Generating a stitched image or three-dimensional model from one or more dimension extractable objects comprising spatial metadata for a captured image or video
AssigneePlethron Inc.
InventorsEric Minami, Charles Chu
Life of this patent
Estimating the term…
Abstract
The invention relates to capturing a still or moving image as well as object position and displacement data for the image, storing the image and the data as a dimension extractable object, and utilizing the dimension extractable object. In one embodiment, the dimension extractable object is used in a method of stitching a plurality of images together to form a stitched image. In another embodiment, the dimension extractable object is used in a method of generating a stitched image from a video image. In another embodiment, the dimension extractable object is used in a method of generating a three-dimensional model from a video image.
Claims20
A method of stitching a plurality of images together to form a stitched image, the method comprising:
- receiving, by a computing device, a plurality of dimension extractable objects;
- extracting, by the computing device, a set of image data and spatial metadata from each of the dimension extractable objects, wherein for each set of image data and spatial metadata, the image data corresponds to an image captured by a device and the spatial metadata comprises image position data and distance data, the distance data indicating a distance between the device and a physical object depicted in the image at a time the image data was captured;
- and
- stitching, by the computing device, images derived from the image data using the spatial metadata to form a stitched image.
A method of generating a stitched image from a video image, the method comprising:
- receiving, by a computing device, a dimension extractable object;
- extracting, by the computing device, a video stream, a first set of metadata, and a second set of metadata from the dimension extractable object, the first set of metadata comprising metadata for the video stream;
- extracting a plurality of frames from the video stream, wherein each of the plurality of frames comprises an image captured by a device and the second set of metadata comprises image position data and distance data for each frame, the distance data indicating a distance between the device and a physical object depicted in the image of the frame at a time the image was captured;
- and
- stitching, by the computing device, a plurality of images from the plurality of frames using some or all of the first set of metadata and the second set of metadata to form a stitched image.
A method of generating a three-dimensional model from a video image, the method comprising:
- receiving, by a computing device, a dimension extractable object;
- extracting, by the computing device, a plurality of sets of images and metadata from the dimension extractable object, wherein the images were captured by a device and the metadata comprises image position data and distance data, the distance data indicating a distance between the device and a physical object depicted in the image at a time the image was captured;
- and
- generating a three-dimensional model, by the computing device, using the plurality of sets of images and spatial metadata.
Dependencies are inferred from the claim text.