Methods, systems, and computer-readable storage media for generating three-dimensional (3D) images of a scene
Disclosed herein are methods, systems, and computer-readable storage media for generating three-dimensional (3D) images of a scene. According to an aspect, a method includes capturing a real-time image and a first still image of a scene. Further, the method includes displaying the real-time image of the scene on a display. The method also includes determining one or more properties of the captured images. The method also includes calculating an offset in a real-time display of the scene to indicate a target camera positional offset with respect to the first still image. Further, the method includes determining that a capture device is in a position of the target camera positional offset. The method also includes capturing a second still image. Further, the method includes correcting the captured first and second still images. The method also includes generating the three-dimensional image based on the corrected first and second still images.
1. An apparatus for continuously determining its relative three-dimensional position and orientation, the apparatus comprising:
at least one camera to continuously capture images from a scene;
at least one processor and memory configured to:
receive a first and second image from the camera at two different time instances, t1 and t2;
perform edge detection on the first and second images;
for each edge in the first image, match the closest edge in the second image, subject to meeting criteria for one of length, slope and curvature;
create a matrix that represents whether an edge in the first image is matched with every edge in the second image;
prune matrix so that no edge in the first image is matched with multiple edges in the second image;
solve a minimization problem via edge matching in order to determine the vertical and horizontal shift between the first and second images;
utilizing the matched edges, determine the focal axis of the first image with the respect to the second image;
utilizing the vertical shift, horizontal shift, and the focal axis between the first and second mages, determine the change in the three-dimensional position and orientation of the apparatus between captured times t1 and t2.
2. The apparatus of claim 1 , wherein the edge detection utilizes one of zero-cross or gradient-based operations.
3. The apparatus of claim 1 , whereas in case enough edges have not been found, utilize one of motion-estimation-based image matching, or quadrant-based, or full-image based cross correlation to determine similarity of pictures.
4. The apparatus of claim 1 , whereas edge extensions from slice boundaries are generated if enough edges have been found.
5. The apparatus of claim 1 , whereas determining the edges within the images by first considering edge segments that span a slice and then growing these edge segments to determine the exact edge size and endpoints.
6. The apparatus of claim 1 , whereas comparing and correlating one of the lengths, slope, curvature, midpoints/offset position, boundaries, and primary points of the resulting edges within the first and second images as an additional check of potential correspondence.
7. The apparatus of claim 1 , whereas testing each edge to determine if it intersects with a single image boundary. In the event of an edge intersecting a single image boundary, the primary point of the edge is classified as the endpoint, which is not on the boundary. Otherwise, the primary point is classified as the midpoint of the edge.
8. The apparatus of claim 1 , whereas Hough transformation is utilized to determine the dominant edges in a scene.
9. The apparatus of claim 1 , whereas in the event of multiple matches, the edge match with minimal distance is used.
10. The apparatus of claim 1 , whereas by examining the direction of the matched edge shifts of a subregion between the first and second image, a right and a left image is determined.
11. The apparatus of claim 1 , whereas rectification is performed on the first and second images.
12. The apparatus of claim 1 , whereas a slice-based edge locator function is applied for extracting edges from the first and second captured images.
13. The apparatus of claim 1 , whereas the edge count of the first and second images is compared to confirm the similarity of the first and second images.
14. The apparatus of claim 1 , whereas using the interest point set for the first image, motion estimation techniques and edge matching techniques is applied to find corresponding points in the second image.