Abstract: Aspects of the disclosure are directed to error recovery. In accordance with one aspect, an apparatus includes a plurality of sensors configured to generate a plurality of sensor data; a plurality of sensor interfaces, wherein each one of the plurality of sensor interfaces is coupled to each one of the plurality of sensors; and an aggregator, coupled to the plurality of sensor interfaces, the aggregator configured a) to multiplex the plurality of sensor data into a single aggregator output stream, b) to detect a transmission error in the plurality of sensor data, and c) to recover the transmission error using an aggregator hardware without software involvement.

Abstract: This disclosure provides systems, methods, and devices for image signal processing that support compression of phase detection (PD) data. In a first aspect, a method of image processing includes receiving image data and first phase detection data corresponding to the image data; determining a first channel of the first phase detection data and a second channel of the first phase detection data; and coding the first phase detection data to determine second phase detection data by separately coding the first channel and the second channel. Other aspects and features are also claimed and described.

Abstract: An image processing system includes an image sensor configured to generate a video frame, the video frame having a data portion and a test portion, an inline front end (IFE) having at least one processing module, a first memory, a functional software register, and a test software register, the IFE configured to receive the video frame, process the video frame and store the processed video frame to a second memory, a test pattern generator configured to generate test data that is provided to the IFE during the test portion of the video frame, a multiple input signature register (MISR) test function configured to compute a MISR signature from the test data, and a comparison function configured to compare a verified version of the test data to the computed MISR signature in the IFE to determine whether a system interrupt should be generated.

Abstract: Systems and techniques are described herein for processing frames. For example, a process can include obtaining a current frame from a sequence of frames, the current frame associated with a first bit depth resolution and a reference frame preceding the current frame associated with the first bit depth and resolution. The process can include determining a difference between a first pixel value of the current frame and a second pixel value of the reference frame, the first pixel value and the second pixel value associated with a corresponding first pixel position. The process can include outputting a first portion of the determined difference as a first output value and, based on a determination that the determined difference does not exceed a maximum magnitude of a second bit depth, outputting an indication that the determined difference does not include a second portion associated with the first pixel position.

Abstract: Techniques are described herein for processing image data. For instance, a technique can include obtaining a first image having a first exposure time and a second image having a second exposure time that is greater than the first exposure time. The technique can further include determining at least one of: that a first pixel of the first image has a first pixel value below a first threshold value; or that a second pixel of the second image has a second pixel value above a second threshold value; suppressing at least one of the first pixel or the second pixel based on the determination so as to prevent storing the first pixel or the second pixel; replacing the suppressed first pixel or second pixel based on a another pixel value; and outputting the first image or the second image, the first image or the second image including the another pixel.

Abstract: Techniques are described herein for processing image data. For instance, a technique can include obtaining a first image having a first exposure time and a second image having a second exposure time, the second exposure time greater than the first exposure time; determining at least one of: that one or more pixels of the first image has a pixel value below a first threshold value; or that one or more pixels of the second image has a pixel value above a second threshold value; preventing image processing on the one or more pixels based on the determination; replacing, based on preventing image processing on the one or more pixels, one or more pixel values of the one or more pixels with one or more replacement pixel values; and outputting the first or the second image, the first or the second image including the one or more replacement pixel values.

Abstract: Techniques are described herein for processing image data. For instance, a technique can include obtaining a first image having a first exposure time and a second image having a second exposure time that is greater than the first exposure time. The technique can further include determining at least one of: that a first pixel of the first image has a first pixel value below a first threshold value; or that a second pixel of the second image has a second pixel value above a second threshold value; suppressing at least one of the first pixel or the second pixel based on the determination so as to prevent storing the first pixel or the second pixel; replacing the suppressed first pixel or second pixel based on a another pixel value; and outputting the first image or the second image, the first image or the second image including the another pixel.

Abstract: Techniques are described herein for processing data. For instance, a process can include receiving input data by a symmetrical processing engine of two or more symmetrical processing engines coupled to an auxiliary processing engine. The process can further include receiving an indication to process the input data using a module of the auxiliary processing engine, transmitting output data to the auxiliary processing engine, receiving processed data from the auxiliary processing engine, further processing the processed data in one or more portions of a pipeline of modules of the symmetrical processing engine, and outputting the further processed data.

