Abstract: A method is provided that includes receiving pictures of a video sequence in a video encoder, and encoding the pictures to generate a compressed video bit stream that is transmitted to a video decoder in real-time, wherein encoding the pictures includes selecting a picture to be encoded as a delayed duplicate intra-predicted picture (DDI), wherein the picture would otherwise be encoded as an inter-predicted picture (P-picture), encoding the picture as an intra-predicted picture (I-picture) to generate the DDI, wherein the I-picture is reconstructed and stored for use as a reference picture for a decoder refresh picture, transmitting the DDI to the video decoder in non-real time, selecting a subsequent picture to be encoded as the decoder refresh picture, and encoding the subsequent picture in the compressed bit stream as the decoder refresh picture, wherein the subsequent P-picture is encoded as a P-picture predicted using the reference picture.

Abstract: This disclosure relates to various implementations an embedded computing system. The embedded computing system comprises a hardware accelerator (HWA) thread user and a second HWA thread user that creates and sends out message requests. The HWA thread user and the second HWA thread user is communication with a microcontroller (MCU) subsystem. The embedded computing system also comprises a first inter-processor communication (IPC) interface between the HWA thread user and the MCU subsystem and a second IPC interface between the second HWA thread user and the MCU subsystem, where the first IPC interface is isolated from the second IPC interface. The MCU subsystem is also in communication with a first domain specific HWA and a second domain specific HWA.

Abstract: A computer vision system is provided that includes an image generation device configured to capture consecutive two dimensional (2D) images of a scene, a first memory configured to store the consecutive 2D images, a second memory configured to store a growing window of consecutive rows of a reference image and a growing window of consecutive rows of a current image, wherein the reference image and the current image are a pair of consecutive 2D images stored in the first memory, a third memory configured to store a sliding window of pixels fetched from the growing window of the reference image, wherein the pixels in the sliding window are stored in tiles, and a dense optical flow engine (DOFE) configured to determine a dense optical flow map for the pair of consecutive 2D images, wherein the DOFE uses the sliding window as a search window for pixel correspondence searches.

Abstract: A method for geometrically correcting a distorted input frame and generating an undistorted output frame includes capturing and storing an input frame in an external memory, allocating an output frame with an output frame size and dividing the output frame into output blocks, computing a size of the input blocks in the input image corresponding to each output blocks, checking if the size of the input blocks is less than the size of the internal memory and if not dividing until the required input block size of divided sub blocks is less than the size of the internal memory, programming an apparatus with input parameters, fetching the input blocks into an internal memory, processing each of the divided sub blocks sequentially and processing the next output block in step until all the output blocks are processed; and composing the output frame for each of the blocks in the output frame.

Abstract: A data processing device is provided that includes a plurality of hardware data processing nodes, wherein each hardware data processing node performs a task, and a hardware thread scheduler including a plurality of hardware task schedulers configured to control execution of a respective task on a respective hardware data processing node of the plurality of hardware data processing nodes, and a proxy hardware task scheduler coupled to a data processing node external to the data processing device, wherein the proxy hardware task scheduler is configured to control execution of a task by the external data processing device, wherein the hardware thread scheduler is configurable to execute a thread of tasks, the tasks including the task controlled by the proxy hardware task scheduler and a first task controlled by a first hardware task scheduler of the plurality of hardware task schedulers.

Abstract: A method of de-mosaicing pixel data from an image processor includes generating a pixel block that includes a plurality of image pixels. The method also includes determining a first image gradient between a first set of pixels of the pixel block and a second image gradient between a second set of pixels of the pixel block. The method also includes determining a first adaptive threshold value based on intensity of a third set of pixels of the pixel block. The pixels of the third set of pixels are adjacent to one another. The method also includes filtering the pixel block in a vertical, horizontal, or neutral direction based on the first and second image gradients and the first adaptive threshold value utilizing a plurality of FIR filters to generate a plurality of component images.

