Techniques for gaze-contingent sensing and processing

    公开(公告)号:US12124623B1

    公开(公告)日:2024-10-22

    申请号:US17954583

    申请日:2022-09-28

    IPC分类号: G06F3/01 G06T19/00

    CPC分类号: G06F3/013 G06T19/006

    摘要: Various embodiments set forth computer vision systems. In some embodiments, one or more activation maps are generated based on eye gaze data and used to control operation of one or more sensors. Each activation map indicates a highest density for acquiring sensor data in a region corresponding to an eye gaze direction and lower densities for acquiring sensor data in other regions. After the sensor data is acquired, a processing pipeline sub-samples (or bins) and processes regions of the acquired sensor data at different ratios based on the eye gaze direction. The sub-sampled (or binned) data for each region is processed independently, and results of the processing are combined to generate processed data, such as an image that can be displayed to a user.

    Image sensor post processing
    2.
    发明授权

    公开(公告)号:US11595602B2

    公开(公告)日:2023-02-28

    申请号:US16672427

    申请日:2019-11-01

    IPC分类号: H04N5/378 H04N5/359

    摘要: Methods and systems for quantizing a physical quantity, such as light, are provided. In one example, an apparatus comprises an analog-to-digital (A/D) converter configured to generate raw digital outputs based on performing at least one of: (1) a first quantization operation to quantize a physical stimulus within a first intensity range based on a first A/D conversion relationship, or (2) a second quantization operation to quantize the physical stimulus within a second intensity range based on a second A/D conversion relationship; and a raw output conversion circuit configured generate a refined digital output based on a raw digital output obtained from the A/D converter and at least one predetermined conversion parameter. The at least one conversion parameter compensates for a discontinuity between the first A/D conversion relationship and the second A/D conversion relationship.

    Programmable smart sensor with adaptive readout

    公开(公告)号:US12075175B1

    公开(公告)日:2024-08-27

    申请号:US17469258

    申请日:2021-09-08

    IPC分类号: H04N25/75

    CPC分类号: H04N25/75

    摘要: In some examples, a sensor apparatus comprises: an array of pixel cells configured to generate a charge in response to light and convert the charge to output a voltage of an array of voltages, one or more an analog-to-digital converter (ADC) configured the convert the array of voltages to first pixel data comprising one or more pixel values, and an on-sensor controller configured to receive the first digital pixel data from the ADC, determine first pixel values and second pixel values, generate second digital pixel data comprising the first pixel values and not the second pixel values, and send the second digital pixel data off-sensor. The on-sensor controller may generate a control signal to alter the rate of charge generation by the array of pixel cells. The digital image data may be generated using a compressed map of pixels.

    Programmable pixel array having multiple power domains

    公开(公告)号:US11825228B2

    公开(公告)日:2023-11-21

    申请号:US17324803

    申请日:2021-05-19

    摘要: In some examples, an apparatus comprises an array of pixel cells, and processing circuits associated with blocks of pixel cells of the array of pixel cells and associated with first hierarchical power domains. The apparatus further includes banks of memory devices, each bank of memory devices being associated with a block of pixel cells, to store the quantization results of the associated block of pixel cells, the banks of memory devices further being associated with second hierarchical power domains. The apparatus further includes a processing circuits power state control circuit configured to control a power state of the processing circuits based on programming data targeted at each block of pixel cells and global processing circuits power state control signals, and a memory power state control circuit configured to control a power state of the banks of memory devices based on the programming data and global memory power state control signals.

    Object tracking using sparse sensor captures

    公开(公告)号:US11804010B2

    公开(公告)日:2023-10-31

    申请号:US18069896

    申请日:2022-12-21

    摘要: In one embodiment, a computing system instructs, at a first time, a camera having a plurality of pixel sensors to use the plurality of pixel sensors to capture a first image of an environment comprising an object. The computing system predicts, using at least the first image, a projection of the object appearing in a virtual image plane associated with a predicted camera pose at a second time. The computing system determines, based on the predicted projection of the object, a first region of pixels and a second region of pixels. The computing system generates pixel-activation instructions for the first region of pixels and the second region of pixels. The computing system instructs the camera to capture a second image of the environment at the second time according to the pixel-activation instructions. The pixel-activation instructions are configured to cause a first subset of the plurality of pixel sensors to sample the first region of pixels and a second subset of the plurality of pixel sensors to sample the second region of pixels. The first subset of the plurality of pixel sensors used for sampling the first region of pixels is more dense than the second subset of the plurality of pixel sensors used for sampling the second region of pixels. The computing system tracks, based on the second image, the object at the second time.

    ON-SENSOR IMAGE PROCESSOR UTILIZING CONTEXTUAL DATA

    公开(公告)号:US20230239582A1

    公开(公告)日:2023-07-27

    申请号:US18148834

    申请日:2022-12-30

    摘要: In some examples, a sensor apparatus comprises: an array of pixel cells each including one or more photodiodes configured to generate a charge in response to light, and a charge storage device to convert the charge to output a voltage of an array of voltages, one or more an analog-to-digital converter (ADC) configured the convert the array of voltages to first pixel data, and an on-sensor controller configured to input the first pixel data into a machine-learning model to generate output data comprising prediction data associated with one or more features of the first pixel data, generate, based on the prediction data, second pixel data, the second pixel data associated with one or more transformed features of the first pixel data, and send, from the sensor apparatus to a separate receiving apparatus, the second pixel data.

    Object tracking using sparse sensor captures

    公开(公告)号:US11562534B2

    公开(公告)日:2023-01-24

    申请号:US17541907

    申请日:2021-12-03

    摘要: In one embodiment, a method includes instructing, at a first time, a camera having a plurality of pixel sensors to capture a first image of an environment comprising an object to determine a first object pose; determining, based on the first object pose, a predicted object pose of the object at a second time; generating pixel-activation instructions based on a buffer region around a projection of a 3D model of the object having the predicted object pose onto a virtual image plane associated with a predicted camera pose, where the size of the buffer region may be dependent on predicted dynamics for the object; instructing, at the second time, the camera to use a subset of the plurality of pixel sensors to capture a second image of the environment according to the pixel-activation instructions, and; determining, based on the second image, a second object pose of the object.

    Pixel sensor having multiple photodiodes and shared comparator

    公开(公告)号:US11956413B2

    公开(公告)日:2024-04-09

    申请号:US16550851

    申请日:2019-08-26

    摘要: In one example, an apparatus comprises: a first photodiode to generate a first charge; a second photodiode to generate a second charge; a quantizer; a first memory bank and a second memory bank; and a controller configured to: control the quantizer to perform a first quantization operation and a second quantization operation of the first charge to generate, respectively, a first digital output and a second digital output, the first and second quantization operations being associated with different intensity ranges; store one of the first digital output or the second digital output in the first memory bank; control the quantizer to perform a third quantization operation of the second charge to generate a third digital output, the third quantization operation being associated with a different intensity range from at least one of the first or second quantization operations; and store the third digital output in the second memory bank.