Method for processing multiple images of a same scene
View Patent ↗In a first exemplary embodiment of the present invention, an automated, computerized method is provided for processing an image. According to a feature of the present invention, the method comprises the steps of providing a sequence of image files depicting images of a same scene, in a computer memory, determining correspondence information relevant to the same scene across the sequence of images, and generating individual intrinsic images for each one of the sequence of images, as a function of the correspondence information.
1. An automated, computerized method for processing an image, comprising the steps of:
providing a sequence of image files depicting images of a same scene, in a computer memory;
determining correspondence information relevant to the same scene across the sequence of images; and
generating individual intrinsic images for each one of the sequence of images, as a function of the correspondence information.
2. The method of claim 1 including the further step of identifying token regions in each image of the sequence of images, and wherein the correspondence information comprises matching token information across the sequence of images.
3. The method of claim 1 wherein the step of determining correspondence information is carried out by executing a sparse correspondence technique.
4. The method of claim 1 wherein the step of determining correspondence information is carried out by executing a dense correspondence technique.
5. The method of claim 1 wherein the step of generating individual intrinsic images for each one of the sequence of images, as a function of the correspondence information is carried out by executing an anchor constraint.
6. The method of claim 1 wherein the step of generating individual intrinsic images for each one of the sequence of images, as a function of the correspondence information is carried out by executing a multi-image solve technique.
7. The method of claim 1 wherein the step of individual generating intrinsic images for each one the sequence of images, as a function of the correspondence information is carried out by executing an intrinsic image process according to a spatio-spectral operator/constraint/solver model and performing post processing techniques on generated intrinsic images using the correspondence information.
8. The method of claim 3 wherein the sparse correspondence technique is selected from the group consisting of a patch registration technique, a histogram-based correspondence technique and a spectral-ratio-based correspondence technique.
9. A computer system which comprises:
a CPU; and
a memory storing a sequence of image files depicting images of a same scene;
the CPU arranged and configured to execute a routine to determine correspondence information relevant to the same scene across the sequence of images, and generate individual intrinsic images for each one of the sequence of images, as a function of the correspondence information.
10. A computer program product, disposed on a non-transitory computer readable media, the product including computer executable process steps operable to control a computer to: provide a sequence of image files depicting images of a same scene, in a computer memory, determine correspondence information relevant to the same scene across the sequence of images, and generate individual intrinsic images for each one of the sequence of images, as a function of the correspondence information.
11. The computer program product of claim 10 including the further process step of identifying token regions in each image of the sequence of images, and wherein the correspondence information comprises matching token information across the sequence of images.
12. The computer program product of claim 10 wherein the process step of determining correspondence information is carried out by executing a sparse correspondence technique.
13. The computer program product of claim 10 wherein the process step of determining correspondence information is carried out by executing a dense correspondence technique.
14. The computer program product of claim 10 wherein the process step of generating individual intrinsic images for each one of the sequence of images, as a function of the correspondence information is carried out by executing an anchor constraint.
15. The computer program product of claim 10 wherein the process step of generating individual intrinsic images for each one of the sequence of images, as a function of the correspondence information is carried out by executing a multi-image solve technique.
16. The computer program product of claim 10 wherein the process step of generating individual intrinsic images for each one of the sequence of images, as a function of the correspondence information is carried out by executing an intrinsic image process according to a spatio-spectral operator/constraint/solver model and performing post processing techniques on generated intrinsic images using the correspondence information.
17. The computer program product of claim 12 wherein the sparse correspondence technique is selected from the group consisting of a patch registration technique, a histogram-based correspondence technique and a spectral-ratio-based correspondence technique.
18. The method of claim 1 wherein the same scene comprises an object.
19. The method of claim 18 wherein the object is preselected.
20. The computer system of claim 9 wherein the same scene comprises an object.
21. The computer system of claim 20 wherein the object is preselected.
22. The computer program product of claim 10 wherein the same scene comprises an object.
23. The computer program product of claim 22 wherein the object is preselected.