CONFIDENCE ESTIMATION FOR OPITCAL FLOW
First Claim
Patent Images
1. A method of confidence estimation for optical flow comprising the steps of:
- computing a set of features for each pixel of an input image, where the features include image features, matching costs and flow features or flow gradient features;
computing smoothed versions of said features;
constructing a feature vector for each pixel of the input image;
computing a classifier score from said features by employing a set of decision tree classifiers;
converting the classifier score into a confidence score.
1 Assignment
0 Petitions
Accused Products
Abstract
A confidence map for optical flow gradients is constructed calculating a set of gradients for each pixel of an image, filtering said gradients and extracting confidence values from said gradients using a plurality of decision tree classifiers. A confidence map is then generated from said confidence values.
13 Citations
10 Claims
-
1. A method of confidence estimation for optical flow comprising the steps of:
-
computing a set of features for each pixel of an input image, where the features include image features, matching costs and flow features or flow gradient features; computing smoothed versions of said features; constructing a feature vector for each pixel of the input image; computing a classifier score from said features by employing a set of decision tree classifiers; converting the classifier score into a confidence score. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9)
-
-
10. An apparatus for confidence estimation for optical flow comprising of:
A processor operable to compute a set of features for each pixel of an input image; compute a smoothed version of said features; construct a feature vector from said features; construct a confidence map from said feature vector.
Specification