-
公开(公告)号：US20190244051A1
公开(公告)日：2019-08-08
申请号：US16386723
申请日：2019-04-17
Applicant: TEXAS INSTRUMENTS INCORPORATED
Inventor： Anish Reghunath , Hetul Sanghvi , Michael Lachmayr , Mihir Mody
CPC classification number: G06K9/4642 , G06K9/00791 , G06K9/4661 , G06K9/481 , G06K9/52 , G06K9/6202
Abstract: Systems and methods for performing Census Transforms that includes an input from an image, with a support window created within the image, and a kernel within the support window. The Census Transform calculations and comparisons are performed within the kernel windows. A new Census Transform is disclosed which always inverts a previously made comparison. This new approach can be demonstrated to be equivalent to, applying the original Census Transform, on a pre-processed input kernel, where the pre-processing step adds a fractional position index to each pixel within the N×N kernel. The fractional positional index ensures that no two pixels are equal to one another, and thereby makes the Original Census algorithm on pre-processed kernel same as the new Census algorithm on original kernel. The hardware design for this new Census Transform kernel allows for an always invert of previous comparison system resulting in reduced hardware and power consumption.
-
公开(公告)号：US10515288B2
公开(公告)日：2019-12-24
申请号：US16386723
申请日：2019-04-17
Applicant: TEXAS INSTRUMENTS INCORPORATED
Inventor： Anish Reghunath , Hetul Sanghvi , Michael Lachmayr , Mihir Mody
Abstract: Systems and methods for performing Census Transforms that includes an input from an image, with a support window created within the image, and a kernel within the support window. The Census Transform calculations and comparisons are performed within the kernel windows. A new Census Transform is disclosed which always inverts a previously made comparison. This new approach can be demonstrated to be equivalent to, applying the original Census Transform, on a pre-processed input kernel, where the pre-processing step adds a fractional position index to each pixel within the N×N kernel. The fractional positional index ensures that no two pixels are equal to one another, and thereby makes the Original Census algorithm on pre-processed kernel same as the new Census algorithm on original kernel. The hardware design for this new Census Transform kernel allows for an always invert of previous comparison system resulting in reduced hardware and power consumption.
-
公开(公告)号：US10325174B2
公开(公告)日：2019-06-18
申请号：US15707695
申请日：2017-09-18
Applicant: TEXAS INSTRUMENTS INCORPORATED
Inventor： Anish Reghunath , Hetul Sanghvi , Michael Lachmayr , Mihir Mody
Abstract: Systems and methods for performing Census Transforms that includes an input from an image, with a support window created within the image, and a kernel within the support window. The Census Transform calculations and comparisons are performed within the kernel windows. One disclosed method allows for previously performed comparison to be calculated and compared as an if not equal invert or if equal use pervious comparison hardware design. Alternatively, a new Census Transform is disclosed which always inverts a previously made comparison. This new approach can be demonstrated to be equivalent to, applying the original Census Transform, on a pre-processed input kernel, where the pre-processing step adds a fractional position index to each pixel within the N×N kernel. The fractional positional index ensures that no two pixels are equal to one another, and thereby makes the Original Census algorithm on pre-processed kernel same as the new Census algorithm on original kernel. The hardware design for this new Census Transform kernel allows for an always invert of previous comparison system resulting in reduced hardware and power consumption.
-
公开(公告)号：US20190087681A1
公开(公告)日：2019-03-21
申请号：US15707695
申请日：2017-09-18
Applicant: TEXAS INSTRUMENTS INCORPORATED
Inventor： Anish Reghunath , Hetul Sanghvi , Michael Lachmayr , Mihir Mody
Abstract: Systems and methods for performing Census Transforms that includes an input from an image, with a support window created within the image, and a kernel within the support window. The Census Transform calculations and comparisons are performed within the kernel windows. One disclosed method allows for previously performed comparison to be calculated and compared as an if not equal invert or if equal use pervious comparison hardware design. Alternatively, a new Census Transform is disclosed which always inverts a previously made comparison. This new approach can be demonstrated to be equivalent to, applying the original Census Transform, on a pre-processed input kernel, w here the pre-processing step adds a fractional position index to each pixel within the N×N kernel. The fractional positional index ensures that no two pixels are equal to one another, and thereby makes the Original Census algorithm on pre-processed kernel same as the new Census algorithm on original kernel. The hardware design for this new Census Transform kernel allows for an always invert of previous comparison system resulting in reduced hardware and power consumption.
-
-
-
Search Results
4
records
(took 0.01 seconds)
