公开(公告)号：US10691952B2

公开(公告)日：2020-06-23

申请号：US16577515

申请日：2019-09-20

Applicant: QUALCOMM Incorporated

Inventor： Ran Tao ,  Efstratios Gavves ,  Arnold Wilhelmus Maria Smeulders

IPC: G06T7/246 ,  G06K9/32 ,  G06K9/00 ,  G06K9/46 ,  G06K9/62 ,  G06N3/04 ,  G06N3/08

Abstract: A method of tracking a position of a target object in a video sequence includes identifying the target object in a reference frame. A generic mapping is applied to the target object being tracked. The generic mapping is generated by learning possible appearance variations of a generic object. The method also includes tracking the position of the target object in subsequent frames of the video sequence by determining whether an output of the generic mapping of the target object matches an output of the generic mapping of a candidate object.

公开(公告)号：US10902615B2

公开(公告)日：2021-01-26

申请号：US16186391

申请日：2018-11-09

Applicant: QUALCOMM Incorporated

Inventor： Ran Tao ,  Efstratios Gavves ,  Arnold Smeulders

IPC: G06T7/246 ,  G06T7/73 ,  G06K9/62 ,  G06K9/00

Abstract: A method of tracking an object includes performing a hybrid search over a sequence of frames. The hybrid search includes periodically performing a global search on selected frames of the sequence of frames and performing a local search on frames between the selected frames of the global search. The method also includes updating a similarity function based on a result of the hybrid search. The method further includes tracking the object based on the hybrid search.

公开(公告)号：US10438068B2

公开(公告)日：2019-10-08

申请号：US16030685

申请日：2018-07-09

Applicant: QUALCOMM Incorporated

Inventor： Ran Tao ,  Efstratios Gavves ,  Arnold Wilhelmus Maria Smeulders

IPC: G06K9/00 ,  G06K9/32 ,  G06N3/04 ,  G06T7/246 ,  G06K9/46 ,  G06K9/62

Abstract: A method of tracking a position of a target object in a video sequence includes identifying the target object in a reference frame. A generic mapping is applied to the target object being tracked. The generic mapping is generated by learning possible appearance variations of a generic object. The method also includes tracking the position of the target object in subsequent frames of the video sequence by determining whether an output of the generic mapping of the target object matches an output of the generic mapping of a candidate object.

公开(公告)号：US10733755B2

公开(公告)日：2020-08-04

申请号：US16039133

申请日：2018-07-18

Applicant: QUALCOMM Incorporated

Inventor： Shuai Liao ,  Efstratios Gavves ,  Cornelis Gerardus Maria Snoek

IPC: G06K9/00 ,  G06T7/73 ,  G06T7/50 ,  G06N5/04 ,  G06N3/08 ,  G06T7/60 ,  G06T15/00 ,  G06N3/04 ,  G06T7/33 ,  G06K9/62 ,  G06K9/46 ,  G06T7/194

Abstract: A method aligns, with an artificial neural network, a three-dimensional (3D) model to an object in a 2D image. The method includes detecting, with an object detector, the object from the 2D image. The method also includes estimating a geodesic distance value between the object and multiple discretized poses of the 3D model. The method further includes selecting a discretized pose of the multiple discretized poses corresponding to a smallest geodesic distance value. The method still further includes propagating pose parameters of the selected discretized pose of the 3D model to the object.

公开(公告)号：US10049279B2

公开(公告)日：2018-08-14

申请号：US15267621

申请日：2016-09-16

Applicant: QUALCOMM Incorporated

Inventor： Zhenyang Li ,  Efstratios Gavves ,  Mihir Jain ,  Cornelis Gerardus Maria Snoek

IPC: G06K9/00 ,  G06K9/62 ,  G06N3/04

Abstract: A method of predicting action labels for a video stream includes receiving the video stream and calculating an optical flow of consecutive frames of the video stream. An attention map is generated from the current frame of the video stream and the calculated optical flow. An action label is predicted for the current frame based on the optical flow, a previous hidden state and the attention map.

公开(公告)号：US10019631B2

公开(公告)日：2018-07-10

申请号：US15192935

申请日：2016-06-24

Applicant: QUALCOMM Incorporated

Inventor： Ran Tao ,  Efstratios Gavves ,  Arnold Wilhelmus Maria Smeulders

IPC: G06K9/00 ,  G06T7/20

CPC classification number: G06K9/00758 ,  G06K9/3241 ,  G06K9/4628 ,  G06K9/6234 ,  G06K2009/3291 ,  G06N3/04 ,  G06N3/0454 ,  G06N3/08 ,  G06T7/246 ,  G06T7/248 ,  G06T2207/10016 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: A method of tracking a position of a target object in a video sequence includes identifying the target object in a reference frame. A generic mapping is applied to the target object being tracked. The generic mapping is generated by learning possible appearance variations of a generic object. The method also includes tracking the position of the target object in subsequent frames of the video sequence by determining whether an output of the generic mapping of the target object matches an output of the generic mapping of a candidate object.

公开(公告)号：US09830709B2

公开(公告)日：2017-11-28

申请号：US15249280

申请日：2016-08-26

Applicant: QUALCOMM Incorporated

Inventor： Zhenyang Li ,  Efstratios Gavves ,  Mihir Jain ,  Cornelis Gerardus Maria Snoek

IPC: G06K9/62 ,  G06T7/00 ,  G06N3/04 ,  G06N3/08

CPC classification number: G06T7/11 ,  G06K9/00335 ,  G06K9/00718 ,  G06N3/0445 ,  G06N3/0454 ,  G06N3/08 ,  G06T7/0081 ,  G06T2207/10004 ,  G06T2207/20084

Abstract: A method of processing data within a convolutional attention recurrent neural network (RNN) includes generating a current multi-dimensional attention map. The current multi-dimensional attention map indicates areas of interest in a first frame from a sequence of spatio-temporal data. The method further includes receiving a multi-dimensional feature map. The method also includes convolving the current multi-dimensional attention map and the multi-dimensional feature map to obtain a multi-dimensional hidden state and a next multi-dimensional attention map. The method identifies a class of interest in the first frame based on the multi-dimensional hidden state and training data.