公开(公告)号：US10475186B2

公开(公告)日：2019-11-12

申请号：US15190784

申请日：2016-06-23

Applicant: INTEL CORPORATION

Inventor： Gowri Somanath ,  Jiajie Yao ,  Yong Jiang

IPC: G06K9/00 ,  G06T7/11 ,  G06T7/136 ,  G06T7/143 ,  G06T7/174

Abstract: Techniques are provided for segmentation of objects in video 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.

公开(公告)号：US20180137625A1

公开(公告)日：2018-05-17

申请号：US15566656

申请日：2015-05-14

Applicant: INTEL CORPORATION

Inventor： Gowri Somanath ,  Jiajie Yao ,  Yong Jiang

IPC: G06T7/143 ,  G06T7/11 ,  G06K9/46

CPC classification number: G06T7/143 ,  G06K9/4638 ,  G06T7/11 ,  G06T7/136 ,  G06T7/162 ,  G06T2200/04 ,  G06T2207/10024 ,  G06T2207/10028 ,  G06T2207/20072 ,  G06T2207/20076 ,  H04N2013/0092

Abstract: Image scene labeling with 3D image data. A plurality of pixels of an image frame may be label based at least on a function of pixel color and a pixel depth over the spatial positions within the image frame. A graph-cut technique may be utilized to optimize a data cost and neighborhood cost in which at least the data cost function includes a component that is a dependent on a depth associated with a given pixel in the frame. In some embodiments, in the MRF formulation pixels are adaptively merged into pixel groups based on the constructed data cost(s) and neighborhood cost(s). These pixel groups are then made nodes in the directed graphs. In some embodiments, a hierarchical expansion is performed, with the hierarchy set up within the label space.

公开(公告)号：US09699380B2

公开(公告)日：2017-07-04

申请号：US14931369

申请日：2015-11-03

Applicant: INTEL CORPORATION

Inventor： Gowri Somanath ,  Christos G. Bampis

IPC: H04N5/232 ,  H04N13/02 ,  G06T3/00 ,  G06T11/60 ,  G06T7/00

CPC classification number: H04N5/23238 ,  G06T3/4038 ,  G06T7/11 ,  G06T7/194 ,  G06T7/215 ,  G06T7/33 ,  G06T7/37 ,  G06T11/60 ,  G06T2207/10004 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/10028 ,  G06T2207/20152 ,  G06T2207/20221 ,  H04N13/15 ,  H04N13/207 ,  H04N13/257 ,  H04N13/271 ,  H04N2013/0092

Abstract: Techniques are provided for fusion of image frames to generate panoramic background images using color and depth data provided from a 3D camera. An example system may include a partitioning circuit configured to partition an image frame into segments and objects, the segments comprising a group of pixels sharing common features associated with the color and depth data, the objects comprising one or more related segments. The system may also include an object consistency circuit configured to assign either 2D or 3D transformation types to each of the segments and objects to transform them to a co-ordinate system of a reference image frame. The system may further include a segment recombination circuit to combine the transformed objects and segments into a transformed image frame and an integration circuit to integrate the transformed image frame with the reference image frame to generate the panoramic image.