-
1.发明授权公开(公告)号：US11915431B2
公开(公告)日：2024-02-27
申请号：US16532658
申请日：2019-08-06
Applicant: TEXAS INSTRUMENTS INCORPORATED
Inventor： Deepak Kumar Poddar , Anshu Jain , Desappan Kumar , Pramod Kumar Swami
IPC: G06T7/246
CPC classification number: G06T7/246 , G06T2200/28 , G06T2207/20016 , G06T2207/30241
Abstract: A method for sparse optical flow based tracking in a computer vision system is provided that includes detecting feature points in a frame captured by a monocular camera in the computer vision system to generate a plurality of detected feature points, generating a binary image indicating locations of the detected feature points with a bit value of one, wherein all other locations in the binary image have a bit value of zero, generating another binary image indicating neighborhoods of currently tracked points, wherein locations of the neighborhoods in the binary image have a bit value of zero and all other locations in the binary image have a bit value of one, and performing a binary AND of the two binary images to generate another binary image, wherein locations in the binary image having a bit value of one indicate new feature points detected in the frame.
-
2.发明申请公开(公告)号：US20170193669A1
公开(公告)日：2017-07-06
申请号：US15266149
申请日：2016-09-15
Applicant: Texas Instruments Incorporated
Inventor： Deepak Kumar Poddar , Anshu Jain , Desappan Kumar , Pramod Kumar Swami
Abstract: A method for sparse optical flow based tracking in a computer vision system is provided that includes detecting feature points in a frame captured by a monocular camera in the computer vision system to generate a plurality of detected feature points, generating a binary image indicating locations of the detected feature points with a bit value of one, wherein all other locations in the binary image have a bit value of zero, generating another binary image indicating neighborhoods of currently tracked points, wherein locations of the neighborhoods in the binary image have a bit value of zero and all other locations in the binary image have a bit value of one, and performing a binary AND of the two binary images to generate another binary image, wherein locations in the binary image having a bit value of one indicate new feature points detected in the frame.
-
3.发明授权公开(公告)号：US10460453B2
公开(公告)日：2019-10-29
申请号：US15266149
申请日：2016-09-15
Applicant: Texas Instruments Incorporated
Inventor： Deepak Kumar Poddar , Anshu Jain , Desappan Kumar , Pramod Kumar Swami
IPC: G06T7/246
Abstract: A method for sparse optical flow based tracking in a computer vision system is provided that includes detecting feature points in a frame captured by a monocular camera in the computer vision system to generate a plurality of detected feature points, generating a binary image indicating locations of the detected feature points with a bit value of one, wherein all other locations in the binary image have a bit value of zero, generating another binary image indicating neighborhoods of currently tracked points, wherein locations of the neighborhoods in the binary image have a bit value of zero and all other locations in the binary image have a bit value of one, and performing a binary AND of the two binary images to generate another binary image, wherein locations in the binary image having a bit value of one indicate new feature points detected in the frame.
-
-
Search Results
3
records
(took 0.015 seconds)
