Digital composition of a mosaic motion picture

• US 20050100319A1
• Filed: 09/29/2004
• Published: 05/12/2005
• Est. Priority Date: 10/01/2003
• Status: Active Grant

• Current Assignee: Aryan Saed
• Original Assignee: Aryan Saed
• Inventors: Saed, Aryan
• Granted Patent: US 8,334,877 B2
• Time in Patent Office: Days
• US Class Current: 386/318
• CPC Class Codes: H04N 5/262 Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
• CPC Class Codes: H04N 5/2624 for obtaining an image which is composed of whole input images, e.g. splitscreen

Abstract

A mosaic movie resembling a target movie is composed of movies from a data base. The target movie is divided into tile regions of a specified size and shape, and the individual movies from the data base are compared to each region to find the best matching tile. The comparison is performed by calculating a figure of visual difference between each tile and each region. The data base of tile images is created from raw source movie using digital image processing, whereby multiple instances of each individual raw source movie are produced. Tile matching is performed such that all raw source movies are represented in the final mosaic. The digital image processing involves the adjustment of colour, brightness and contrast of tile movies, as well as cropping. A movie description index locates each movie in the final mosaic.

Claims

1. A method of generating a mosaic representation of a target movie, the mosaic representation incorporating a plurality of source movies, comprising the steps of:

a) loading the target movie into a computer;

b) generating a database having a library of source movies;

c) dividing the target movie into multiple tile regions;

d) selecting source movies from the library;

e) searching through the multiple tile regions to locate tile regions having a high visual similarity when compared with the selected source movies;

f) positioning the source movies in the located regions; and

g) repeating steps d) to f) until the mosaic representation is complete.

2. The method according to claim 1 wherein a single source movie is selected from the library and wherein a single tile region is located having the highest visual similarity.

3. The method according to claim 1 wherein multiple source movies are selected from the library and wherein for each of the source movies a tile region is located having a high visual similarity.

4. The method according to claim 1 wherein the source movies are subjected to delay matching to increase the visual similarity

5. The method according to claim 1 wherein the source movies are subjected to digital image processing to increase the visual similarity.

6. The method according to claim 5 wherein the digital image processing is applied after a region has been located for the source movie.

7. The method according to claim 5 wherein the digital image processing is applied before a region has been located for the source movie.

8. The method according to claim 5 wherein the digital image processing includes a cropping stage.

9. The method according to claim 5 wherein the digital image processing includes an adaptive cropping stage wherein the source movie is cropped based on the located region.

10. The method according to claim 5 wherein the digital image processing includes adjustment of brightness and/or contrast.

11. The method according to claim 5 wherein the digital image processing includes adjustment of colour.

12. The method according to claim 5 wherein parameter ranges of the digital imaging processing are determined individually for each source image.

13. The method according to claim 5 wherein parameter ranges of the digital imaging processing are set jointly for multiple source images.

14. A method of generating a subject matter index for source movies used in a mosaic representation of a master movie, the source movies being positioned in tile regions of the mosaic representation based on visual similarity compared with corresponding regions of the target movie, the method comprising the steps of:

a) dividing the target movie into multiple tile regions;

b) assigning a co-ordinate to the location of each tile region;

c) providing a title for the subject matter of each source movie; and

d) preparing a list of co-ordinates for each title

15. An article displaying a mosaic representation of a target movie, the mosaic representation incorporating a plurality of source movies, the mosaic representation composed by a process comprising the steps of:

a) loading the target movie into a computer;

b) generating a database having a library of source movies;

c) dividing the target movie into multiple tile regions;

d) selecting source movies from the library;

e) searching through the multiple tile regions to locate tile regions having a high visual similarity when compared with the selected source movies;

f) positioning the source movies in the located regions; and

g) repeating steps d) to f) until the mosaic representation is complete.

16. The article of claim 15 wherein the article includes optical display technology;

17. The article of claim 15 wherein the article includes movie storage technology.

18. A method for generating source movies for the purpose of inserting the source movies in a movie mosaic with an appearance that approximates a target movie, comprising the steps

a) loading the target movie into a computer;

b) dividing the target movie into multiple tile regions;

c) selecting a tile region;

d) generating a tile region movie based on the tile region;

e) generating a tile movie that resembles the tile region movie;

f) positioning the tile region movie in the mosaic movie at a locus corresponding to the tile region;

19. The method of claim 18 wherein the tile movie is generated with animation technology;

20. A method of adaptively cropping a source movie for the purpose of inserting the source movie in a movie mosaic with an appearance that approximates a target movie, comprising the steps of:

a) loading the source movie into a computer;

b) rendering a tile region movie based on the target movie;

c) selecting a first frame of the tile region movie and a first frame of the target movie;

d) searching within the frame of the source movie to obtain a crop frame that yields a cropped source frame that best matches the frame of the tile region movie

e) repeating step d) for further frames.

21. The method of claim 20 wherein a frame to frame displacement of the crop frame is limited to a maximum;