder rate model and verification circuit

A device implementing the subject video coding system may include a processor that encodes an N&#xd7;M block using an x-tap filter for horizontal interpolation and a y-tap filter for vertical interpolation, where x is proportional to N and y is proportional to M. The processor may use a current block size to select an interpolation filter with a first length or a second length for a current block, use an overlapped block size to select an interpolation filter with a first length or a second length for overlapped areas, and, when a neighboring block uses a long interpolation filter and a short interpolation filter is selected for the overlapped area, maps the long interpolation filter to a short interpolation filter of a selected type. The processor may calculate a reference block size based on a scaling factor and use the reference block size to select a filter length.

A method, system, and computer program product for adaptive decoding is provided herein. The method includes the steps of receiving a video bitstream, selecting an initial extraction level, and switching to a lower quality extraction level if a decoding rate is less than a rate at which data extracted from the video bitstream is sent to the decoder. The method further includes the step of switching to a higher quality extraction level if the decoding rate is greater than a rate at which data extracted from the video bitstream is to the decoder.

Adaptive decoding system

Video coding tree sub-block splitting. A parser and treeblock splitter is implemented for adaptive partitioning of treeblocks (TBs) into various respective sub-treeblocks (STBs). Such adaptation may be tailored for effectuating parallel processing in accordance with video decoding. Different respective decoding engines may each individually and respectively also perform further partitioning of the STBs into sub-STBs as well. Such adaptation of respective STB size and/or sub-STB size may be made based on local and/or remote consideration(s). For example, adaptation may be made based upon communication link and/or channel conditions, a remote characteristic (e.g., associated with a source device and/or destination device), a local characteristic (e.g., associated with operations and/or processing performed locally within a given device), and/or any other type of consideration. Different respective portions of a video signal may be processed using different respective sized STBs/sub-STBs (and different respective engines may also employ different respective sized STBs/sub-STBs).

Video coding tree sub-block splitting

Multi-mode error concealment, recovery and resilience coding. Adaptation of a number of coding units (CUs) employed in accordance with video coding may be made as a function of error. As a number of errors increases, the respective number of CUs may correspondingly increase (e.g., which may be made in accompaniment with a reduction of CU size). As a number of errors decreases, the respective number of CUs may correspondingly decrease (e.g., which may be made in accompaniment with an increase of CU size). Such errors may be associated with a type of source providing a video signal, a type of error resilience coding employed, communication link and/or channel conditions, a remote error characteristic (e.g., such as associated with a source device and/or destination device), a local error characteristic (e.g., such as associated with operations and/or processing within a given device), and/or any other type of consideration.

Multi-mode error concealment, recovery and resilience coding

A system may receive an input stream for a coding operation. The system may determine available coding modes for the coding operation. The system may include coding selection logic that may determine a coding mode in response to the based on the available selection of coding modes. The coding selection logic may use the selected coding mode to determine a coding strategy. The selection logic may send an indication of the selected coding mode and coding strategy to coding logic to support execution of the coding operation, which may use the selected coding mode and coding strategy.

Mode complexity based coding strategy selection

Within a device, one or more subsets associated with one or more frames or pictures of the video signal may be adaptively selected and used for motion vector calculation (e.g., such as in accordance with inter-prediction). For example, a picture or frame of the video signal may be partitioned into a number of respective regions. Any one or more, but typically fewer than all, of the respective regions of that picture or frame may be appropriately selected, and stored, based on any one or more considerations for use in motion vector calculation (e.g., inter-prediction). A sub-sampled or down-sampled picture or frame [or alternatively, a sub-sampled or down-sampled version of one or more respective regions of a picture or frame] (e.g., the sub-sampling or down-sampling ratio which may be adaptively determined based on any one or more considerations) may be stored for use in motion vector calculation (e.g., inter-prediction).

Video coding infrastructure using adaptive prediction complexity reduction

In various embodiments, video streams are decoded using decoders that support a different decoding profile. First processing circuitry is configured to receive a video stream encoded using a first encoding profile, transcode the video stream from the first encoding profile to a second encoding profile, and store the transcoded video stream in an output buffer. Second processing circuitry is configured to receive the transcoded video stream from the output buffer and decode the transcoded video stream according to the second encoding profile. The second processing circuitry may be unable to decode the video stream encoded using the first encoding profile.

Decoding video streams using decoders supporting a different encoding profile

In conventional packet communications systems, such as MPEG-2, the data stream includes a program clock reference (PCR) so that the receiver decoder can lock on to the data stream. The invention eliminates the need to send the PCR by transferring a data transport rate explicitly in the header of the data packets so that the decoder can use the transport rate as a locking reference and adjust its phase lock loop. The transport rate is carried in the adaptation field as user private data.

Method for reconstructing system time clock (STC) without carrying PCR

Aspects of virtual field buffer based decoding are described. In one embodiment, a current picture field is read from a coded picture buffer comprising coded pictures of video, for example. The current picture may be associated with a top or bottom field polarity. According to decoding and picture output orders, the current picture field is assigned to an available field entry of a virtual field buffer, and an available frame index of a virtual frame map is assigned to the current picture field. The assignment of the available frame index to the current picture field is indicated to a decoder that decodes the current picture field with reference to the assigned frame index. According to aspects of the embodiments described herein, rather than determining complimentary picture fields after decoding, the assignment of complimentary picture fields to virtual frame indexes before decoding provides certain efficiencies.

Virtual field buffer based decoding

Disclosed are various embodiments for determining a filter length according to a width and height of the reference block and selecting a filter based on the block size. Corresponding pixels from memory may be fetched based on the filter length and the block size. Reference pixels may be interpolated based on the selected filter to generate a prediction.

Block size dependent filter selection for motion compensation

Video coding sub-block sizing based on infrastructure capabilities and current conditions. Sub-block size, such as employed in accordance with the video processing, maybe adaptively modified based on any of a number of considerations. For example, such adaptation of sub-block size may be made with respect to one or more characteristics associated with streaming media source flow(s) and/or streaming media delivery flow(s) being received by and/or output from a given device including a video processor. For example, such a video processor may be a video decoder implemented within a middling or destination device. Such a video processor may be a video encoder implemented within the middling or source device. Adaptation of sub-block size employed in accordance with video coding may also be effectuated in accordance with feedback or control signaling provided between respective devices. (e.g., from destination or source device to middling device, or from destination device to source device, etc.).

Growing community of inventors

Irvine, CA, United States of America

Zhijie Yang