摘要:
A cache management policy is provided, comprising a method for writing back to a memory (104) a data element set (122) stored in a cache (110). The method reduces the time some items stay in the cache, and thereby improves the utilization of the cache for some applications, especially for video applications. The method comprises determining that each one of the multiple data elements has been updated through at least one write request; marking the data element set as a write-back candidate, in dependency on said determination; and writing the write-back candidate to the memory.
摘要:
A cache management policy is provided, comprising a method for writing back to a memory (104) a data element set (122) stored in a cache (110). The method reduces the time some items stay in the cache, and thereby improves the utilization of the cache for some applications, especially for video applications. The method comprises determining that each one of the multiple data elements has been updated through at least one write request; marking the data element set as a write-back candidate, in dependency on said determination; and writing the write-back candidate to the memory.
摘要:
Video stream processing, such as processing that includes MPEG decoding an subsequent post-processing involves using signal processing circuitry (102, 106) to execute a first and a second video stream processing function. The first video stream processing function produces frame data of successive video frames in a temporally ordered output sequence of frames. The second video stream processing function uses the frame data in an ordered input sequence of frames that differs from the output sequence, for example because later P-frames are needed to decode B frames. The frame data is buffered between application of the first and second video processing function to the frame data. A first and a second. buffer memory (12, 106) are used. The first buffer memory (12) is coupled to the signal processing circuitry via a shareable channel (15) such as an external IC terminals, but the processing circuitry does not use the shareable channel (15) to access the second buffer memory (106). The second video processing function reads frame data from first and second ones of the frames selectively from the first and second buffer memory (12, 106) respectively. The second ones of the frames occur in the same temporal order in both the input and output sequence. The first ones of the frames contain at least all particular frames whose position relative to the second ones of the frames in the output sequence differs from the position of the particular frames relative to the second ones of the frames in the input sequence.
摘要:
A method and apparatus for rendering image data on a 3D display is disclosed. A first image signal is received and then at least one colour component of the first image signal is rendered in reduced spatial resolution to produce a second image signal. The second image signal is spatial filtered wherein spatial errors and view errors are balanced when reconstructing a full resolution signal for the display.
摘要:
Signal processing device for providing multiple output images by processing input images of an interlaced video signal, comprising a temporal interpolater circuit (18) and a memory buffer (26, 27) connected to the temporal interpolater circuit. The memory buffer (26, 27)is arranged for storing at least part of a previous input image (11, 13) and a current input image (12). The temporal interpolater circuit (18) is arranged for receiving at least the previous and current input image from the memory buffer (26, 27) and for providing multiple interlaced or de-interlaced frame data (15) at temporal positions between the previous input image temporal position and the current input image temporal position.
摘要:
An apparatus and method for facilitating a subsequent choice of a motion vector from a plurality of candidate motion vectors in a motion estimation method, include receiving video image data from first, second and third consecutive groups (10, 20, 30) of image data. A first image part (12) of the first group of image data (10), a second image part (22) of the second group of image data (20), and a third image part (32) of the third group of image data (30) are identified, wherein the positions of the three image parts (12, 22, 32) correspond to a motion trajectory that is indicated by a candidate motion vector. A first error measure is then calculated by testing for differences between the first image part (12) and the third image part (32) and quantified as a first error measure. A second error measure is calculated by testing for differences between either the first image part (12) and the second image part (22) or the second image part and the third image part and quantified as a second error measure. An output error measure is then quantified, wherein the output error measure is derived from either the first or the second or a combination of both error measures.
摘要:
A method and apparatus for rendering image data on a 3D display is disclosed. A first image signal is received and then at least one colour component of the first image signal is rendered in reduced spatial resolution to produce a second image signal. The second image signal is spatial filtered wherein spatial errors and view errors are balanced when reconstructing a full resolution signal for the display.
摘要:
The image processor (101) for motion compensated image processing comprises a motion compensation unit (106) for calculating an output image based on a particular motion vector field and based on a first input image and a second input image. The particular motion vector field can be calculated by a motion estimator (104) which is part of the image processor (101) or by an external unit (108). The image processor (101) is designed to select from which source, i.e. the motion estimator (104) or the external unit (108), the particular motion vector field is taken to calculate the output image. The external source is designed to calculate the particular motion vector field based on a motion vector field which was provided by the motion estimator (104) of the image processor (101).
摘要:
A processor executes image processing under control of a clock facility, such that a sequence of C effective clock cycles will effect a processing operation of a predetermined amount of image information. In particular, the processor has programming means for implementing programmable stall clock cycles interspersed between the effective clock cycles for implementing a programmable slowdown factor S, such that a modified number of C*S overall clock cycles will effect processing of the predetermined amount of digital signal information.
摘要:
A technique for frame rate conversion that utilizes motion estimation and motion compensated temporal interpolation includes obtaining a first image and a second image, where the first and second images correspond to different instances in time, compressing the second image using multiple motion vectors that result from motion estimation between the first image and the second image to generate a compressed image, and generating an interpolated image using the compressed image.