Efficient sub-pixel disparity estimation for all sub-aperture images from densely sampled light field cameras

    公开(公告)号:US10832430B2

    公开(公告)日:2020-11-10

    申请号:US16463456

    申请日:2016-12-23

    申请人: INTEL CORPORATION

    摘要: A system for sub-pixel disparity estimation is described herein. The system includes a plenoptic camera, a memory, and a processor. The memory is configured to store imaging data. The processor is \coupled to the memory and the plenoptic camera. The processor is to obtain a plurality of sub-aperture views, select a subset of sub-aperture views as reference views for a disparity calculation, and calculate an integer disparity for the reference views. The processor is also to refine the integer disparity to sub-pixel disparity accuracy for the reference views and propagate the sub-pixel disparity from the reference views to other views of the plurality of sub-aperture views.

    METHOD AND APPARATUS TO IMPROVE SHARED MEMORY EFFICIENCY

    公开(公告)号:US20190042412A1

    公开(公告)日:2019-02-07

    申请号:US15757727

    申请日:2015-09-25

    申请人: Intel Corporation

    IPC分类号: G06F12/084

    摘要: Methods and apparatus to improve shared memory efficiency are described. In an embodiment, a first version of a code to access one or more registers as shared local memory is compiled. A second version of the same code is also compiled to access a cache as the shared local memory. The first version of the code is executed in response to comparison of a work group size of the code with a threshold value. Other embodiments are also disclosed and claimed.

    EFFICIENT SUB-PIXEL DISPARITY ESTIMATION FOR ALL SUB-APERTURE IMAGES FROM DENSELY SAMPLED LIGHT FIELD CAMERAS

    公开(公告)号:US20210035317A1

    公开(公告)日:2021-02-04

    申请号:US17072784

    申请日:2020-10-16

    申请人: Intel Corporation

    摘要: A system for sub-pixel disparity estimation is described herein. The system includes memory circuitry to store image data and at least one processor to execute instructions to calculate a first disparity for a set of reference views. The reference views correspond to a first subset of views among a plurality of sub-aperture views represented in the image data. The at least one processor is to refine the first disparity to a second disparity for the reference views. The second disparity has higher precision than the first disparity. The at least one processor is to map the second disparity from the reference views to a second subset of views among the plurality of sub-aperture views different than the first subset of views.

    EFFICIENT SUB-PIXEL DISPARITY ESTIMATION FOR ALL SUB-APERTURE IMAGES FROM DENSELY SAMPLED LIGHT FIELD CAMERAS

    公开(公告)号:US20190355139A1

    公开(公告)日:2019-11-21

    申请号:US16463456

    申请日:2016-12-23

    申请人: INTEL CORPORATION

    摘要: A system for sub-pixel disparity estimation is described herein. The system includes a plenoptic camera, a memory, and a processor. The memory is configured to store imaging data. The processor is \coupled to the memory and the plenoptic camera. The processor is to obtain a plurality of sub-aperture views, select a subset of sub-aperture views as reference views for a disparity calculation, and calculate an integer disparity for the reference views. The processor is also to refine the integer disparity to sub-pixel disparity accuracy for the reference views and propagate the sub-pixel disparity from the reference views to other views of the plurality of sub-aperture views.

    SEGMENTATION OF OBJECTS IN VIDEOS USING COLOR AND DEPTH INFORMATION

    公开(公告)号:US20170372479A1

    公开(公告)日:2017-12-28

    申请号:US15190784

    申请日:2016-06-23

    申请人: INTEL CORPORATION

    IPC分类号: G06T7/11 G06T7/136 G06T5/00

    摘要: Techniques are provided for segmentation of objects, in videos comprising a sequence of color and depth image frames. A methodology implementing the techniques according to an embodiment includes receiving image frames, including an initial reference frame, and receiving a mask to outline a region in the reference frame that contains the object to be segmented. The method also includes calculating Gaussian mixture models associated with both the masked region and a background region external to the masked region. The method further includes segmenting the object from a current frame based on a modelling of the pixels within an active area of the current frame as a Markov Random Field of nodes for cost minimization. The costs are based in part on the Gaussian mixture models. The active area is based on the segmentation of a previous frame and on an estimation of optical flow between the previous frame and the current frame.