International Business Machines Corporation

Charles E Boice

Agnes Yee Ngai

John Mark Kaczmarczyk

Krishna Chaitanya Ratakonda

Edward Francis Westermann

Charles John Stein

Robert L Woodard

Rajaram B Krishnamurthy

Carl Joseph Parris

Barbara A Hall

Michael Patrick Vachon

Lurng-Kuo Liu

Joseph G Schaefer

John A Murdock

Joseph H Underwood

Everett G Vail, Iii

Stephen Philip Pokrinchak

Nader Mohsenian

Brian J Cascarino

Adrian Stephen Butter

Lawrence D Curley

James David Greenfield

Charles C Stein

Stanley J Bogumil

Frederic G Webster

Stream processing is facilitated by distributing responsibility for processing the stream to multiple components of a computing environment. A programmable unit receives one or more streams and determines the operations to be performed for the one or more streams and which components of the computing environment are to perform those operations. It forwards data relating to the one or more streams to one or more components of the computing environment for processing and/or information purposes.

Multi-granular stream processing

An end-to-end record, request, response token-based protocol is used to facilitate processing of client jobs. This allows the client to forward analytical tasks of a job directly to an analytics cluster and to record an indication of such at a server. The accelerators of the cluster to perform the tasks are specified in a token provided by the server to the client.

Interactive analytics processing

Request processing within a computing environment is facilitated. Request processing and analytics processing for the request are performed substantially concurrently in order to improve efficiency of request execution. The analytics processing is at least commenced, and may complete, prior to receiving an indication of success or failure of the request processing. If request processing fails, analytics processing ceases, if not already complete, and results of the analytic processing are not used.

Concurrent execution of request processing and analytics of requests

A method and apparatus are provided for implementing B-picture scene changes. A prediction stage predicts a B-picture scene change based upon a sequence of statistical information in an encoder order and a reaction stage is responsive to the prediction stage for modifying a quantization scale of a rate control algorithm.

Implementing B-picture scene changes

An encode control strategy is provided for variable bit rate encoding of a sequence of video frames in a single pass. The control strategy includes determining whether a video frame has a complexity level statistically outside a defined range from a complexity level of at least one preceding frame of the sequence of video frames, and if so, determining a new average bit rate target for the video frame. The new average bit rate for the video frame is determined employing at least one of spatial complexity and temporal complexity of the video frame. The new average bit rate target for the video frame is used to set frame level bit rate control parameter(s), and the video frame is encoded using the set frame level bit rate control parameter(s).

Single pass variable bit rate control strategy and encoder for processing a video frame of a sequence of video frames

Method and apparatus for implementing B-picture scene changes

System and method are provided for optimally encoding a sequence of video frames using image statistics collected from multiple encoders connected in parallel, each encoder employing a different set of encode parameters. The image statistics are used to select an optimum set of encode parameters for use in encoding the sequence of video frames in a subsequent encode subsystem stage. As an alternative, multiple buffers are connected to the outputs of the multiple, parallel connected encoders, with the encoded stream from the encoder employing the optimum set of encode parameters selected for output as the bitstream of encoded video data.

Multiple parallel encoders and statistical analysis thereof for encoding a video sequence

A digital video encoder is presented adapted for dynamically switching between sets of quantizer matrix tables without pausing encoding of a stream of video data. Two or more sets of quantizer matrix tables are held at the encoder's quantization unit and compressed store interface for dynamically switching between sets of quant matrix tables at a picture boundary of the sequence of video data, i.e., without stopping encoding of the sequence of video data. Further, while one set of matrix tables is being employed to quantize the stream of video data, the encoder can be updating or modifying another set of quantization matrix tables, again without stopping encoding of the sequence of video data.

