Marvell International Limited

Intel Corporation

Analog Devices,inc.

Other

Marvellworld Trade Ltd.

Bradley C Aldrich

Nigel C Paver

Moinul H Khan

Adam George

Jose Fridman

Ping-Sing Tsai

Ravi Kolagotla

Murli Ganeshan

Thomas A Hartin

Matthew P Wingert

William T Maghielse

Anitha Kona

Hongxin Li

Kayla L Chalmers

Rajith Kumar Mavila

Gang Liang

Jianwei Liu

Paul G Meyer

David B Witt

Mark Norman Fullerton

Ashutosh J Bakhle

According to some embodiments, a technique provides for the execution of an instruction that includes receiving residual data of a first image and decoded pixels of a second image, zero-extending a plurality of unsigned data operands of the decoded pixels producing a plurality of unpacked data operands, adding a plurality of signed data operands of the residual data to the plurality of unpacked data operands producing a plurality of signed results; and saturating the plurality of signed results producing a plurality of unsigned results.

Residual addition for video software techniques

An apparatus, method, and other embodiments associated with performing interpolations to compute gain values that correct for varying spatial intensity are described. In one embodiment, a method includes determining, by an apparatus that processes image data, a gain value for a pixel in the image data for which there is no gain value available in the apparatus, by interpolating related gain values associated with corners of a rectangle bounding the pixel, wherein the interpolating includes determining at least two partial coefficients by interpolating pairs of the related gain values. Noise is filtered from the image data using a noise threshold, and the noise threshold is modified by using the at least two partial coefficients. The method also applies the gain value to the pixel in the image data.

Gain value interpolation

An image capture system including a statistics module. An image processing module is configured to receive image data corresponding to a plurality of pixels of a captured image, wherein the image data includes respective locations of each of the plurality of pixels, and implement an image processing pipeline configured to modified image data. The statistics module is configured to gather a plurality of sets of statistics using the image data and the modified image data, each of the sets of statistics corresponding to a different one of a plurality of zones within the captured image. To gather the statistics, the statistics module is further configured to determine, based on the respective location of a first pixel, a first zone of the plurality of zones that the first pixel is located in, and store data in a corresponding set of statistics for the first pixel based on the determined first zone.

Image capture system and method for gathering statistics for captured image data

A system including an image data source and a transfer function module. The image data source is configured to provide image data. The transfer function module is configured to generate a transfer function to process the image data, define a first region of the transfer function, wherein a curvature of the transfer function in the first region is less than or equal to a threshold, define a second region of the transfer function, wherein a curvature of the transfer function in the second region is greater than the threshold, allocate a first number of sample inputs to the first region, allocate a second number of the sample inputs to the second region, wherein the second number is greater than the first number, map the sample inputs to sample outputs using the transfer function, and populate entries of a lookup table with the sample outputs.

Systems and methods for generating a transfer function to process image data

A method of synthesizing color data through the use of what is called a Gradient Vector Synthesis method is comprised of calculating gradients at 0&#xb0;, 45&#xb0;, 90&#xb0;, and 135&#xb0; with respect to a generation point in a matrix of color data. A first-level edge test is performed by comparing each of the gradients to a noise threshold. If the first-level test indicates that an edge may be present along either of the diagonals, a second-level test may be performed. An interpolation technique is selected in response to the first-level edge test and, when performed, the second-level edge test. The selected interpolation technique is used to synthesize the missing color data at the generation point.

Method and apparatus for color data synthesis in digital image and video capture systems

Images are obtained for image compression. The images are compared using sum of absolute difference devices, which have arithmetic parts, and accumulators. The sign bits of the accumulators are determined at a time of minimum distortion between two images. These sign bits are associated with sets of probabilistically-similar parts. When other sets from that set are obtained later, an early exit is established.