Abstract: A method for filtering noise for imaging includes receiving an image frame having position and range data. A filter size divides the frame into filter windows for processing each of the filter windows. For the first pixel, a space to the center pixel and a range difference between this pixel and the center pixel is determined and used for choosing a selected weight from weights in a 2D weight LUT including weighting for space and range difference, a filtered range value is calculated by applying the selected 2D weight to the pixel, and the range, filtered range value and selected 2D weight are summed. The determining, choosing, calculating and summing are repeated for at least the second pixel. A total sum of contributions from the first and second pixel are divided by the sum of selected 2D weights to generate a final filtered range value for the center pixel.

Abstract: Methods, apparatus, systems and articles of manufacture to perform graphics processing on combinations of graphic processing units and digital signal processors are disclosed. A disclosed example method includes processing first data representing input vertices to create second data, the first data using a first format organized by vertex, the second data using a second format organized by components of the vertices. A digital signal processor (DSP) is to perform vertex shading on the second data to create third data, the third data formatted using the second format, the vertex shading performed by executing a first instruction at the DSP, the first instruction generated based on a second instruction capable of being executed at a graphics processing unit (GPU). The third data is processed to create fourth data, the fourth data formatted using the first format.

Abstract: In some examples, a method comprises receiving pixel data from an image capture device having a color filter, wherein the pixel data represents a portion of an image. The method further includes performing wavelet decomposition on the pixel data to produce decomposed pixel data and determining a local intensity of the pixel data. The method also includes determining a noise threshold value based on the local intensity and a noise intensity function that is based on the color filter; determining a noise value for the pixel data based on the decomposed pixel data and the noise threshold value; and correcting the pixel data based on the noise value to produce an output image.

Abstract: A method is provided that includes receiving pictures of a video sequence in a video encoder, and encoding the pictures to generate a compressed video bit stream that is transmitted to a video decoder in real-time, wherein encoding the pictures includes selecting a picture to be encoded as a delayed duplicate intra-predicted picture (DDI), wherein the picture would otherwise be encoded as an inter-predicted picture (P-picture), encoding the picture as an intra-predicted picture (I-picture) to generate the DDI, wherein the I-picture is reconstructed and stored for use as a reference picture for a decoder refresh picture, transmitting the DDI to the video decoder in non-real time, selecting a subsequent picture to be encoded as the decoder refresh picture, and encoding the subsequent picture in the compressed bit stream as the decoder refresh picture, wherein the subsequent P-picture is encoded as a P-picture predicted using the reference picture.

Abstract: A method for geometrically correcting a distorted input frame and generating an undistorted output frame includes capturing and storing an input frame in an external memory, allocating an output frame with an output frame size and dividing the output frame into output blocks, computing a size of the input blocks in the input image corresponding to each output blocks, checking if the size of the input blocks is less than the size of the internal memory and if not dividing until the required input block size of divided sub blocks is less than the size of the internal memory, programming an apparatus with input parameters, fetching the input blocks into an internal memory, processing each of the divided sub blocks sequentially and processing the next output block in step until all the output blocks are processed; and composing the output frame for each of the blocks in the output frame.

Abstract: An apparatus and method for geometrically correcting a distorted input frame and generating an undistorted output frame. The apparatus includes an external memory block that stores the input frame, a counter block to compute output coordinates of the output frame for a region based on a block size of the region, a back mapping block to generate input coordinates corresponding to each of the output coordinates, a bounding module to compute input blocks corresponding to each of the input coordinates, a buffer module to fetch data corresponding to each of the input blocks, an interpolation module to interpolate data from the buffer module and a display module that receives the interpolated data for each of the regions and stitch an output image. The method includes determining the size of the output block based on a magnification data.

Abstract: An apparatus for scaling images is provided that includes at least two input ports, a scaling component coupled to the at least two input ports, the scaling component including a plurality of scalers, the scaling component configurable to map any scaler to any input port of the at least two input ports and configurable to map more than one scaler to any input port, and a memory coupled to the at least two input ports and to outputs of the plurality of scalers, the memory configured to store image data for each input port and scaled image data output by the plurality of scalers.

