Fault-Aware Matched Filter and Optical Flow
AssigneePrioria Robotics, Inc.
InventorWalter Lee Hunt
Life of this patent
Estimating the term…
Abstract
In one embodiment, a fault-aware matched filter augments the output of a component matched filter to provide both fault-aware matched filter output and a measure of confidence in the accuracy of the fault-aware matched filter output. In another embodiment, an optical flow engine derives, from a plurality of images, both optical flow output and a measure of confidence in the optical flow output. The measure of confidence may be derived using a fault-aware matched filter.
Claims12
A method performed by at least one computer processor, the method comprising:
- (A) receiving a first image input;
- (B) receiving a second image input;
- (C) receiving an image coregistration data set input defining a coregistration between the first image input and the second image input, wherein the image coregistration data set input includes a plurality of elements;
- (D) at the at least one computer processor, applying a filter to each of the plurality of elements of the image coregistration data set input and at least one of the first image input and the second image input, comprising:
- (1) deriving a match statistic map (MSM), wherein the MSM is a two-dimensional measure of similarity between the first image input and the second image input;
- (2) identifying a value PK1 representing a peak similarity response in the MSM;
- and
- (3) identifying a value PK2 representing a value in the MSM other than the peak similarity response in the MSM;
- and
- (E) at the at least one computer processor, generating, for each of the plurality of elements in the image coregistration data set input, a first corresponding confidence estimate metric based on the ratio PK1/PK2.
A non-transitory computer-readable medium comprising computer program instructions executable by at least one computer processor to perform a method, the method comprising:
- (A) receiving a first image input;
- (B) receiving a second image input;
- (C) receiving an image coregistration data set input defining a coregistration between the first image input and the second image input, wherein the image coregistration data set input includes a plurality of elements;
- (D) at the at least one computer processor, applying a filter to each of the plurality of elements of the image coregistration data set input and at least one of the first image input and the second image input, comprising:
- (1) deriving a match statistic map (MSM), wherein the MSM is a two-dimensional measure of similarity between the first image input and the second image input;
- (2) identifying a value PK1 representing a peak similarity response in the MSM;
- and
- (3) identifying a value PK2 representing a value in the MSM other than the peak similarity response in the MSM;
- and
- (E) at the at least one computer processor, generating, for each of the plurality of elements in the image coregistration data set input, a first corresponding confidence estimate metric based on the ratio PK1/PK2.
Dependencies are inferred from the claim text.