Video mosaic
First Claim
Patent Images
1. A computer-implemented method of creating a video mosaic, comprising:
- extracting a first individual frame and a second individual frame of imagery from a series of video frames;
detecting edges in the first individual frame and the second individual frame;
following adjacent on pixels until an off pixel is detected;
counting a number of on pixels and if above a preset threshold, designate as a structure;
repeat said searching, said following, and said counting steps until entire frame is structure detected;
determining regions of interest in the first individual frame and the second individual frame based on the detected edges;
identifying commonality from the first individual frame to the second individual frame, including correlating determined regions of interest between the two individual frames by comparing each region of interest in the first individual frame to a region of interest in the second individual frame; and
overlapping the individual frames based on the commonality identified from the first individual frame to the second individual frame and displaying an image representing a continuous area.
2 Assignments
0 Petitions
Accused Products
Abstract
The present invention is directed to a system and method for building a video mosaic from a sequence of video images. Advantageously, the present invention can quickly and easily align each image by performing an image registration. The image registration includes detecting edges of structures and determining regions of interest. Once regions of interest are determined, then the distance from the center of the video image to the region of interest can be determined and from that determined data, the video images can be aligned.
-
Citations
20 Claims
-
1. A computer-implemented method of creating a video mosaic, comprising:
-
extracting a first individual frame and a second individual frame of imagery from a series of video frames; detecting edges in the first individual frame and the second individual frame; following adjacent on pixels until an off pixel is detected; counting a number of on pixels and if above a preset threshold, designate as a structure; repeat said searching, said following, and said counting steps until entire frame is structure detected; determining regions of interest in the first individual frame and the second individual frame based on the detected edges; identifying commonality from the first individual frame to the second individual frame, including correlating determined regions of interest between the two individual frames by comparing each region of interest in the first individual frame to a region of interest in the second individual frame; and overlapping the individual frames based on the commonality identified from the first individual frame to the second individual frame and displaying an image representing a continuous area. - View Dependent Claims (2, 3, 4, 5)
-
-
6. A computer architecture, comprising:
-
extracting means for extracting a first individual frame and a second individual frame of imagery from a series of video frames; detecting means for detecting edges in the first individual frame and the second individual frame; means for following adjacent on pixels until an off pixel is detected; means for counting a number of on pixels and if above a preset threshold, designate as a structure; means for repeating said searching, said following, and said counting steps until entire image is structure detected; determining means for determining regions of interest in the first individual frame and the second individual frame based on the detected edges detected by the detecting means; identifying means for identifying commonality from the first individual frame to the second individual frame, including correlating determined regions of interest between the two individual frames by comparing each region of interest in the first individual frame to a region of interest in the second individual frame; and overlapping means for overlapping the individual frames based on the commonality identified by the identifying means from the first individual frame to the second individual frame and displaying an image representing a continuous area. - View Dependent Claims (7, 8, 9, 10)
-
-
11. An article, comprising:
-
at least one sequence of processor-executable instructions; a computer-readable medium bearing the processor-executable instructions wherein execution of the instructions by one or more processors causes the one or more processors to; extract a first individual frame and a second individual frame of imagery from a series of video frames; detect edges in the fast individual frame and the second individual frame; follow adjacent on pixels until an off pixel is detected; count a number of on pixels and if above a preset threshold, designate as a structure; repeat said detect, said follow, and said count instructions until the entire image is structure detected; determine regions of interest in the first individual frame and the second individual frame based on the detected edges; identify commonality from the first individual frame to the second individual frame, including correlating determined regions of interest between the two individual frames by comparing each region of interest in the first individual frame to a region of interest in the second individual frame; and overlap the individual frames based on the commonality identified from the first individual frame to the second individual frame and display an image representing a continuous area. - View Dependent Claims (12, 13, 14, 15)
-
-
16. A computer system, comprising:
-
a processor; and a memory coupled to said processor, the memory having stored therein sequences of instructions, which, when executed by said processor, causes said processor to perform the steps of; extracting a first individual frame and a second individual frame from a series of video frames; detecting edges in the first individual frame and the second individual frame; following adjacent on pixels until an off pixel is detected; counting a number of on pixels and if above a preset threshold, designate as a structure; repeat said searching, said following, and said counting steps until entire image is structure detected; determining regions of interest in the first individual frame and the second individual frame based on the detected edges; identifying commonality from the first individual frame to the second individual frame, including correlating determined regions of interest between the two individual frames by comparing each region of interest in the first individual frame to a region of interest in the second individual frame; overlapping the individual frames based on the commonality identified from the first individual frame to the second individual frame and displaying an image representing a continuous area. - View Dependent Claims (17, 18, 19, 20)
-
Specification