Dynamic calibration method for single and multiple video capture devices
First Claim
1. A dynamic calibration method for video capture device, comprising:
- providing at least one video capture device for capturing at least one initial image;
panning or tilting said video capture device for capturing at least one successive image with different angles;
extracting at least one initial feature point from said initial image, and extracting at least one feature point from said successive image, wherein said feature point is corresponding to said initial feature point;
acquiring variations of a pan angle and a tilt angle of said video capture device according to the displacement between said initial feature point and said feature point;
wherein the step of acquiring the variations of said pan angle and said tilt angle of said video capture device further comprises;
back-projecting said initial feature point onto a pseudo plane to form a corresponding pseudo point; and
searching a pose of said video capture device so as to back project said feature point to said pseudo point on said pseudo plane.
1 Assignment
0 Petitions
Accused Products
Abstract
The present invention discloses a dynamic calibration method for a single and multiple video capture devices. The present invention can acquire the variations of the pan angle and tilt angle of a single video capture device according to the displacement of the feature points between successive images. For a plurality of video capture devices, the present invention includes the epipolar-plane constraint between a plurality of video capture devices to achieve the goal of dynamical calibration. The calibration method in the present invention does not require specific calibration patterns or complicated correspondence of feature points, and can be applied to surveillance systems with wide-range coverage.
-
Citations
6 Claims
-
1. A dynamic calibration method for video capture device, comprising:
-
providing at least one video capture device for capturing at least one initial image; panning or tilting said video capture device for capturing at least one successive image with different angles; extracting at least one initial feature point from said initial image, and extracting at least one feature point from said successive image, wherein said feature point is corresponding to said initial feature point; acquiring variations of a pan angle and a tilt angle of said video capture device according to the displacement between said initial feature point and said feature point;
wherein the step of acquiring the variations of said pan angle and said tilt angle of said video capture device further comprises;back-projecting said initial feature point onto a pseudo plane to form a corresponding pseudo point; and searching a pose of said video capture device so as to back project said feature point to said pseudo point on said pseudo plane. - View Dependent Claims (2, 3, 4, 5, 6)
-
Specification