Methods for multi-point descriptors for image registrations
Methods for generating an image mosaic are provided. In one respect, pixels saliency of a first image and a second image are determined. One salient pixel may be selected from the determined pixels saliency group of the first image and one salient pixel may be selected from the determined pixels saliency group of the second image. A mosaicking technique of the first and second image may be performed if the one salient pixel of the first image and the one salient pixel of the second image are registered successfully.
1. A method comprising:
providing at least a first image and a second image;
selecting, in a processor, a similar object in the first image and the second image;
selecting, in the processor, a first pair of points of interest from the first image and a second pair of points of interest from the second image related to the selected object, where each of the points of interest is a corner of the object;
generating, in the processor, a first intensity profile of a first line connecting the first pair of points of interest;
generating, in the processor, a second intensity profile of a second line connecting the second pair of points of interest; and
comparing, in the processor, the first intensity profile of the first line to the second intensity profile of the second line.
2. The method of claim 1 , where the first and second images are static images or dynamic images.
3. The method of claim 1 , where at least one of the first pair of points of the first image and the second pair or points of the second image correspond to a corner pixel of the first image and second image respectively.
4. The method of claim 1 , further comprising selecting a first additional point of interest in the first image and a second additional point of interest in the second image;
generating a first additional intensity profile of a first pair of lines between the first additional point of interest and the first pair of points of interest, wherein a first triangle is formed by the first line connecting the first pair of points of interest and the first pair of lines;
generating a second additional intensity profile of a second pair of lines between the second additional point of interest and the second pair of points of interest, wherein a second triangle is formed by the second line connecting the second pair of points of interest and the second pair of lines; and
generating a first intensity profile of the first triangle;
generating a second intensity profile of the second triangle; and
comparing the first intensity profile of the first triangle to the second intensity profile of the second triangle.
5. The method of claim 1 , further comprising generating an image mosaic.
6. The method of claim 5 , where generating the image mosaic comprises correcting luminance variance between the first image and the second image.
7. A non-transitory computer or machine readable medium embodying a program, that when executed by a processor, is configured to cause the processor to perform the steps comprising:
providing at least a first image and a second image;
selecting, in the processor, a similar object in the first image and the second image;
selecting, in the processor, a first pair of points of interest from the first image and a second pair of points of interest from the second image related to the selected object, where each of the points of interest is a corner of the object;
generating, in the processor, a first intensity profile of a first line connecting the first pair of points of interest;
generating, in the processor, a second intensity profile of a second line connecting the second pair of points of interest; and
comparing, in the processor, the first intensity profile of the first line to the second intensity profile of the second line.
8. A method comprising:
determining, in a processor, a first intensity profile of a line connecting two points of interest of an image, where each of the points of interest is a corner of an object;
determining, in the processor, a second intensity profile of a line connecting two points of interest from a surrounding image, where each of the points of interest is a corner of an object; and
using the first and second intensity profiles for generating, in the processor, an image mosaic of two or more images.
9. The method of claim 8 , where detecting surrounding images comprises determining a window around the selected pixel.
10. The method of claim 8 , where using the selected pixel for generating an image mosaic comprises
registering the selected pixel; and
generating an image mosaic if the registering of the selected pixel is successful.
11. The method of claim 8 , where determining a type of pixel comprises determining a corner pixel.
12. The method of claim 8 , further comprising where generating the image mosaic comprises correcting luminance variance between the first image and the second image.
13. A non-transitory computer or machine readable medium embodying a program, that when executed by a processor, is configured to cause the processor to perform the steps comprising:
determining, in the processor, a first intensity profile of a line connecting two points of interest of an image, where each of the points of interest is a corner of an object;
determining, in the processor, a second intensity profile of a line connecting two points of interest from a surrounding image, where each of the points of interest is a corner of an object; and
using the first and second intensity profiles for generating, with the processor, an image mosaic of two or more images.
14. A processor-implemented method for image mosaicking comprising:
determining, in a processor, a first pixel intensity profile of pixels along a first line between two points of interest of a first image;
determining, in the processor, a second pixel intensity profile of pixels along a second line between two points of interest of a second image, the second image being similar to the first image; and
mosaicking the first and second image if the first and second pixel intensity profiles from the first and second images are successfully registered, with the processor,
where each of the points of interest is a corner of an object.
15. The method of claim 14 , where selecting one salient pixel of the first image comprises selecting an interior pixel, an edge pixel, or a corner pixel.
16. The method of claim 14 , where selecting one salient pixel of the second image comprises selecting an interior pixel, an edge pixel, or a corner pixel.
17. The method of claim 14 , where the first image and the second image are static images or dynamic images.
18. The method of claim 14 , further comprising correcting luminance variance between the first image and the second image.
19. A non-transitory computer or machine readable medium embodying a program, that when executed by a processor, is configured to cause the processor to perform the steps comprising:
determining, in the processor, a first pixel intensity profile of pixels along a first line between two points of interest of a first image;
determining, in the processor, a second pixel intensity profile of pixels along a second line between two points of interest of a second image, the second image being similar to the first image; and
mosaicking, with the processor, the first and second image if the first and second pixel intensity profiles from the first and second images are successfully registered,
where each of the points of interest is a corner of an object.