Texas Instruments Corporation

Niraj Nandan

Mihir Narendra Mody

Rajasekhar Reddy Allu

Hetul Sanghvi

Shashank Dabral

Brian Okchon Chae

Gang Hua

Anthony J Lell

Kedar Satish Chitnis

Anish Reghunath

Mayank Mangla

Brijesh Rameshbhai Jadav

Denis R Beaudoin

Hideo Tamama

Sujith Shivalingappa

Michael Peter Lachmayr

Dipan Kumar Mandal

Mahesh Madhukar Mehendale

Jason A T Jones

Rajat Sagar

Jesse Gregory Villarreal, Jr

Subrangshu Kumar Das

Mullangi Venkata Ratna Reddy

Pandy Kalimuthu

Vikram Vijayanbabu Appia

Gary A Cooper

Prithvi Shankar Yeyyadi Anantha

Pavan Venkata Shastry

Ankur Ankur

Hrushikesh Tukaram Garud

William Cronin Wallace

Jing-Fei Ren

Manoj Koul

Nainala Vyagrheswarudu

Vikram VijayanBabu Appia

Lucas Carl Weaver

Vijayavardhan Baireddy

Hetul Sanghavi

Veeramanikandan Raju

Rahul Gulati

Sriramakrishnan Govindarajan

Shyam Jagannathan

Gregory Raymond Shurtz

Samuel Paul Visalli

Chaitanya Satish Ghone

Piyali Goswami

Denis Roland Beaudoin

Prashant Dinkar Karandikar

Vasant Easwaran

Prithvi Y A Shankar

Sivakumar Ramaiyan

Naresh Kumar Yadav

Rajashekhar Allu

Rajsekhar Allu

David Stoller

Vivek Vilas Dhande

Santhanakrishnan Narayanan Narayanan

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.

Noise estimation using user-configurable information

A system is provided. The system generally includes a first processor configured to receive image input data from a red-green-blue infrared (RGBIR) sensor. The first processor of the system is configured to generate a first intermediate image data from the image input data. The system generally includes a second processor. The second processor of the system is configured to generate a second intermediate image data that includes red-green-blue (RGB) image data from the first intermediate image data, and to generate a third intermediate image data that includes infrared (IR) image data from the first intermediate image data. The system generally includes a third processor. The third processor of the system is configured to process the third intermediate image data. The system generally includes a fourth processor. The fourth processor of the system is configured to process the second image data.

RGBIR color filter image processing with lens shading correction

Various embodiments disclosed herein relate to defective pixel detection and correction, and more specifically to using threshold functions based on color channels to compare pixel values to threshold values. A method is provided herein that comprises identifying a color channel of an image pixel in a frame and identifying a threshold function based at least on the color channel. The method further comprises applying the threshold function to one or more nearest-neighbor values to obtain a threshold value and determining whether a corresponding sensor pixel is defective based at least on a comparison of the image pixel to the threshold value.

Defective pixel detection

A method for error handling in a geometric correction engine (GCE) is provided that includes receiving configuration parameters by the GCE, generating, by the GCE in accordance with the configuration parameters, output blocks of an output frame based on corresponding blocks of an input frame, detecting, by the GCE, a run-time error during the generating, and reporting, by the GCE, an event corresponding to the run-time error.

Error handling in a geometric correction engine

A system to implement debugging for a multi-threaded processor is provided. The system includes a hardware thread scheduler configured to schedule processing of data, and a plurality of schedulers, each configured to schedule a given pipeline for processing instructions. The system further includes a debug control configured to control at least one of the plurality of schedulers to halt, step, or resume the given pipeline of the at least one of the plurality of schedulers for the data to enable debugging thereof. The system further includes a plurality of hardware accelerators configured to implement a series of tasks in accordance with a schedule provided by a respective scheduler in accordance with a command from the debug control. Each of the plurality of hardware accelerators is coupled to at least one of the plurality of schedulers to execute the instructions for the given pipeline and to a shared memory.

Debug for multi-threaded processing

In described examples, an integrated circuit includes first, second, third, and fourth image processing blocks, a data selection circuitry, and a pipeline memory. An input of the first image processing block receives raw image data. An input of the second image processing block is coupled to an output of the first image processing block. An input of the third image processing block is coupled to an output of the second image processing block. A first input of the data selection circuitry is coupled to an output of the first image processing block, and a second input of the data selection circuitry is coupled to an output of the second image processing block. A data input of the pipeline memory is coupled to an output of the data selection circuitry, and an output of the pipeline memory is coupled to an input of the fourth image processing block.

Integrated circuit with multi-application image processing

In an advanced driver-assistance system (ADAS), RAW sensor image processing for a machine vision (MV) application is important. Due to different color, e.g., red/green/blue (RGB), color components, being focused by the lens at different locations in image plane, the lateral chromatic aberration phenomenon may sometimes be observed, which causes false color around edges in the final image output, especially for high contrast edges, which can impede MV applications. Disclosed herein are low-latency, efficient, optimized designs for chromatic aberration correction (CAC) components. An in-pipeline CAC design may be used to perform on-the-fly CAC without any out-of-pipeline memory traffic; enable use of wide dynamic range (WDR) sensors; uses bicubic interpolation; support vertical and horizontal chromatic aberration color channel offsets, reduce CAC line memory requirements, and support flexible look-up table (LUT) down-sampling factors to improve the spatial precision of correction and accommodate popular image sensor resolutions.

