Method for optimizing image motion estimation
AssigneeIntel Corporation
InventorMichael Keith
Life of this patent
Estimating the term…
Loading patent…
AssigneeIntel Corporation
InventorMichael Keith
Estimating the term…
A method is provided for performing motion estimation in a system having a test image and a plurality of candidate images. A candidate image is selected and the difference between the test image and the selected candidate image is determined. The motion of an image is estimated according to this differencing and a determination is made of the duration of the motion estimation process in the system of the present invention. The candidate image selection, the differencing and the motion estimation are then repeated according to the duration determination. The duration determination may be a determination of a time duration or a determination of a number of machine cycles. The system is adapted to iteratively decrease a measurement of the error between the test image and selected candidate images as these actions are repeated. When the error stops decreasing and begins increasing the assumption is made in the system of the present invention that a best match has been determined. Thus a best match is iteratively determined unless a time out occurs first.
A method for estimating image motion in a video processing system having a test image, a plurality of candidate images, difference determining means for determining a difference between images, and duration determining means for determining the duration of the image motion estimation process of steps (a), (b), and (c) below, comprising the steps of:
Dependencies are inferred from the claim text.
Drawings are temporarily unavailable. Open the PDF at USPTO
No related US applications are recorded in the indexed filing history.
Fourier, Walsh or analogous domain transformations , e.g. Laplace, Hilbert, Karhunen-Loeve, transforms: discrete orthonormal transforms, e.g.…
Movement detection: movement estimation
Methods or arrangements for coding, decoding, compressing or decompressing digital video signals: characterised by implementation details or…
Involving temporal prediction: motion estimation or motion compensation
Term ended 13 May 2013 (estimated)
USPTO file history isn’t available for this patent, so only indexed dates are shown.
1. Field of the Invention
This invention relates to the field of video processing and, in particular, to the compression and decompression of video signals.
2. Background Art Statement
FIG. 1 shows a block diagram representation of a video processing system including a system and method for accelerating the compression and decompression of digital video signals of the present invention.
FIG. 2 shows a block diagram representation of the pipelined architecture of the system and method for accelerating the compression and decompression of video digital signals of the present invention.
FIGS. 3A, B show a block diagram representation of the data flow of the system and method of FIG. 2 when it is adapted to encode digital video signals and physical buffer memories for use in this process.
Referring now to FIG. 1, there is shown remote video processing system 100 including compression/decompression accelerator 120. The bus structure of remote video processing system 100, including address bus 116 and data bus 118, permits easy interconnection of the components of a multimedia display system without using a host processor bus. For example, the local video data of video camera 127 may be received by video processing system 100 by way of line 129 and captured, digitized, subsampled and scaled by video capture 128. The signals provided by video capture 126 may then be processed by system 100 for transmission to merge logic video by way of system output line 132 and capture 128. All of these operations are performed by remote video processing system 100 without use of a host processor bus or an industry standard bus such as bus 140 which may couple remote system 100 to a host computer by way of bus 138. Because system 100 interfaces a source of video data such as video camera 127 to bus 140, system 100 may be understood to be a remote video interface system 100.
Within video processing system 100 digital video processor 112 performs software processing while accelerator 120 does hardwired functions. Nucleus gate array 121 performs the required memory interface functions. For example, VRAM emulation block 124 makes nucleus gate array 121 function like DRAM with respect to capture 128. Video processing system 100 is therefore limited to the memory configurations supported by nucleus gate array 121.
In a typical configuration of remote video processing system 100 up to sixteen megabytes of address space may be supported. The first fifteen megabytes of this address space may be reserved for DRAM, for example, DRAM 114, which is interfaced with nucleus gate array 121 by DRAM interface 122. The upper one megabyte of the memory space of video processing system 100 is reserved for communication between various devices which may be coupled to address bus 116 and data bus 118. Compression/decompression accelerator 120 may occupy the first one hundred twenty-eight kilobytes of the communication area in the upper one megabyte of memory space.