Adjusting perspective and disparity in stereoscopic image pairs
A system and method for adjusting perspective and disparity in a stereoscopic image pair using range information includes receiving the stereoscopic image pair representing a scene; identifying range information associated with the stereoscopic image pair and including distances of pixels in the scene from a reference location; generating a cluster map based at least upon an analysis of the range information and the stereoscopic images, the cluster map grouping pixels of the stereoscopic images by their distances from a viewpoint; identifying objects and background in the stereoscopic images based at least upon an analysis of the cluster map and the stereoscopic images; generating a new stereoscopic image pair at least by adjusting perspective and disparity of the object and the background in the stereoscopic image pair, the adjusting occurring based at least upon an analysis of the range information; and storing the new generated stereoscopic image pair in a processor-accessible memory system.
1. A method comprising:
receiving a stereoscopic image pair representing a scene;
identifying range information associated with the stereoscopic image pair, wherein the range information includes distances of pixels in the scene from a reference location;
generating a cluster map based at least upon an analysis of the range information using a clustering algorithm, wherein the cluster map groups pixels of the stereoscopic images by distances from a viewpoint;
identifying objects and background in the stereoscopic image pair based at least upon an analysis of the cluster map and the stereoscopic image pair wherein the analysis of the cluster map and the stereoscopic image pair includes:
identifying edges in the stereoscopic image pair ; and
refining pixel groupings in the cluster map by comparing the identified edges with borders of the pixel groupings and removing pixels that are outside of the identified edges from the pixel groupings;
generating a new stereoscopic image pair by adjusting perspective and disparity for at least one of the identified objects or the background in the stereoscopic image pair, wherein the adjusting occurs based at least upon the range information; and
storing the new stereoscopic image pair in a processor-accessible memory system.
2. The method of claim 1 , wherein the perspective and disparity adjustment is responsive to a user-preference input.
3. The method of claim 1 , further comprising filtering the identified edges to remove insignificant edges prior to the comparing the identified edges with borders of the pixel groupings.
4. The method of claim 1 , wherein the range information is identified at least from an analysis of the stereoscopic image pair.
5. The method of claim 1 , wherein a magnitude of the perspective and disparity adjustment is responsive to a distance of the object from a viewpoint location.
6. The method of claim 5 , wherein the viewpoint location is the reference location.
7. The method of claim 1 , wherein the analysis of the cluster map comprises reducing noise from the cluster map.
8. The method of claim 7 , wherein the reducing of noise from the cluster map fills small holes and removes small clustered regions from the cluster map.
9. A non-transitory computer-readable medium having instructions store thereon that upon execution by a computing device cause the computing device to perform a method comprising:
receiving a stereoscopic image pair representing a scene;
identifying range information associated with the stereoscopic image pair, wherein the range information includes distances of pixels in the scene from a reference location;
generating a cluster map based at least upon an analysis of the range information using a clustering algorithm, wherein the cluster map groups pixels of the stereoscopic images by distances from a viewpoint;
identifying objects and background in the stereoscopic image pair based at least upon an analysis of the cluster map and the stereoscopic image pair, wherein the analysis of the cluster map and the stereoscopic image pair includes:
identifying edges in the stereoscopic image pair: and
refining pixel groupings in the cluster map by comparing the identified edges with borders of the pixel groupings and removing pixels that are outside of the identified edges from the pixel groupings:
generating a new stereoscopic image pair by adjusting perspective and disparity for at least one of the identified objects or the background in the stereoscopic image pair, wherein the adjusting occurs based at least upon the range information: and
storing the new stereoscopic image pair in a processor-accessible memory system.
10. The non-transitory computer-readable medium of claim 9 , wherein the perspective and disparity adjustment is responsive to a user-preference input.
11. The non-transitory computer-readable medium of claim 9 , wherein the memory system further comprises instructions to filter the identified edges to remove insignificant edges prior to comparing the identified edges with borders of the pixel groupings.
12. The non-transitory computer-readable medium of claim 9 , wherein a magnitude of the perspective and disparity adjustment is responsive to a distance of the object from a viewpoint location.
13. The non-transitory computer-readable medium of claim 12 , wherein the viewpoint location is the reference location.
14. The non-transitory computer-readable medium of claim 9 , wherein the instructions to identify objects and background in the stereoscopic image pair comprise instructions to reduce noise from the cluster map.
15. The non-transitory computer-readable medium of claim 14 , wherein the reducing of noise from the cluster map fills small holes and removes small clustered regions from the cluster map.
16. A system comprising:
a data processing system; and
a memory system communicatively connected to the data processing system and storing instructions configured to cause the data processing system to implement a method for adjusting perspective and disparity in a stereoscopic image pair, wherein the instructions comprise:
instructions to receive the stereoscopic image pair representing a scene;
identifying instructions to identify range information associated with the stereoscopic image pair, wherein the range information includes distances of pixels in the scene from a reference location;
instructions to generate a cluster map based at least upon an analysis of the range information using a clustering algorithm, wherein the cluster map groups pixels of the stereoscopic images by distances from a viewpoint;
instructions to identify objects and background in the stereoscopic image pair based at least upon an analysis of the cluster map and the stereoscopic image pair, wherein the analysis of the cluster map and the stereoscopic image pair includes:
identifying edges in the stereoscopic pair; and
refining the pixel groupings in the cluster map by comparing the identified edges with borders of the pixel groupings and removing pixels that are outside of the identified edges from the pixel groupings;
instructions to generate a new stereoscopic image pair by adjusting perspective and disparity for at least one of the identified objects or the background in the stereoscopic image pair, wherein the adjusting is based at least upon the range information; and
instructions to store the new stereoscopic image pair in a processor-accessible memory system.
17. The system of claim 16 , wherein the stereoscopic image pair is received from a stereo-image-capture device.
18. The system of claim 17 , wherein the range information is identified at least from an analysis of the stereoscopic image pair.
19. The system of claim 16 , wherein the data processing system comprises at least part of a stereo-image-capture device.
20. The method system of claim 19 , wherein the stereo-image-capture device comprises a parallel camera, a multi-view camera, a single lens camera, or a hybrid stereo image camera.