Abstract: Disclosed are systems, apparatuses, processes, and computer-readable media to capture images with subjects at different depths of fields. For instance, a method of processing image data includes obtaining a first image captured using an image sensor with a first exposure. The method may further include obtaining a second image captured using the image sensor with a second exposure. The method may include compressing the second image based on a comparison of the second image with the first image and storing the compressed second image in a memory. The method may further include obtaining the compressed second image from the memory and decompressing the compressed second image based on a difference between the compressed second image and the first image. The method may further include generating a combined image at least in part by combining the first image and the second image.

Abstract: Systems and techniques are provided for generating an HDR image. An example method can include obtaining a first image and a second image that has an exposure that is greater than an exposure of the first image; setting pixels of the first image that are below a minimum threshold to a minimum value and pixels of the second image that are above a maximum threshold to a maximum value; retrieving, from memory, a compressed version of the first image with the pixels set to the minimum value and a compressed version of the second image with the pixels set to the maximum value; generating a first decompressed image including the first image with the pixels set to the minimum value and a second decompressed image including the second image with the pixels set to the maximum value; and generating an HDR image based on the first and second decompressed images.

Abstract: Systems and techniques are provided for generating an HDR image. An example method can include obtaining a first image and a second image that has an exposure that is greater than an exposure of the first image; setting pixels of the first image that are below a minimum threshold to a minimum value and pixels of the second image that are above a maximum threshold to a maximum value; retrieving, from memory, a compressed version of the first image with the pixels set to the minimum value and a compressed version of the second image with the pixels set to the maximum value; generating a first decompressed image including the first image with the pixels set to the minimum value and a second decompressed image including the second image with the pixels set to the maximum value; and generating an HDR image based on the first and second decompressed images.

Abstract: Systems and techniques are described herein for processing frames. For example, a process can include obtaining a current frame from a sequence of frames, the current frame associated with a first bit depth resolution and a reference frame preceding the current frame associated with the first bit depth and resolution. The process can include determining a difference between a first pixel value of the current frame and a second pixel value of the reference frame, the first pixel value and the second pixel value associated with a corresponding first pixel position. The process can include outputting a first portion of the determined difference as a first output value and, based on a determination that the determined difference does not exceed a maximum magnitude of a second bit depth, outputting an indication that the determined difference does not include a second portion associated with the first pixel position.

Abstract: An example image processor for processing pixels includes processing circuitry configured to determine that a first subset of input bits of a current pixel are the same as a first subset of input bits of a previously processed pixel, selectively bypass processing the first subset of input bits through a first pipeline based on the determination, output a first subset of output bits of the previously processed pixel as a first subset of output bits of the current pixel based on the determination, and merge the first subset of output bits of the current pixel with a second subset of output bits of the current pixel generated through a second pipeline from a second subset of input bits of the current pixel.

Abstract: Systems and methods for processing pixels of an image at an imaging hardware device are provided. The method comprises receiving a first pixel. The method further comprises determining a content parameter of the first pixel. The method further comprises, based on the determining, storing the content parameter of the first pixel. The method further comprises initiating a computation of a first output pixel value for the first pixel. The method further comprises receiving a second pixel. The method further comprises determining a content parameter of the second pixel. The method further comprises determining that the second pixel is redundant in response to the content parameter of the second pixel matching the stored content parameter of the first pixel. The method further comprises, in response to the matching, setting a second output pixel value for the second pixel to be equal to the first output pixel value.

Abstract: System and method for storing information units is provided. The system includes a memory comprising a plurality of contiguous memory segments, a local memory storing a plurality of pointers, each pointer pointing to one contiguous memory segment, a receiving unit configured to arrange incoming information units into queues and memory control logic configured to allocate pointers to the queues and configured to cause the incoming information units to be written into contiguous memory segments. The incoming information units form at least one queue and wherein pointers form a linked list of pointers if the information units are written into more than one contiguous memory segment.

Abstract: System and method for storing information units is provided. The system includes a memory comprising a plurality of contiguous memory segments, a local memory storing a plurality of pointers, each pointer pointing to one contiguous memory segment, a receiving unit configured to arrange incoming information units into queues and memory control logic configured to allocate pointers to the queues and configured to cause the incoming information units to be written into contiguous memory segments. The incoming information units form at least one queue and wherein pointers form a linked list of pointers if the information units are written into more than one contiguous memory segment.