In-line chromatic aberration correction in wide dynamic range (WDR) image processing pipeline

In an example, a method includes receiving image data of an input image having lines therein. The method also includes storing a first portion of the image data in a circular buffer in a first memory, wherein the first portion begins at a circular buffer start line in the input image and ends at a circular buffer end line in the input image. The method includes storing a second portion of the image data in a linear buffer in a second memory, where the second portion is non-overlapping with the first portion. The method includes processing the second portion of the image data to produce a first block of an output image. The method includes processing the first portion of the image data to produce a second block of the output image.

Hybrid addressing for imaging and vision data

Methods, apparatus, systems and articles of manufacture (e.g., physical storage media) to implement thread scheduling for multithreaded data processing environments are disclosed. Example thread schedulers disclosed herein for a data processing system include a buffer manager to determine availability of respective buffers to be acquired for respective processing threads implementing respective functional nodes of a processing flow, and to identify first ones of the processing threads as stalled due to unavailability of at least one buffer in the respective buffers to be acquired for the first ones of the processing threads. Disclosed example thread schedulers also include a thread execution manager to initiate execution of second ones of the processing threads that are not identified as stalled.

Thread scheduling for multithreaded data processing environments

A technique for image processing, comprising: receiving input image data, wherein the image data is companded into a first bit depth, wherein the image data includes incomplete color values for pixels of the image data, and wherein the image data is associated with a first color space, interpolating the image data to generate color values for the incomplete color values for pixels of the image data, expanding the image data from the first bit depth to a second bit depth, wherein the color values of the expanded image data have a linear dynamic range, and wherein the second bit depth is higher than the first bit depth, converting the color values for pixels of the expanded image data from the first color space to a second color space, and compressing the color values for pixels of the image data to a third bit depth, the third bit depth lower than the second bit depth, and wherein the compressed color values have a nonlinear dynamic range.

High precision color processing for wide dynamic range sensors

Local automatic white balance (AWB) of wide dynamic range (WDR) images is provided. Methods and systems include collecting, by an image signal processor (ISP), statistics for local AWB from at least one wide dynamic range (WDR) image received by the ISP; generating, by a processor, based on the statistics, local gain lookup tables (LUTs), one for each color channel represented in the WDR image(s), each local gain LUT providing a correlation between gain and intensity; and storing the local gain LUTs. Further processing includes, for each of multiple pixels of a WDR image to be output calculating an intensity value, accessing the local gain LUT for the color channel corresponding to that pixel using the calculated intensity value to identify a corresponding local gain value, and applying the local gain value to that pixel.

Intensity separated local white balance correction

Techniques for image processing including receiving input image data, wherein the input image data includes data associated with a clear color channel, receiving a color offset value associated with a color channel, wherein color values for the color channel are not provided in the input image data, based on the color offset value, generating intermediate estimated color values for the color channel, wherein generating the intermediate estimated color values includes: clipping color values that have a magnitude greater than the color offset value, and adjusting color values that have a magnitude less than the color offset value based on the color offset value, applying a color correction function to the intermediate estimated color values based on the color offset value to determine color corrected estimated color values, and outputting the color corrected estimated color values.

Suppression of clipping artifacts from color conversion

A technique including receiving an image stream for processing; processing the received image stream in a real time mode of operation; outputting an indication that an image processing pipeline has begun processing the received image stream; receiving, in response to the indication, first configuration information associated with test data for testing the image processing pipeline; switching the image processing pipeline to a non-real time mode of operation to process the test data based on the first configuration information during a vertical blanking period of the received image stream; loading the test data from an external memory; switching an input of the image processing pipeline from the image stream to the test data; determining a checksum based on the processed test data; comparing the determined checksum to an expected checksum to determine that the test data was successfully processed; and outputting an indication that the test data was successfully processed.

Fault detection in a real-time image pipeline

A processing accelerator includes a shared memory, and a stream accelerator, a memory-to-memory accelerator, and a common DMA controller coupled to the shared memory. The stream accelerator is configured to process a real-time data stream, and to store stream accelerator output data generated by processing the real-time data stream in the shared memory. The memory-to-memory accelerator is configured to retrieve input data from the shared memory, to process the input data, and to store, in the shared memory, memory-to-memory accelerator output data generated by processing the input data. The common DMA controller is configured to retrieve stream accelerator output data from the shared memory and transfer the stream accelerator output data to memory external to the processing accelerator; and to retrieve the memory-to-memory accelerator output data from the shared memory and transfer the memory-to-memory accelerator output data to memory external to the processing accelerator.

Image processing accelerator

A lens distortion correction function operates by backmapping output images to the uncorrected, distorted input images. As a vision image processor completes processing on the image data lines needed for the lens distortion correction function to operate on a group of output, undistorted image lines, the lens distortion correction function begins processing the image data. This improves image processing pipeline delays by overlapping the operations. The vision image processor provides output image data to a circular buffer in SRAM, rather than providing it to DRAM. The lens distortion correction function operates from the image data in the circular buffer. By operating from the SRAM circular buffer, access to the DRAM for the highly fragmented backmapping image data read operations is removed, improving available DRAM bandwidth. By using a circular buffer, less space is needed in the SRAM. The improved memory operations further improve the image processing pipeline delays.

Low latency streaming remapping engine

Growing community of inventors

Plano, TX, United States of America

Niraj Nandan