Dynamically switching quant matrix tables within an MPEG-2 encoder

A method and structure for performing a sequence of integer divides without propagation of truncation error. During encoding and decoding of video signals, a buffer is dynamically filled with binary bits of encoded video data at a variable rate, and the data is subsequently removed from the buffer at a constant rate. Calculating the number of bits removed from the buffer as each video frame is processed requires integer divides with consequent truncation of the quotient. An accumulator is utilized for each integer divide to cumulatively store remainders generated by successive integer divides. If the accumulator accumulates to a value (A) that is no less than the divisor (D) of the associated integer divide, then the quotient is effectively increased by 1, and A is decremented by D, which compensates for the prior truncations and avoids a buffer overflow violation that may otherwise occur.

Method for performing integer divides without propagation of truncation error

A frequency domain data management technique for producing pseudo-constant bits per picture compressed video bit-streams in a low delay digital encoding environment is presented. This technique forms a hierarchy among the localized samples of the picture in terms of frequency importance and the picture difficulty after a shot-change is detected. After a shot change, the data management technique implements a series of tasks composed of picture difficulty evaluation, frequency classification, frequency constraining, and zero bytes generation to achieve a pre-determined average picture bits. Further, the low delay encoder uses a unique updating mechanism to encode certain regions of the pictures in intra mode and ensures that the whole picture is updated after a pre-selected number of pictures. The updating method disseminates compression artifacts throughout the video stream by changing the orientation of the intra-coded regions for every picture and scatters intra-picture compression artifacts by spatially decimating the aforementioned regions at different rates.

Method and apparatus for producing pseudo-constant bits per picture video bit-streams for low-delay compression system

Method, system and computer program product are provided for adaptively encoding in hardware, software or a combination thereof a series of still or partially still pictures using motion video encoding. A pre-encode statistics measurement unit is employed to derive statistics on each frame of the sequence of video frames to be encoded. The statistics are determinative of whether the frame comprises a still frame. If so, at least one controllable parameter to be used to encode the still frame is modified, and an encoding engine employs the at least one controllable parameter to encode the still frame so that pulsation artifacts are prevented between still frames of the series of still frames. Partial still picture encoding to prevent pulsation artifacts on a macroblock level is also addressed.

Adaptive encoding of a sequence of still frames or partially still frames within motion video

An apparatus used for video encoding MPEG compliant digital visual images, having multiple MPEG encoders used in the motion estimation function. The search capabilities used in the motion estimation function of a single MPEG encoder are extended beyond its design limitations as a result of utilizing more than one MPEG encoder. The utilization of multiple encoders effectively creates the capability for a user to specify a wider search window than what is available in a single encoder configuration. The computational search efficency associated with searching the wider window is not adversely affected as a consequence of the multiple processors subdividing the extended window and analyzing each subdivision in parallel.

Multiple encoder architecture for extended search

System for reducing power consumption in MPEG-2 compliant video encoder circuitry employs logic for controlling first clock signals input to functional I, HSU and RSU blocks and functional sub-units performing specific tasks therein. Second clock signals are continuously input to a processing detection circuits requiring continuous clock inputs throughout video encode operations for a functional sub-unit. A trigger signal is asserted by the sub-unit itself or, an external processor, to indicate idle or active processing for that particular sub-unit. The combination of the second clock signals and receipt of the trigger signal enable the sub-unit to generate a sleep signal for that sub-unit which is input to a clock control circuit to either enable input of first clock signals to the functional sub-unit during active processing or, disable input of the first clock signal during idle, in-active processing periods, for as long as the trigger signal is asserted. There are a variety of video input conditions that may be detected which will enable generation of a trigger signal indicating idle processing for one or more functional sub-units, including, for example, detection of still input pictures, fade sequences and specification of high bitstream output rates.

Apparatus and method for power reduction control in a video encoder device

A method to insert or splice new pictures into an existing video stream is provided where the video stream is compressed according to the MPEG-2 video compression standard. The method assures that the new pictures will fit into the encoded stream in the space allotted without running over or under their given bit allocation. The method comprises of steps by which a number of new pictures may be encoded to a precise bit target given the number of free bits in the buffer at the start and end of the splicing, while preventing buffer overruns and under runs.

Growing community of inventors

Endicott, NY, United States of America

Charles E Boice