Abstract: Certain aspects of a system and method for handling video data may comprise determining data rates associated with each of a plurality of destination devices utilized for processing video data in a video processing system that supports multiple display data rates. A data rate associated with a first portion of the plurality of destination devices may be adjusted to match at least one data rate associated with one or more of a remaining portion of the plurality of destination devices in instances where the determined data rate of the first portion of the plurality of destination devices is greater than one or more data rate associated with one or more of the remaining portion of the plurality of destination devices.

Abstract: Systems and methods are disclosed for video processing modules. More specifically a network is disclosed for processing data. The network comprises a register DMA controller adapted to support register access and at least one node adapted to the data. At least one link communicates with the node, and is adapted to transmit data and at least one network module communicates with at least the link, and is adapted to route data to at least the link.

Abstract: A method and system for processing video data using multi-pixel scaling in a memory system are provided. The multi-pixel scaling may include reading pixel data for one or more data streams from the memory system into one or more scalers, wherein each of the plurality of data streams includes a plurality of pixels, scaling the pixel via the one or more scalers and outputting the scaled pixels from the one or more scalers. Pixel data may be sequential or parallel. The plurality of scalers may be in parallel, scaling sequential pixel data with independent phase control, or scaling parallel pixel data in substantially equal phase. Pixel data may be transposed, replicated, distributed and aligned prior to reading by scalers, and may be aligned merged and transposed after scaling. Scaling may include interpolation or sub sampling using pixel phase, position, step size and scaler quantities.

Abstract: A method and system for processing video data using multi-pixel scaling in a memory system are provided. The multi-pixel scaling may include reading pixel data for one or more data streams from the memory system into one or more scalers, wherein each of the plurality of data streams includes a plurality of pixels, scaling the pixel via the one or more scalers and outputting the scaled pixels from the one or more scalers. Pixel data may be sequential or parallel. The plurality of scalers may be in parallel, scaling sequential pixel data with independent phase control, or scaling parallel pixel data in substantially equal phase. Pixel data may be transposed, replicated, distributed and aligned prior to reading by scalers, and may be aligned merged and transposed after scaling. Scaling may include interpolation or sub sampling using pixel phase, position, step size and scaler quantities.

Abstract: In a signal processing system, a programming system and method for a video network are provided. An event may trigger an RDMA controller to execute current instructions in a register update list. The triggering event may be a start-of-field signal from a live source or an end-of-frame signal. The current instructions may be used to modify the mode of operation of at least one of the network elements in the video network. The modification to the mode of operation may depend on whether the current video field is top field originated or bottom field originated. An interrupt may be used to initiate an interrupt handler that generates at least one new instruction and that updates the new instructions in the register update list. When a trigger occurs prior to an update of the register update list, the RDMA controller may execute the current instructions in the register update list.

Abstract: Various aspects of processing video information in a display controller may comprise calculating a decision value for a current field based on a video format of the current field and an output video format. The decision value may be compared to a threshold value. In instances where the decision value is greater than said threshold value, scaling may be performed prior to performing capturing. In instances where the decision value is less than said threshold value, capturing may be performed before performing scaling.

Abstract: A system and method that support display of video fields using related data encoded in data structures. Each data structure is associated with one video field and contains all the information associated with the display of the video field. The data structure is encoded with the video field that is displayed exactly one field prior to the field associated with the data structure. In an embodiment of the present invention, the data structure contains all the information associated with the display of a video field, regardless of whether certain data changes from one field to the next.

Abstract: Systems and methods are disclosed for filter modules in a video display system or network. One embodiment relates to a method for operating a filter module in a video display network comprising determining a picture type, display type and operation of the display network. The method further comprises determining, in real time, a filter configuration from a plurality of possible filter configurations based on the determined picture type, display type and operation.

Abstract: Systems and methods are disclosed for non-preemptive DRAM transactions. More specifically, the present invention relates to improvements in non-preemptive DRAM transactions in real-time unified memory architectures. One embodiment of the present invention relates to a method for determining access to non-preemptive DRAM devices. This method comprises determining real time need for access to the device and prioritizing access using a rate monotonic scheduling.

Abstract: Aspects of a system and method for processing an image are presented. The method may comprise stretching contrast of an input image based on a distribution of luma values for the input image and a distribution of luma values for a desired output image. The pixels below a specified level of contrast defined by the distribution of luma values for the input image and the distribution of luma values for the desired output image are substantially stretched. The method may also comprise constructing a lookup table of the desired output luma values and stretching a contrast of the input image using the constructed lookup table. The method may also comprise applying linear function and a non-linear function to the distribution of luma values, and applying a stretch factor above a specified level of the distribution and a stretch factor below a specified level of the distribution.

