HARDWARE ACCELERATION MACHINE LEARNING AND IMAGE PROCESSING SYSTEM WITH ADD AND SHIFT OPERATIONS

    公开(公告)号:US20210326107A1

    公开(公告)日:2021-10-21

    申请号:US16903335

    申请日:2020-06-16

    Abstract: A system and a method are disclosed to approximately calculate a mathematical function using a digital processing device. An acceleration function is performed on at least one operand for a mathematical function. The acceleration function includes a predetermined sequence of addition operations that approximate the mathematical function in which the mathematical function may be a base-2 logarithm, a power of 2, a multiplication, an inverse square root, an inverse, a division, a square root, and an arctangent. The predetermined sequence of addition operations may include a first predetermined number of additions of integer-formatted operands and a second predetermined number of additions of floating-point-formatted operands in which the additions of integer-formatted operands and additions of floating-point-formatted operands can occur in any order.

    INCREASE DEPTH RESOLUTION AND DEPTH ACCURACY IN TOF SENSORS BY AVOIDING HISTOGRAMMIZATION

    公开(公告)号:US20200225353A1

    公开(公告)日:2020-07-16

    申请号:US16830254

    申请日:2020-03-25

    Abstract: A method is disclosed to determine a traveling time for a plurality of received light pulses that reflected and returned from an object. Each returned light pulse is associated with a timestamp indicating a time between a transmission time of a corresponding light pulse and a time of arrival of the returned light pulse. For each timestamp, a number C is determined of time stamps that are subsequent to the timestamp and within a predetermined time window after the timestamp. A maximum number C is determined, and an index i is determined for the maximum number C. A traveling time is determined for the plurality of light pulses as an average of the timestamp having a same index as the maximum number C and timestamps that are within the predetermined time window after the timestamp having the same index as the maximum number C.

    SUPER-RESOLUTION IN PROCESSING IMAGES SUCH AS FROM MULTI-LAYER SENSORS

    公开(公告)号:US20160292822A1

    公开(公告)日:2016-10-06

    申请号:US15181404

    申请日:2016-06-13

    Abstract: Pixels of an array capture values for an input image. The captured values correspond to pixel center points of the pixels that captured the values. Additional values about the input image may be further computed from the captured values. These additional values may correspond to additional center points, which can be different from any of the pixel center points. An output image may be constructed from the captured values plus the additional values. These values may be stored together and/or displayed together as the output image. Embodiments are applicable to images such as from multi-layer sensors. Since the output image can be created from a higher total number of values than those captured by the available number of pixels, such image processing can be called super-resolution, and can be applied to image processing within imaging devices, for still pictures, video and motion pictures, and so on.

    IMAGE SENSORS AND SYSTEMS WITH AN IMPROVED RESOLUTION
    16.
    发明申请
    IMAGE SENSORS AND SYSTEMS WITH AN IMPROVED RESOLUTION 审中-公开
    具有改进分辨率的图像传感器和系统

    公开(公告)号:US20150138412A1

    公开(公告)日:2015-05-21

    申请号:US14086965

    申请日:2013-11-21

    CPC classification number: H04N9/045

    Abstract: A device, comprising a plurality of pixel arrays. Two or more pixel arrays are stacked in overlapping fashion and rotated. Optionally, one or more of the pixel arrays are shifted with respect to others. As a result, the horizontal and vertical Nyquist spatial sampling frequency limits are increased, thus permitting an increase in image resolution, for example in terms of line pairs that can be resolved, without reducing the pixel size. Certain stacked pixel pattern arrangement can also be read out as Bayer color pattern for processing by traditional Bayer image signal processors.

    Abstract translation: 一种装置,包括多个像素阵列。 两个或更多个像素阵列以重叠的方式堆叠并旋转。 可选地,一个或多个像素阵列相对于其他像素阵列移位。 结果,水平和垂直奈奎斯特空间采样频率极限增加,从而允许增加图像分辨率,例如,在可以解决的线对上,而不减小像素尺寸。 某些堆叠的像素图案布置也可以被读出作为拜耳颜色图案,以便由传统的拜耳图像信号处理器进行处理。

    ULTRAFAST, ROBUST AND EFFICIENT DEPTH ESTIMATION FOR STRUCTURED-LIGHT BASED 3D CAMERA SYSTEM

    公开(公告)号:US20230116406A1

    公开(公告)日:2023-04-13

    申请号:US18080704

    申请日:2022-12-13

    Abstract: A system and a method are disclosed for a structured-light system to estimate depth in an image. An image is received in which the image is of a scene onto which a reference light pattern has been projected. The projection of the reference light pattern includes a predetermined number of particular sub-patterns. A patch of the received image and a sub-pattern of the reference light pattern are matched based on either a hardcode template matching technique or a probability that the patch corresponds to the sub-pattern. If a lookup table is used, the table may be a probability matrix, may contain precomputed correlations scores or may contain precomputed class IDs. An estimate of depth of the patch is determined based on a disparity between the patch and the sub-pattern.

    TIME-RESOLVING IMAGE SENSOR FOR RANGE MEASUREMENT AND 2D GREYSCALE IMAGING

    公开(公告)号:US20200033456A1

    公开(公告)日:2020-01-30

    申请号:US16140529

    申请日:2018-09-24

    Abstract: An image sensor includes a time-resolving sensor and a processor. The time-resolving sensor outputs a first signal and a second signal pair in response detecting one or more photons that have been reflected from an object. A first ratio of a magnitude of the first signal to a sum of the magnitude of the first signal and a magnitude of the second signal is proportional to a time of flight of the one or more detected photons. A second ratio of the magnitude of the second signal to the sum of the magnitude of the first signal and the magnitude of the second signal is proportional to the time of flight of the one or more detected photons. The processor determines a surface reflectance of the object where the light pulse has been reflected based on the first signal and the second signal pair and may generate a grayscale image.

    TIME-RESOLVING SENSOR USING SHARED PPD+SPAD PIXEL AND SPATIAL-TEMPORAL CORRELATION FOR RANGE MEASUREMENT

    公开(公告)号:US20190281276A1

    公开(公告)日:2019-09-12

    申请号:US16422944

    申请日:2019-05-24

    Abstract: A Time-of-Flight (TOF) technique is combined with analog amplitude modulation within each pixel in a pixel array using multiple Single Photon Avalanche Diodes (SPADs) in conjunction with a single Pinned Photo Diode (PPD) in each pixel. A SPAD may be shared among multiple neighboring pixels. The TOF information is added to the received light signal by the analog domain-based single-ended to differential converter inside the pixel itself. The spatial-temporal correlation among outputs of multiple, adjacent SPADs in a pixel is used to control the operation of the PPD to facilitate recording of TOF values and range of an object. Erroneous range measurements due to ambient light are prevented by stopping the charge transfer from the PPD—and, hence, recording a TOF value—only when two or more SPADs in the pixel are triggered within a pre-defined time interval. An autonomous navigation system with multi-SPAD pixels provides improved vision for drivers under difficult driving conditions.

Patent Agency Ranking