LEARNING BASED BAD PIXEL CORRECTION
    2.
    发明公开

    公开(公告)号:US20230316471A1

    公开(公告)日:2023-10-05

    申请号:US17657171

    申请日:2022-03-30

    Abstract: Methods and apparatuses for correcting bad image pixels are described. The described sensor-independent image processing techniques leverage one or more dynamic dictionaries of learned filters for bad pixel correction (e.g., where a camera leverages such dictionaries to efficiently identify filters to accurately adjust and correct bad pixel values). For example, a dictionary may store filters that are learned offline (via a self-supervised learning algorithm implemented at a server using known images and ground truth bad pixel correction values). To select a filter for a bad pixel correction operation, a camera may encode an image patch surrounding a bad pixel (into an encoded patch descriptor) and search the dictionary for a matching patch descriptor key. The camera may then apply the filter (value) corresponding to the searched patch descriptor (key) of the dictionary to the image patch to correct the bad pixel and generate a corrected output image.

    IMAGE SENSOR DOWN-UP SAMPLING USING A COMPRESSED GUIDE

    公开(公告)号:US20210377497A1

    公开(公告)日:2021-12-02

    申请号:US16888291

    申请日:2020-05-29

    Abstract: A method for down-up sampling of image sensor data includes the steps of down sampling green pixels in a super Bayer pattern of image sensor data, where a decimation factor of the downsampling corresponds to a size of a color cluster in the super Bayer pattern, where two green pixels that are those closest to a non-green pixel cluster remain in each green cluster after downsampling, and wherein each non-green pixel cluster is bordered by four downsampled green pixels, and up sampling non-green color pixels in a non-green cluster from the remaining green pixels that are closest to the non-green cluster by a bilinear interpolation of each non-green pixel with respect to the closest remaining green pixels, where the up sampling of the non-green color pixels is guided by a compressed array that corresponds to the image sensor data.

    TIME-OF-FLIGHT DEPTH MEASUREMENT USING MODULATION FREQUENCY ADJUSTMENT

    公开(公告)号:US20200349728A1

    公开(公告)日:2020-11-05

    申请号:US16401285

    申请日:2019-05-02

    Abstract: In a method for time-of-flight (ToF) based measurement, a scene is illuminated using a ToF light source modulated at a first modulation frequency FMOD(1). While the light is modulated using FMOD(1), depths are measured to respective surface points within the scene, where the surface points are represented by a plurality of respective pixels. At least one statistical distribution parameter is computed for the depths. A second modulation frequency FMOD(2) higher than FMOD(1) is determined based on the at least one statistical distribution parameter. The depths are then re-measured using FMOD(2) to achieve a higher depth accuracy.

    HDR IMAGE SENSOR WITH LFM AND REDUCED MOTION BLUR

    公开(公告)号:US20200092459A1

    公开(公告)日:2020-03-19

    申请号:US16135647

    申请日:2018-09-19

    Abstract: An HDR image sensor supporting LED Flicker Mitigation to reduce Motion Blur and a method of operating same are provided. A timing controller circuit generates at least one control signal that controls an operation of the image sensor. A split-photodiode (PD) pixel includes at least two or more photodiodes that may be independently exposed to one or more bursts of light from a light source. A first photodiode of the two or more photodiodes has a first exposure period that is longer in duration than a second exposure period of a second photodiode of the two or more photodiodes. The second photodiode performs a fragmented exposure operation in which a plurality of exposure periods of the second photodiode are shorter in duration than the first exposure period of the first photodiode, and include both continuous and fragmented exposure periods to capture the one or more bursts of light.

    Hardware disparity evaluation for stereo matching

    公开(公告)号:US10529085B2

    公开(公告)日:2020-01-07

    申请号:US15941721

    申请日:2018-03-30

    Abstract: A method for calculating disparity in a pair of images includes receiving a first image of a scene and designating the first image as a master image. A second image of the scene is received, and the second image is designated as a slave image. The master image is binarized to produce a binarized master image. The slave image is binarized to produce a binarized slave image. A matching cost associated with matching each pixel within the binarized master image with a corresponding set of candidate pixels within the binarized slave image is calculated. A probability density function is created based on the calculated matching costs associated with each pixel within the binarized master image. The created probability density function is used to produce a disparity for the master image and the slave image and to produce a confidence for the produced disparity.

Patent Agency Ranking