-
公开(公告)号：US11620757B2
公开(公告)日：2023-04-04
申请号：US17533256
申请日：2021-11-23
Applicant: TEXAS INSTRUMENTS INCORPORATED
Inventor： Hetul Sanghvi , Mihir Narendra Mody , Niraj Nandan , Anish Reghunath , Michael Peter Lachmayr
Abstract: A computer vision system is provided that includes an image generation device configured to generate consecutive two dimensional (2D) images of a scene, and a dense optical flow engine (DOFE) configured to determine a dense optical flow map for pairs of the consecutive 2D images, wherein, for a pair of consecutive 2D images, the DOFE is configured to perform a predictor based correspondence search for each paxel in a current image of the pair of consecutive 2D images, wherein, for an anchor pixel in each paxel, the predictor based correspondence search evaluates a plurality of predictors to select a best matching pixel in a reference image of the pair of consecutive 2D images, and determine optical flow vectors for each pixel in a paxel based on the best matching pixel selected for the anchor pixel of the paxel.
-
2.发明授权公开(公告)号：US10824877B2
公开(公告)日：2020-11-03
申请号：US15638142
申请日：2017-06-29
Applicant: Texas Instruments Incorporated
Inventor： Hetul Sanghvi , Mihir Narendra Mody , Niraj Nandan , Anish Reghunath , Michael Peter Lachmayr
Abstract: A computer vision system is provided that includes an image generation device configured to capture consecutive two dimensional (2D) images of a scene, a first memory configured to store the consecutive 2D images, a second memory configured to store a growing window of consecutive rows of a reference image and a growing window of consecutive rows of a current image, wherein the reference image and the current image are a pair of consecutive 2D images stored in the first memory, a third memory configured to store a sliding window of pixels fetched from the growing window of the reference image, wherein the pixels in the sliding window are stored in tiles, and a dense optical flow engine (DOFE) configured to determine a dense optical flow map for the pair of consecutive 2D images, wherein the DOFE uses the sliding window as a search window for pixel correspondence searches.
-
公开(公告)号：US20220084215A1
公开(公告)日：2022-03-17
申请号：US17533256
申请日：2021-11-23
Applicant: TEXAS INSTRUMENTS INCORPORATED
Inventor： Hetul Sanghvi , Mihir Narendra Mody , Niraj Nandan , Anish Reghunath , Michael Peter Lachmayr
Abstract: A computer vision system is provided that includes an image generation device configured to generate consecutive two dimensional (2D) images of a scene, and a dense optical flow engine (DOFE) configured to determine a dense optical flow map for pairs of the consecutive 2D images, wherein, for a pair of consecutive 2D images, the DOFE is configured to perform a predictor based correspondence search for each paxel in a current image of the pair of consecutive 2D images, wherein, for an anchor pixel in each paxel, the predictor based correspondence search evaluates a plurality of predictors to select a best matching pixel in a reference image of the pair of consecutive 2D images, and determine optical flow vectors for each pixel in a paxel based on the best matching pixel selected for the anchor pixel of the paxel.
-
公开(公告)号：US11182908B2
公开(公告)日：2021-11-23
申请号：US16585333
申请日：2019-09-27
Applicant: TEXAS INSTRUMENTS INCORPORATED
Inventor： Hetul Sanghvi , Mihir Narendra Mody , Niraj Nandan , Anish Reghunath , Michael Peter Lachmayr
Abstract: A computer vision system is provided that includes an image generation device configured to generate consecutive two dimensional (2D) images of a scene, and a dense optical flow engine (DOFE) configured to determine a dense optical flow map for pairs of the consecutive 2D images, wherein, for a pair of consecutive 2D images, the DOFE is configured to perform a predictor based correspondence search for each paxel in a current image of the pair of consecutive 2D images, wherein, for an anchor pixel in each paxel, the predictor based correspondence search evaluates a plurality of predictors to select a best matching pixel in a reference image of the pair of consecutive 2D images, and determine optical flow vectors for each pixel in a paxel based on the best matching pixel selected for the anchor pixel of the paxel.
-
5.发明授权公开(公告)号：US11682212B2
公开(公告)日：2023-06-20
申请号：US17086560
申请日：2020-11-02
Applicant: TEXAS INSTRUMENTS INCORPORATED
Inventor： Hetul Sanghvi , Mihir Narendra Mody , Niraj Nandan , Anish Reghunath , Michael Peter Lachmayr
CPC classification number: G06V20/52 , G06T1/0007 , G06T7/20 , G06T7/269 , G06V20/64 , G06T2200/28 , G06T2207/10004 , G06T2207/20016 , G06T2207/20032 , G06T2207/30252
Abstract: A computer vision system is provided that includes an image generation device configured to capture consecutive two dimensional (2D) images of a scene, a first memory configured to store the consecutive 2D images, a second memory configured to store a growing window of consecutive rows of a reference image and a growing window of consecutive rows of a current image, wherein the reference image and the current image are a pair of consecutive 2D images stored in the first memory, a third memory configured to store a sliding window of pixels fetched from the growing window of the reference image, wherein the pixels in the sliding window are stored in tiles, and a dense optical flow engine (DOFE) configured to determine a dense optical flow map for the pair of consecutive 2D images, wherein the DOFE uses the sliding window as a search window for pixel correspondence searches.
