IP Library Granted Patent US 7,995,067
Granted Patent B2
US 7,995,067 · App. 11/692,941 · Granted Aug 9, 2011

Cyclical image buffer

View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 7,995,067
App. No.
11/692,941
Granted
Aug 9, 2011
Kind
B2
Abstract

A storage buffer attached to an image processor for stereo image processing. The processor compares a first image and a second image. The storage buffer stores image data of the second image. The storage buffer includes: a data-shifting-hardware mechanism which while the processor compares a patch of the first image to a swath of the second image, the data shifting mechanism using hardware within the storage buffer shifts at least a portion of the swath within the storage buffer. The data-shifting hardware mechanism includes preferably digital multiplexers with respective selectable inputs from adjacent and non-adjacent columns of data within the storage buffer and selectable inputs from adjacent rows of data within the storage buffer.

Claims (17)

1. In a system including an image processor attached to a storage buffer wherein the storage buffer includes a plurality of n columns of data, said columns numbered from zero to N, wherein N is greater than 1, a method for comparison between first image data and second image data, the method comprising the steps of:

(a) comparing a patch of the first image data to a swath of the second image data, the storage buffer storing the swath of the second image data; and

(b) during said comparing, shifting of said swath using a hardware mechanism within the storage buffer, wherein said shifting includes upon each clock cycle of the processor:

(i) moving the data stored in column one into column N; and

(ii) moving the data stored in each of the n columns from column n into column n−1.

2. The method according to claim 1 , wherein the storage buffer includes a plurality of columns of data, said columns numbered from zero to N, wherein for said patch said comparing to said swath is performed M times, wherein M is less than N, further comprising the step of:

(c) upon completing said comparing to said swath, moving at least N−M+1 columns of data in a single step.

3. The method according to claim 1 , further comprising the step of:

(c) upon completing said comparing to said swath, second shifting into the storage buffer a portion of the second image data, wherein said second shifting is performed from a second storage buffer using a second hardware mechanism into the storage buffer thereby completing a second swath in the storage buffer.

4. The method according to claim 3 , wherein said second storage buffer includes no more than two columns of second image data, the height of said columns being equal to the height of said swath.

5. A storage buffer attached to a processor, wherein the processor compares a first image and a second image, the storage buffer storing image data of the second image, wherein the storage buffer includes a plurality of n columns of data, said columns numbered from zero to N, wherein N is greater than 1, the storage buffer comprising:

(a) a data-shifting-hardware mechanism which while the processor compares a patch of the first image to a swath of the second image, the data shifting mechanism using hardware within the storage buffer shifts at least a portion of the swath within the storage buffer wherein said data-shifting-hardware mechanism which upon each clock cycle of the processor:

(i) moves the data stored in column one into column N; and

(ii) moves the data stored in each of the n columns from column n into column n−1.

6. The storage buffer of claim 5 , wherein the data-shifting hardware mechanism includes a plurality of digital multiplexers with respective selectable inputs from adjacent columns of data within the storage buffer.

7. The storage buffer of claim 6 , wherein said digital multiplexers include a plurality of respective selectable inputs from adjacent rows of data within the storage buffer.

8. The storage buffer of claim 6 , wherein said digital multiplexers include a plurality of respective selectable inputs from at least one non-adjacent columns of data within the storage buffer.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 2, 2014
From: MOBILEYE TECHNOLOGIES LIMITED
To: MOBILEYE VISION TECHNOLOGIES LTD.
Reel/Frame 034305/0993 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 29, 2007
From: NAVON, MOIS
To: MOBILEYE TECHNOLOGIES LTD.
Reel/Frame 019080/0900 →