Abstract: A video processing device includes a video processing unit that decodes a video input signal into a decoded video signal in accordance with a video compression protocol, based on uncompressed video frame data. A data object compression/decompression module generates compressed video frame data by compressing a plurality of video data objects into a plurality of compressed video data objects, storing the plurality of compressed video data objects in a compressed frame buffer. The data object compression/decompression module retrieves a selected portion of video frame data from the compressed video frame buffer by identifying selected ones of plurality of compressed video data objects that correspond to the selected portion of video frame data, retrieving the selected ones of the plurality of compressed video data objects and generating the uncompressed video frame data by decompressing the selected ones of the plurality of compressed video data objects.

Abstract: A video processing device includes a video processing unit that decodes a video input signal into a decoded video signal in accordance with a video compression protocol, based on uncompressed video frame data. A data object compression/decompression module generates compressed video frame data for storage in a compressed video frame buffer by compressing a plurality of video data objects into a plurality of compressed video data objects, wherein a first subset of the plurality of video data objects are compressed via lossless compression and a second subset of the plurality of video data objects are compressed via lossy compression.

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 processing device includes an interface to receive an input video stream and an interface to provide an encoded video stream. The input video stream includes a sequence of frames. Each frame comprises two fields. The video processing device further includes an encoder to encode the input video stream to generate the encoded video stream. The encoder is to dynamically switch between a first encoding mode and a second encoding mode responsive to a variable quantization parameter. In the first encoding mode the encoder is to encode both fields or the complete frame of a corresponding frame of the sequence. In the second encoding mode the encoder is to encode only one field of the two fields of a corresponding frame of the sequence. This approach can achieve a specified low bit rate with reduced quantization effects while keeping the horizontal resolution unchanged.

Abstract: A device encodes a video signal having a sequence of images into an encoded video signal. The device includes a group of picture (GOP) adaption module that detects a high complexity scene in the sequence of images and that generates GOP adaption data indicating the high complexity scene when the high complexity scene is detected. An encoding module generates the encoded video signal with hierarchical B frames disabled when the GOP adaption data indicates the high complexity scene.

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 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 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 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 metric representing the sum of variances for pixel blocks of a region of an image are used to identify the presence a video feature of the image, and a transcoding is performed responsive to identifying the presence of the video feature. The identified video feature can include, but is not limited to, a scene change, the presence of a black border region or a caption region, or the complexity of the image. The transcoding operation can include, but is not limited to, coding the image as an Intra-frame, omitting the content corresponding to the black border region or the caption region from the transcoded image or allocating a relatively lower bit budget for the black border region or a relatively higher bit budget to the caption region during transcoding of the image, or setting the bit budget for rate control during transcoding.

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 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 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 human action 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 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.

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 scaled motion search section can be used in a video processing device that processes a video input signal that includes a plurality of pictures. The scaled motion search section includes a downscaling module that downscales the plurality of pictures to generate a plurality of downscaled pictures, wherein the downscaling module includes a horizontal downscaling filter and a vertical downscaling filter, and wherein the vertical downscaling filter generates downscaled pixels for a macroblock pair using only pixels from the macroblock pair. A transfer function that models the scaled motion vectors is determined and used to identify a final set of motion vector candidates used in a larger scale motion search.

Abstract: A video encoder includes a mode decision module that determines a final macroblock cost for each macroblock of the plurality of macroblocks based on costs associated with a plurality of motion vectors. An intra pulse code modulation (IPCM) module, when enabled, selects an IPCM mode when the final macroblock cost compares unfavorably to an IPCM threshold. A reconstruction module generates residual pixel values for each macroblock of the plurality of macroblocks and a transform and quantization module, transforms and quantizes the residual pixel values when the IPCM mode is not selected.

Abstract: A motion compensation module, that can be used in a video encoder for encoding a video input signal, includes a motion search module that generates a motion search motion vector for each macroblock of a plurality of macroblocks by contemporaneously evaluating a top frame macroblock and bottom frame macroblock from a frame of the video input signal and a top field macroblock and a bottom field macroblock from corresponding fields of the video input signal. A motion refinement module, when enabled, generates a refined motion vector for each macroblock of the plurality of macroblocks, based on the motion search motion vector.

Abstract: A video encoder includes a forward path section that processes a video input signal in accordance with a video compression standard, based on a plurality of reference pictures, to generate a processed video signal and a plurality of transformed quantized residual pixel values. A decoding engine decodes the plurality of transformed quantized residual pixel values in accordance with the video compression standard to the plurality of reference pictures.