-
Patent Agency Ranking
公开(公告)号：US10467765B2
公开(公告)日：2019-11-05
申请号：US15638123
申请日：2017-06-29
Applicant: Texas Instruments Incorporated
Inventor： Hetul Sanghvi , Mihir Narendra Mody , Niraj Nandan , Anish Reghunath , Michael Peter Lachmayr
Abstract: A computer vision system is provided that includes an image generation device configured to generate consecutive two dimensional (2D) images of a scene, and a dense optical flow engine (DOFE) configured to determine a dense optical flow map for pairs of the consecutive 2D images, wherein, for a pair of consecutive 2D images, the DOFE is configured to perform a predictor based correspondence search for each paxel in a current image of the pair of consecutive 2D images, wherein, for an anchor pixel in each paxel, the predictor based correspondence search evaluates a plurality of predictors to select a best matching pixel in a reference image of the pair of consecutive 2D images, and determine optical flow vectors for each pixel in a paxel based on the best matching pixel selected for the anchor pixel of the paxel.
-
7.发明申请公开(公告)号：US20190005335A1
公开(公告)日：2019-01-03
申请号：US15638142
申请日：2017-06-29
Applicant: Texas Instruments Incorporated
Inventor： Hetul Sanghvi , Mihir Narendra Mody , Niraj Nandan , Anish Reghunath , Michael Peter Lachmayr
Abstract: A computer vision system is provided that includes an image generation device configured to capture consecutive two dimensional (2D) images of a scene, a first memory configured to store the consecutive 2D images, a second memory configured to store a growing window of consecutive rows of a reference image and a growing window of consecutive rows of a current image, wherein the reference image and the current image are a pair of consecutive 2D images stored in the first memory, a third memory configured to store a sliding window of pixels fetched from the growing window of the reference image, wherein the pixels in the sliding window are stored in tiles, and a dense optical flow engine (DOFE) configured to determine a dense optical flow map for the pair of consecutive 2D images, wherein the DOFE uses the sliding window as a search window for pixel correspondence searches.
-
8.发明申请公开(公告)号：US20210049368A1
公开(公告)日：2021-02-18
申请号：US17086560
申请日：2020-11-02
Applicant: TEXAS INSTRUMENTS INCORPORATED
Inventor： Hetul Sanghvi , Mihir Narendra Mody , Niraj Nandan , Anish Reghunath , Michael Peter Lachmayr
Abstract: A computer vision system is provided that includes an image generation device configured to capture consecutive two dimensional (2D) images of a scene, a first memory configured to store the consecutive 2D images, a second memory configured to store a growing window of consecutive rows of a reference image and a growing window of consecutive rows of a current image, wherein the reference image and the current image are a pair of consecutive 2D images stored in the first memory, a third memory configured to store a sliding window of pixels fetched from the growing window of the reference image, wherein the pixels in the sliding window are stored in tiles, and a dense optical flow engine (DOFE) configured to determine a dense optical flow map for the pair of consecutive 2D images, wherein the DOFE uses the sliding window as a search window for pixel correspondence searches.
-
公开(公告)号：US20200027219A1
公开(公告)日：2020-01-23
申请号：US16585333
申请日：2019-09-27
Applicant: TEXAS INSTRUMENTS INCORPORATED
Inventor： Hetul Sanghvi , Mihir Narendra Mody , Niraj Nandan , Anish Reghunath , Michael Peter Lachmayr
Abstract: A computer vision system is provided that includes an image generation device configured to generate consecutive two dimensional (2D) images of a scene, and a dense optical flow engine (DOFE) configured to determine a dense optical flow map for pairs of the consecutive 2D images, wherein, for a pair of consecutive 2D images, the DOFE is configured to perform a predictor based correspondence search for each paxel in a current image of the pair of consecutive 2D images, wherein, for an anchor pixel in each paxel, the predictor based correspondence search evaluates a plurality of predictors to select a best matching pixel in a reference image of the pair of consecutive 2D images, and determine optical flow vectors for each pixel in a paxel based on the best matching pixel selected for the anchor pixel of the paxel.
-
公开(公告)号：US20190005656A1
公开(公告)日：2019-01-03
申请号：US15638123
申请日：2017-06-29
Applicant: Texas Instruments Incorporated
Inventor： Hetul Sanghvi , Mihir Narendra Mody , Niraj Nandan , Anish Reghunath , Michael Peter Lachmayr
CPC classification number: G06T7/251 , G06T7/20 , G06T7/246 , G06T7/269 , G06T2207/10016 , G06T2207/10028 , G06T2207/30252 , G06T2207/30261
Abstract: A computer vision system is provided that includes an image generation device configured to generate consecutive two dimensional (2D) images of a scene, and a dense optical flow engine (DOFE) configured to determine a dense optical flow map for pairs of the consecutive 2D images, wherein, for a pair of consecutive 2D images, the DOFE is configured to perform a predictor based correspondence search for each paxel in a current image of the pair of consecutive 2D images, wherein, for an anchor pixel in each paxel, the predictor based correspondence search evaluates a plurality of predictors to select a best matching pixel in a reference image of the pair of consecutive 2D images, and determine optical flow vectors for each pixel in a paxel based on the best matching pixel selected for the anchor pixel of the paxel.
-
-
-
-
-
-
-
-
-
Search Results
10
records
(took 0.013 seconds)