Abstract: A computer vision system is provided that includes an image generation device configured to capture consecutive two dimensional (2D) images of a scene, a first memory configured to store the consecutive 2D images, a second memory configured to store a growing window of consecutive rows of a reference image and a growing window of consecutive rows of a current image, wherein the reference image and the current image are a pair of consecutive 2D images stored in the first memory, a third memory configured to store a sliding window of pixels fetched from the growing window of the reference image, wherein the pixels in the sliding window are stored in tiles, and a dense optical flow engine (DOFE) configured to determine a dense optical flow map for the pair of consecutive 2D images, wherein the DOFE uses the sliding window as a search window for pixel correspondence searches.

Abstract: Described examples include an integrated circuit including a vector multiply unit including a plurality of multiply/accumulate nodes, in which the vector multiply unit is operable to provide an output from the multiply/accumulate nodes, a first data feeder operable to provide first data to the vector multiply unit in vector format, and a second data feeder operable to provide second data to the vector multiply unit in vector format.

Abstract: An outer product multiplier (GPM) system/method that integrates compute gating and input/output circular column rotation functions to balance time spent in compute and data transfer operations while limiting overall dynamic power dissipation is disclosed. Matrix compute gating (MCG) based on a computation decision matrix (CDM) limits the number of computations required on a per cycle basis to reduce overall matrix compute cycle power dissipation. A circular column rotation vector (CRV) automates input/output data formatting to reduce the number of data transfer operations required to achieve a given matrix computation result. Matrix function operators (MFO) utilizing these features are disclosed and include: matrix-matrix multiplication; matrix-matrix and vector-vector point-wise multiplication, addition, and assignment; matrix-vector multiplication; vector-vector inner product; matrix transpose; matrix row permute; and vector-column permute.

Abstract: Methods, apparatus, systems and articles of manufacture to perform graphics processing on combinations of graphic processing units and digital signal processors are disclosed. A disclosed example method includes processing first data representing input vertices to create second data, the first data using a first format organized by vertex, the second data using a second format organized by components of the vertices. A digital signal processor (DSP) is to perform vertex shading on the second data to create third data, the third data formatted using the second format, the vertex shading performed by executing a first instruction at the DSP, the first instruction generated based on a second instruction capable of being executed at a graphics processing unit (GPU). The third data is processed to create fourth data, the fourth data formatted using the first format.

Abstract: A method for analyzing images to generate a plurality of output features includes receiving input features of the image and performing Fourier transforms on each input feature. Kernels having coefficients of a plurality of trained features are received and on-the-fly Fourier transforms (OTF-FTs) are performed on the coefficients in the kernels. The output of each Fourier transform and each OTF-FT are multiplied together to generate a plurality of products and each of the products are added to produce one sum for each output feature. Two-dimensional inverse Fourier transforms are performed on each sum.

Abstract: A CNN based-signal processing includes receiving of an encrypted output from a first layer of a multi-layer CNN data. The received encrypted output is subsequently decrypted to form a decrypted input to a second layer of the multi-layer CNN data. A convolution of the decrypted input with a corresponding decrypted weight may generate a second layer output, which may be encrypted and used as an encrypted input to a third layer of the multi-layer CNN data.

Abstract: The disclosure provides a sample adaptive offset (SAO) encoder. The SAO encoder includes a statistics collection (SC) block and a rate distortion optimization (RDO) block coupled to the SC block. The SC block receives a set of deblocked pixels and a set of original pixels. The SC block categorizes each deblocked pixel of the set of deblocked pixels in at least one of a plurality of band and edge categories. The SC block estimates an error in each category as difference between a deblocked pixel of the set of deblocked pixels and corresponding original pixel of the set of original pixels. The RDO block determines a set of candidate offsets associated with each category and selects a candidate offset with a minimum RD cost. The minimum RD cost is used by a SAO type block and a decision block to generate final offsets for the SAO encoder.