Abstract: An entropy coding module is provided for use in a video encoder that encodes a video input signal based on a plurality of macroblocks derived from the video input signal. The entropy coding module includes an entropy coder that generates entropy encoded data from discrete transformed coefficients for the plurality of macroblocks. A neighbor management module stores neighbor data for at least one macroblock of the plurality of macroblocks for retrieval by the entropy encoder, when operating on at least one neighboring macroblock of the plurality of macroblocks.

Abstract: A partition subset selection module selects a subset of available partitions for a macroblock pair of the plurality of macroblock pairs, based on motion search motion vectors generated by a motion search section, and further based on a macroblock adaptive frame and field indicator. A motion refinement module generates refined motion vectors for the macroblock pair, based on the subset of available partitions for a macroblock pair.

Abstract: A partition subset selection module selects a subset of available partitions for a macroblock pair of the plurality of macroblock pairs, based on motion search motion vectors generated by a motion search section, and further based on a macroblock adaptive frame and field indicator. A motion refinement module generates refined motion vectors for the macroblock pair, based on the subset of available partitions for a macroblock pair.

Abstract: A system for processing a video signal into a processed video signal includes a pattern recognition module for detecting a region of text in the image sequence based on coding feedback data and generating pattern recognition data in response thereto. A video codec generates the processed video signal and generates the coding feedback data in conjunction with the processing of the image sequence.

Abstract: A system for searching at least one video signal based on an input text string includes a video processing system that processes the at least one video signal by decoding the at least one video signal, encoding the at least one video signal or transcoding the at least one video signal. The video processing system generates a plurality of text strings that describe the video signal in conjunction with the processing. A memory stores a searchable index that includes the plurality of text strings. A search module identifies at least one matching video of the at least one video signal by comparing the input text string to the plurality of text strings of the searchable index.

Abstract: A multi-pass video encoder includes a video encoding module that encodes a video signal based on an initial configuration data set to generate an initial processed video signal and an initial output data set. An application coding control module generates the initial configuration data set and generates a first updated configuration data set based on both the initial processed video signal and the initial output data set. The video encoding module further encodes the video signal based on the first updated configuration data set to generate a first updated processed video signal and a first updated output data set.

Abstract: An entropy coding module is provided for use in a video encoder that encodes a video input signal based on a plurality of macroblocks derived from the video input signal. The entropy coding module includes an entropy coder that generates entropy encoded data from discrete transformed coefficients for the plurality of macroblocks. A neighbor management module stores neighbor data for at least one macroblock of the plurality of macroblocks for retrieval by the entropy encoder, when operating on at least one neighboring macroblock of the plurality of macroblocks.

Abstract: An entropy coding module is provided for use in a video encoder that encodes a video input signal based on a plurality of macroblocks derived from the video input signal. The entropy coding module includes an entropy coder that generates entropy encoded data from discrete transformed coefficients for the plurality of macroblocks. A neighbor management module stores neighbor data for at least one macroblock of the plurality of macroblocks for retrieval by the entropy encoder, when operating on at least one neighboring macroblock of the plurality of macroblocks.

Abstract: A motion compensation module can be used in a video encoder for encoding a video input signal. The motion compensation module includes a neighbor management module that generates and stores neighbor data for at least one macroblock of the plurality of macroblocks for retrieval for retrieval by at least one of a motion search module, a motion refinement module, a direct mode module, and an intra-prediction module, when operating on at least one neighboring macroblock of the plurality of macroblocks.

Abstract: A video decoder includes an entropy decoding device that generates entropy decoded (EDC) data from an encoded video signal. A multi-format video decoding device includes a plurality of vector processor units that generate a decoded video signal from the EDC data. The plurality of vector processing units are programmed via VPU instructions formatted to include a vector instruction portion, a scalar instruction portion, and a branching instruction portion.

Abstract: A deblocking filter module can be used in a video processing device that processes a video input signal in accordance with a plurality of coding parameters. The deblocking filter module includes an adaptive deblocking filter that receives a plurality of samples and produces a plurality of filtered samples in response thereto, the adaptive deblocking filter having at least one filter parameter that is controllable in response to a filter control signal. A filter control module generates the filter control signal based on the plurality of coding parameters.

Abstract: A motion compensation module can be used in a video encoder that encodes, into a processed video signal, a video input signal including a sequence of pictures. The motion compensation module includes a motion flag generation module that generates a motion flag for at least one of the plurality of macroblocks of a first picture of the sequence of pictures based on a corresponding macroblock of a plurality of macroblocks of a second picture of the sequence of pictures. A direct mode motion vector module evaluates a direct mode motion vector for the corresponding macroblock of the second picture, based on the motion flag for the at least one of the plurality of macroblocks of the first picture.

Abstract: A partition subset selection module selects a subset of available partitions for a macroblock pair of the plurality of macroblock pairs, based on motion search motion vectors generated by a motion search section, and further based on a macroblock adaptive frame and field indicator. A motion refinement module generates refined motion vectors for the macroblock pair, based on the subset of available partitions for a macroblock pair.

Abstract: A system for processing a video signal into a processed video signal includes a pattern recognition module for detecting a face in the image sequence, based on coding feedback data, and generating pattern recognition data in response thereto, wherein the pattern recognition data indicates the pattern of interest. A video codec generates the processed video signal and generates the coding feedback data in conjunction with the processing of the image sequence.

Abstract: A partition subset selection module selects a subset of available partitions for a macroblock pair of the plurality of macroblock pairs, based on motion search motion vectors generated by a motion search section, and further based on a macroblock adaptive frame and field indicator. A motion refinement module generates refined motion vectors for the macroblock pair, based on the subset of available partitions for a macroblock pair.

Abstract: A system for processing a video signal into a processed video signal includes a pattern recognition module for detecting a face in the image sequence, based on coding feedback data, and generating pattern recognition data in response thereto, wherein the pattern recognition data indicates the pattern of interest. A video codec generates the processed video signal and generates the coding feedback data in conjunction with the processing of the image sequence.

Abstract: A system for searching a video library includes a memory that stores a searchable index that includes search features corresponding to videos contained in the video library. A video processing system decodes, encodes or transcodes a video signal and that further generates search features of the video signal. A search module identifies at least one matching video of the video library by comparing the search features of the video signal to corresponding search features of the searchable index. The search features can include at least one shot-level search feature and at least one frame level feature.

Abstract: A system for processing a video signal into a processed video signal includes a pattern recognition module for detecting a region of text in the image sequence based on coding feedback data and generating pattern recognition data in response thereto. A video codec generates the processed video signal and generates the coding feedback data in conjunction with the processing of the image sequence.

Abstract: A system for searching at least one video signal based on an input text string includes a video processing system that processes the at least one video signal by decoding the at least one video signal, encoding the at least one video signal or transcoding the at least one video signal. The video processing system generates a plurality of text strings that describe the video signal in conjunction with the processing. A memory stores a searchable index that includes the plurality of text strings. A search module identifies at least one matching video of the at least one video signal by comparing the input text string to the plurality of text strings of the searchable index.

Abstract: A system for processing a video signal into a processed video signal includes a pattern recognition module for detecting a pattern of interest in the image sequence based on coding feedback data and generating pattern recognition data in response thereto. A video codec generates the processed video signal and generates the coding feedback data in conjunction with the processing of the image sequence.