System and method for creating navigable views

Patent metadata

Field	Value
Publication number	US-2020184251-A1
Application number	US-202016786415-A
Country	US
Kind code	A1
Filing date	Feb 10, 2020
Priority date	Jul 30, 2013
Publication date	Jun 11, 2020
Grant date	—

Abstract

A method for creating navigable views includes receiving digital images, computing a set of feature points for each of the digital images, selecting one of the digital images as a reference image, identifying a salient region of interest in the reference image, identifying other digital images containing a region of interest similar to the salient region of interest in the reference image using the set of feature points computed for each of other digital images, designating a reference location for the salient region of interest in the reference image, aligning the other digital images to the image that contains the designated reference location, ordering the image that contains the designated reference location and the other digital images, and generating a navigable view.

First claim

1 - 20 . (canceled)

21 . A computer-implemented method for extracting objects from digital images, the method comprising:
receiving a plurality of digital images; using a processor to compute a set of feature points for each digital image in the plurality of digital images; using the processor to identify, for each digital image in the plurality of digital images, a primary image object appearing in each digital image, wherein the primary image object is selected from the group consisting of a stationary foreground object, a movable foreground object, a stationary background object, and a movable background object; using the processor to categorize each digital image in the plurality of digital images according to the primary image object identified in the digital image; using the processor to select a digital image in which the identified primary object is a movable foreground object; using the processor to extract the movable foreground object from the selected digital image; one or more selected movable foreground primary image objects to move independently of the related backgrounds; using the processor to combine the extracted movable foreground object and animation options to create a scene, wherein the extracted movable foreground object moves independently of a background in the scene; and presenting, on a display device, a rendering of the scene.

22 . The computer-implemented method of claim 1 , further comprising using the processor to identify a recurring stationary background object in the plurality of digital images, and wherein the background in the scene comprises the recurring stationary background object.

23 . The computer-implemented method of claim 1 , wherein using the processor to combine the extracted movable foreground object and animation options modifies the extracted movable foreground object to create an appearance of movement by the extracted movable foreground object within the scene.

24 . The computer-implemented method of claim 23 , wherein the animation options comprise the animation options comprise human movement animations and vehicle movement animations.

25 . The computer-implemented method of claim 23 , wherein the animation options are user selected from a set of standard image animation tools.

26 . The computer-implemented method of claim 21 , further comprising using the processor to identify recurring stationary background objects in the plurality of digital images and perform panoramic stitching involving the recurring stationary background objects to create the background in the scene.

27 . The computer-implemented method of claim 21 , wherein using the processor to categorize each digital image in the plurality of digital images according to the primary image object identified in the digital image comprises organizing the primary image objects identified in the plurality of digital images according to a temporal criterion or a spatial criterion.

28 . The computer-implemented method of claim 21 , wherein the processor is a component of a digital camera, a smart phone, a digital printer, an internet server, a retail kiosk, or a personal computer.

29 . The computer-implemented method of claim 21 , wherein the display device comprises a graphical user interface, and the method further comprises receiving a user control via the graphical user interface to modify the rendering of the scene.

30 . The computer-implemented method of claim 29 , wherein presenting the rendering of the scene creates a virtual environment, and wherein the user control moves the extracted movable foreground object within the virtual environment.

Assignees

• Kodak Alaris Inc

Inventors

• Loui Alexander C
• Manico Joseph A

Classifications

• G06V20/30 Primary

  in albums, collections or shared content, e.g. social network photos or video · CPC title

• G06V10/462

  Salient features, e.g. scale invariant feature transforms [SIFT] · CPC title

• G06F16/5854

  using shape and object relationship · CPC title

• G06K9/46 Primary

  Physics · mapped topic

• G06K9/00677

  Physics · mapped topic