Generating sparse sample histograms in image processing

    公开(公告)号:US12003871B2

    公开(公告)日:2024-06-04

    申请号:US18123269

    申请日:2023-03-18

    Inventor: Timothy Smith

    Abstract: Apparatus for binning an input value into an array of bins, each bin representing a range of input values and the bins collectively representing a histogram of input values, the apparatus comprising: an input for receiving the input value; a memory for storing the array; and a binning controller configured to: derive a plurality of bin values from the input value according to a binning distribution located about the input value, the binning distribution spanning a range of input values and each bin value having a respective input value dependent on the position of the bin value in the binning distribution; and allocate the plurality of bin values to a plurality of bins in the array, each bin value being allocated to a bin selected according to the respective input value of the bin value.

    Learned feature motion detection
    2.
    发明授权

    公开(公告)号:US11068703B2

    公开(公告)日:2021-07-20

    申请号:US16510509

    申请日:2019-07-12

    Inventor: Timothy Smith

    Abstract: A data processing device for detecting motion in a sequence of frames each comprising one or more blocks of pixels, includes a sampling unit configured to determine image characteristics at a set of sample points of a block, a feature generation unit configured to form a current feature for the block, the current feature having a plurality of values derived from the sample points, and motion detection logic configured to generate a motion output for a block by comparing the current feature for the block to a learned feature representing historical feature values for the block.

    Matching Local Image Feature Descriptors in Image Analysis

    公开(公告)号:US20210081704A1

    公开(公告)日:2021-03-18

    申请号:US17108145

    申请日:2020-12-01

    Abstract: A method of feature matching in images captured from camera viewpoints uses the epipolar geometry of the viewpoints to define a geometrically-constrained region in a second image corresponding to a first feature in a first image; comparing the local descriptor of the first feature with local descriptors of features in the second image to determine respective measures of similarity; identifying, from the features located in the geometrically-constrained region, (i) a geometric best match and (ii) a geometric next-best match to the first feature; identifying a global best match to the first feature; performing a first comparison of the measures of similarity for the geometric best match and the global best match; performing a second comparison of the measures of similarity for the geometric best match and the geometric next-best match; and, if thresholds are met, selecting the geometric best match feature in the second image.

    Learned feature motion detection
    5.
    发明授权

    公开(公告)号:US11676288B2

    公开(公告)日:2023-06-13

    申请号:US17346986

    申请日:2021-06-14

    Inventor: Timothy Smith

    Abstract: A data processing device for detecting motion in a sequence of frames each comprising one or more blocks of pixels, includes a sampling unit configured to determine image characteristics at a set of sample points of a block, a feature generation unit configured to form a current feature for the block, the current feature having a plurality of values derived from the sample points, and motion detection logic configured to generate a motion output for a block by comparing the current feature for the block to a learned feature representing historical feature values for the block.

    Camera calibration
    6.
    发明授权

    公开(公告)号:US10609281B2

    公开(公告)日:2020-03-31

    申请号:US15939504

    申请日:2018-03-29

    Inventor: Timothy Smith

    Abstract: A method of calibrating a camera performs a first calibration for frames of a sequence captured by the camera to calculate for those frames first calibration data for a set of one or more camera parameters; performs, for selected frames of the sequence, a second calibration to calculate second calibration data for the selected frames in dependence on the first calibration data for those frames; and uses the second calibration data in the first calibration performed for subsequent frames of the sequence.

    Learned Feature Motion Detection
    7.
    发明申请

    公开(公告)号:US20190332857A1

    公开(公告)日:2019-10-31

    申请号:US16510509

    申请日:2019-07-12

    Inventor: Timothy Smith

    Abstract: A data processing device for detecting motion in a sequence of frames each comprising one or more blocks of pixels, includes a sampling unit configured to determine image characteristics at a set of sample points of a block, a feature generation unit configured to form a current feature for the block, the current feature having a plurality of values derived from the sample points, and motion detection logic configured to generate a motion output for a block by comparing the current feature for the block to a learned feature representing historical feature values for the block.

    Learned feature motion detection
    8.
    发明授权

    公开(公告)号:US10395102B2

    公开(公告)日:2019-08-27

    申请号:US15468396

    申请日:2017-03-24

    Inventor: Timothy Smith

    Abstract: A data processing device for detecting motion in a sequence of frames each comprising one or more blocks of pixels, includes a sampling unit configured to determine image characteristics at a set of sample points of a block, a feature generation unit configured to form a current feature for the block, the current feature having a plurality of values derived from the sample points, and motion detection logic configured to generate a motion output for a block by comparing the current feature for the block to a learned feature representing historical feature values for the block.

    Generating Sparse Sample Histograms in Image Processing

    公开(公告)号:US20170280069A1

    公开(公告)日:2017-09-28

    申请号:US15468493

    申请日:2017-03-24

    Inventor: Timothy Smith

    Abstract: Apparatus for binning an input value into an array of bins, each bin representing a range of input values and the bins collectively representing a histogram of input values, the apparatus comprising: an input for receiving the input value; a memory for storing the array; and a binning controller configured to: derive a plurality of bin values from the input value according to a binning distribution located about the input value, the binning distribution spanning a range of input values and each bin value having a respective input value dependent on the position of the bin value in the binning distribution; and allocate the plurality of bin values to a plurality of bins in the array, each bin value being allocated to a bin selected according to the respective input value of the bin value.

Patent Agency Ranking