Adaptive early exit techniques in image correlation

Devices, systems, methods, and other embodiments associated with clipping instructions are described. In one embodiment, an apparatus includes a receive logic to receive the clipping instruction. The clipping instruction includes a pixel value to be clipped and a clipping boundary. The apparatus also includes an execution logic to execute the clipping instruction in one clock cycle. The clipping instruction clips pixels by comparing a magnitude of the pixel value identified in the clipping instruction to a magnitude of the clipping boundary identified in the clipping instruction. When the magnitude of the pixel value exceeds the magnitude of the clipping boundary, the pixel is selectively clipped to a result value.

System and method to execute a clipping instruction

According to some embodiments, a device is configured to perform a dual multiply-accumulate operation. In one embodiment, the device includes a functional unit configured to calculate, in parallel, a first multiplication product of a first coefficient and a first sample; and a second multiplication product of the first coefficient and a second sample. The first sample is an (n)th sample and the second sample is an (n+2)th sample in a plurality of sequential samples. The functional unit outputs and stores the first multiplication product and the second multiplication product in different storage locations in at least one storage device.

Dual-multiply-accumulator operation optimized for even and odd multisample calculations

A system includes a block module, a zone module, a statistics module, and a control module. The block module is configured to associate pixel values generated by pixel sensors of an image sensor with M regions. The zone module is configured to define N zones in the M regions. Each of the N zones includes an adjustable number of the M regions. N and M are integers greater than one and N is less than or equal to M. The statistics module is configured to gather statistics corresponding to the N zones. The control module is configured to adjust pixel values generated by the pixel sensors based on the statistics.

Method and apparatus for multiple zone statistics collection for digital image/video capture systems

In one or more embodiments, an apparatus comprises an alignment module implemented in hardware to identify requested data that is not aligned on a natural alignment boundary of a memory and load at least two sets of neighboring data such that each said set includes at least a portion of the requested data. The alignment module is further configured to extract the requested data from the at least two sets of neighboring data and output the extracted data to a processor.

Aligned data access

Transfer functions are often used for image processing. Look-up tables can be used to implement transfer functions in a processor-efficient manner. In one embodiment, the invention is an apparatus that includes a look-up table (LUT) storing sample outputs from an output range of a transfer function, the sample outputs corresponding to sample inputs from an input range of the transfer function, the sample inputs being distributed so that more sample inputs are associated with a first region of the transfer function than a second region of the transfer function; and an address module to calculate an index into the LUT based on image data. In one embodiment, the apparatus uses the LUT to process the image data.

Look-up table for transfer function

A system and method of adaptive edge detection and noise reduction in an image where edge information is detected for each color component of each pixel, whether sensed or synthesized. In some embodiments, the filter applied to a selected non-edge pixel may be determined by the ultimate size of a region around the selected pixel, where the size of the region may be increased if a count of the non-edge pixels in the region is less than a threshold value.

Method and apparatus for spatial noise adaptive filtering for digital image and video capture systems

Systems and methods are provided for processing image data captured by a device. In one implementation, a system is provided to process primary image data based on motion of the device during generation of the image data, as detected by a secondary image sensor. In another implementation, a method is provided for processing image data by generating primary image data, generating secondary image data, calculating, using the secondary image data, at least one motion vector based on motion of the device during generation of the primary image data, processing the primary image data based on the at least one motion vector, and outputting the processed primary image data.

Method and apparatus for processing image data from a primary sensor and a secondary sensor

An apparatus and other embodiments associated with performing interpolations to compute gain values that correct for varying spatial intensity are described. In one embodiment, an apparatus includes interpolation logic configured to determine a gain value for a pixel in image data for which there is no gain value available in the apparatus. The interpolation logic is configured to determine the gain value by performing an interpolation of related gain values available in the apparatus. The apparatus also includes falloff correction logic configured to apply the gain value to the pixel in the image data.

Systems and methods for synthesizing color data. The method includes calculating gradients at a plurality of angles with respect to a generation point in a matrix of color data, performing a first-level edge test by comparing each of the gradients to a noise threshold, selecting an interpolation technique in response to the comparisons, and synthesizing missing color data at said generation point using the selected interpolation technique.

Growing community of inventors

Chandler, AZ, United States of America

Bradley C Aldrich