Range reconstruction using shape prior

    公开(公告)号:US10775501B2

    公开(公告)日:2020-09-15

    申请号:US15611041

    申请日:2017-06-01

    Abstract: Arrangements (e.g., apparatus, system, method, article of manufacture) for reconstructing a depth image of a scene. Some embodiments include: a processor; and a non-transitory computer readable medium to store a set of instructions for execution by the processor, the set of instructions to cause the processor to perform various operations. Operations include: collecting multiple data sets for a code-modulated light pulse reflected from an object in a scene, with each data set associated with a direction in a set of directions for the reflected code-modulated light pulse; assigning a fitness value to each data set based on one or more parameters of a model; and reconstructing a depth image providing a depth at each direction based on a corresponding data set and fitness value, the depth to correspond with a round-trip delay time of the code-modulated light pulse.

    Systems, methods, and apparatuses for implementing maximum likelihood image binarization in a coded light range camera

    公开(公告)号:US09952036B2

    公开(公告)日:2018-04-24

    申请号:US14934599

    申请日:2015-11-06

    Abstract: In accordance with disclosed embodiments, there are provided systems, methods, and apparatuses for implementing maximum likelihood image binarization in a coded light range camera. For instance, a depth camera is described having therein a projector to project a collection of planes, each at a different angle of projection, onto a scene via a plurality of coded pattern images, each of the coded pattern images having encoded therein via a plurality of stripes, the angle of projection for the plane of projection within which the respective coded pattern image is projected; a detector to capture the plurality of coded pattern images from the scene; a processing component to output a bit value for each pixel in the captured plurality of coded pattern images based on the pixel captured and based further on a patch of neighboring pixels surrounding the pixel; a decoder to decode each of the plurality of coded pattern images based on the bit values output by the processing component to determine the angle of projection for the corresponding plane of projection; and a triangulator to determine a position of an object in the scene based on an intersection of the determined angle of projection for the corresponding plane of projection with a geometric ray originating from the detector that detected the plurality of the coded pattern images. Other related embodiments are disclosed.

Patent Agency Ranking