摘要:
A video encoding acceleration service to increase one or more of the speed and quality of video encoding is described. The service acts as an intermediary between an arbitrary video encoder computer program application and arbitrary video acceleration hardware. The service receives one or more queries from the video encoder to identify implementation specifics of the video acceleration hardware. The service interfaces with the video acceleration hardware to obtain the implementation specifics. The service communicates the implementation specifics to the video encoder. The implementation specifics enable the video encoder to: (a) determine whether one or more of speed and quality of software encoding operations associated with the video encoder can be increased with implementation of a pipeline of one or more supported encoding pipeline configurations and capabilities, and (b) implement the pipeline by interfacing with the service.
摘要:
Methods and systems provide approaches to start code emulation prevention at a granularity higher than the bit level. By operating at a level other than the bit level, processing capability requirements on both the encoder and decoder side can be reduced. In accordance with one or more embodiments, a start code emulation prevention method looks for data patterns relative to fixed-size data portions larger than single bits. When a particular pattern is found, start code emulation prevention data is inserted to prevent start code emulation. The inserted data is larger than a single bit and, in some embodiments, comprises a byte. When a decoder decodes data that has had start code emulation prevention data inserted, it can easily identify legitimate start codes and then can remove the start code emulation prevention data to provide the original data that was protected. In addition, a data stuffing method is described which allows payload data to be rounded up in size to an integer number of byte sizes, and then allows filler data to be added in a manner which is easily detectable by a decoder.
摘要:
A video encoding acceleration service to increase one or more of the speed and quality of video encoding is described. The service acts as an intermediary between an arbitrary video encoder computer program application and arbitrary video acceleration hardware. The service receives one or more queries from the video encoder to identify implementation specifics of the video acceleration hardware. The service interfaces with the video acceleration hardware to obtain the implementation specifics. The service communicates the implementation specifics to the video encoder. The implementation specifics enable the video encoder to: (a) determine whether one or more of speed and quality of software encoding operations associated with the video encoder can be increased with implementation of a pipeline of one or more supported encoding pipeline configurations and capabilities, and (b) implement the pipeline by interfacing with the service.
摘要:
A video encoding acceleration service to increase one or more of the speed and quality of video encoding is described. The service acts as an intermediary between an arbitrary video encoder computer program application and arbitrary video acceleration hardware. The service receives one or more queries from the video encoder to identify implementation specifics of the video acceleration hardware. The service interfaces with the video acceleration hardware to obtain the implementation specifics. The service communicates the implementation specifics to the video encoder. The implementation specifics enable the video encoder to: (a) determine whether one or more of speed and quality of software encoding operations associated with the video encoder can be increased with implementation of a pipeline of one or more supported encoding pipeline configurations and capabilities, and (b) implement the pipeline by interfacing with the service.
摘要:
Methods and systems provide approaches to start code emulation prevention at a granularity higher than the bit level. By operating at a level other than the bit level, processing capability requirements on both the encoder and decoder side can be reduced. In accordance with one or more embodiments, a start code emulation prevention method looks for data patterns relative to fixed-size data portions larger than single bits. When a particular pattern is found, start code emulation prevention data is inserted to prevent start code emulation. The inserted data is larger than a single bit and, in some embodiments, comprises a byte. When a decoder decodes data that has had start code emulation prevention data inserted, it can easily identify legitimate start codes and then can remove the start code emulation prevention data to provide the original data that was protected. In addition, a data stuffing method is described which allows payload data to be rounded up in size to an integer number of byte sizes, and then allows filler data to be added in a manner which is easily detectable by a decoder.
摘要:
Methods and systems provide approaches to start code emulation prevention at a granularity higher than the bit level. By operating at a level other than the bit level, processing capability requirements on both the encoder and decoder side can be reduced. In accordance with one or more embodiments, a start code emulation prevention method looks for data patterns relative to fixed-size data portions larger than single bits. When a particular pattern is found, start code emulation prevention data is inserted to prevent start code emulation. The inserted data is larger than a single bit and, in some embodiments, comprises a byte. When a decoder decodes data that has had start code emulation prevention data inserted, it can easily identify legitimate start codes and then can remove the start code emulation prevention data to provide the original data that was protected. In addition, a data stuffing method is described which allows payload data to be rounded up in size to an integer number of byte sizes, and then allows filler data to be added in a manner which is easily detectable by a decoder.
摘要:
Methods and apparatuses are provided for facilitating processing of interlaced video images for progressive video displays. In accordance with certain exemplary implementations, a method includes receiving from a renderer a query for a graphics device driver as to at least one graphics processing capability that can be performed by an associated graphics device in de-interlacing video data, communicating the query to the graphics device driver, receiving from the graphics device driver a response to the query that identifies the graphics processing capability/capabilities to the renderer, and communicating the response to the renderer. The method further includes receiving from the renderer a further query for the graphics device driver as to at least one input requirement associated with the identified graphics processing capability, communicating the further query to the graphics device driver, receiving from the graphics device driver a further response to the further query that identifies the input requirement(s) associated with the graphics processing capability, and communicating the further response to the renderer.
摘要:
Strategies are described for processing image information using a data structure which conveys color information. The color information describes color-related formatting applied to the image information. The data structure can be passed down a video processing pipeline, where each functional component in the pipeline can draw color information from the data structure to improve the accuracy of its processing. Further, each component can supply previously unknown color information to the data structure for use by other (downstream) components in the pipeline. Exemplary fields of the data structure can include one or more of: a video transfer function field; a color primaries field; an image light field; a transfer matrix field; a nominal range field; and a video chroma sampling field. The transfer matrix field can be used to convert image information from one color space to another, such as a luma-related color space to an RGB-related color space. Processing operations can be performed on progressive and linear RGB image information.
摘要:
Techniques are provided to allow developers to use a unified application programming interface to access multimedia data from different containers and in different formats.
摘要:
Techniques and tools for representing pixel data in a video processing or capture system are described. Described techniques and tools provide efficient color representation for video processing and capture, and provide flexibility for representing colors using different bit precisions and memory layouts. Described techniques and tools include video formats that can be used, for example, in hardware or software for capture, processing, and display purposes. In one aspect, chroma and luma information for a pixel in a video image is represented in a 16-bit fixed-point block of data having an integer and fractional components. Data can be easily converted from one representation to another (e.g., between 16-bit and 10-bit representations). In other aspects, formats for representing 8-, 10- and 16-bit video image data (e.g., packed and hybrid planar formats), and codes for indicating the formats, are described.