Abstract: Methods and systems for mosaic mode display of video are disclosed. Aspects of one method may include generating video data for a plurality of video windows using a single video feeder module comprising a single video scaler and a single video capture module. The video data for the video windows may be generated in a single frame time. Register DMA may be used to transfer register update data (RUD) to a plurality of registers to configure video processing for generating video data for a video window. The plurality of RUDs may be generated in response to a single interrupt to a processor, and may be configured as a linked list or stored sequentially in memory. The configuring may occur prior to generating video data for the corresponding video window. Video processing for a subsequent video window may be configured automatically after generating video data for the present video window.

Abstract: Presented herein are system(s), and method(s) for non-linear scaling of source pictures to a destination screen. In one embodiment, there is presented a monitor for displaying a source picture. The monitor comprises a screen and a circuit. The screen comprises a plurality of columns, including at least one center column, a plurality of left columns, and a plurality of right columns. The circuit provides pixels for display at each of the plurality of columns of a source picture that are indicated by the phase accumulator. The phase accumulator is incremented by step values that are continuous with respect to the plurality of columns.

Abstract: Flesh-tones corrections may be performed to correct color shifts that may occur in transmitted video frames wherein chroma information corresponding to flesh-tone video pixels may be distorted. A target region may be determined based on a determined flesh-tones region within a spatial representation of chroma in video color space, such as Y?CrCb. The flesh-tones correction may utilize one or more methodologies based on an elliptical shape and/or a triangular shape algorithm(s). A video processing system may be utilized to analyze chroma information of received video pixels and/or to perform flesh-tones corrections by shifting the chroma value of received video pixels towards good flesh-tones regions to compensate for possible distortions. The video processing system may perform conversion calculation and/or shift operations dynamically. The video processing system may also utilize lookup tables (LUTs) to convert received chroma values.

Abstract: Systems and methods are disclosed for non-preemptive DRAM transactions. More specifically, the present invention relates to improvements in non-preemptive DRAM transactions in real-time unified memory architectures. One embodiment of the present invention relates to a method for determining access to non-preemptive DRAM devices. This method comprises determining real time need for access to the device and prioritizing access using a rate monotonic scheduling.

Abstract: Systems and methods are disclosed for filter modules in a video display system or network. One embodiment relates to a method for operating a filter module in a video display network comprising determining a picture type, display type and operation of the display network. The method further comprises determining, in real time, a filter configuration from a plurality of possible filter configurations based on the determined picture type, display type and operation.

Abstract: A method and system that blend graphics layers and a video layer. The graphics layers may be above and below the video layer, which may be a streaming video. The graphics layers may be stored in memory, blended and stored back in memory. The blended graphics layers may be combined with streaming video and output on a display. Blending the graphics in memory may be done offline and may save processing time and improve real-time combining with streaming video. In an embodiment of the present invention, there may be several layers of graphics below the video layer, and several graphics layers above the video layer. The top graphics layers may be blended into one top graphics layer, and the bottom graphics layers may be blended into one bottom graphics layer. The top and bottom graphics layers may be then blended into one graphics layer and combined with the video layer.

Abstract: Systems and methods are disclosed for performing multiple processing of data in a network. In one embodiment, the network comprises a first display pipeline that is formed in real time from a plurality of possible display pipelines and that performs at least a first processing step on received data. A buffer stores the processed data and a second display pipeline that is formed in real time from a plurality of possible display pipelines performs at least a second processing step on stored data.

Abstract: A system and method for detecting the presence and location of pull-down fields in a video field stream. Various aspects of the present invention may comprise method steps and circuit structure for generating an array of variance indications, each of which represents a degree of variance between two video fields in the video field stream. Various aspects may comprise comparing the array of variance indications to a pattern to detect a pull-down field in the video field stream. Various aspects may comprise comparing corresponding portions of video fields and generating a histogram of differences between the corresponding portions. Various aspects may comprise generating an indication of variance of the histogram and analyzing the indication of variance. Various aspects may comprise analyzing an array of such indications of variance and may comprise comparing the array of such indications to a pattern or plurality of patterns.

Abstract: A system and method for improving decisions for 2D combing of a video. A 2D-comb is applied to a baseband video signal, thus producing a chroma component of the signal, and an associated combing error. A narrowband filter is applied to the chroma component to produce a filtered chroma component. The chroma component and the filtered chroma component are blended in proportions based on the amount of combing error to produce a new chroma component. A larger combing error induces selection or blending a larger portion of the filtered chroma component, which as a result of narrowband filtering contains less cross-chroma error. Subtracting the new chroma component from the baseband video signal produces a new luma component. The chroma component can also be filtered using a wider band filter to produce a non-complementary chroma component to be subtracted from the baseband video signal to produce the new luma component.

Abstract: Aspects of a system and method for processing video data may comprise, for each line of a field of an image, generating noise based on a current seed, inserting the generated noise in a current line of the field, and generating a new seed for processing a subsequent line of the field by shifting the current seed. The current seed may be used to generate a random number and the generated noise may be produced using this generated random number.