Incremental scanning for custom landmarkers
AssigneeSnap Inc.
InventorsMarwan Aljubeh, Nursultan Jubatyrov, Eric Nersesian, Supannee Tanathong
Life of this patent
Estimating the term…
Abstract
A method for generating an updated localizer map of a reference scene is provided. The method may include: acquiring a preliminary localizer map of the reference scene, the preliminary localizer map including a preliminary frame that each is associated with a set of preliminary data points; capturing a plurality of new data points on the reference scene; determining poses of the capture device related to the capture of the plurality of new data points; creating at least one new frame; selecting one or more target frames from the preliminary frame and the new frame; and generating the updated localizer map based on the one or more target frames.
Claims14
A method to generate an updated localizer map of a reference scene, the method comprising:
- acquiring a preliminary localizer map of the reference scene, the preliminary localizer map including a preliminary frame that each is associated with a set of preliminary data points;
- capturing, using a capture device, a plurality of new data points on the reference scene;
- determining a pose of the capture device related to the capture of the plurality of new data points;
- creating a new frame, the new frame corresponding to the pose and being associated with a set of new data points of the plurality of new data points;
- selecting one or more target frames from the preliminary frame and the new frame;
- generating the updated localizer map based on the one or more target frames and the associated sets of preliminary data points or new data points;
- acquiring a 3D data representation of the reference scene;
- aligning the preliminary localizer map with the 3D data representation of the reference scene;
- transforming the new frame from a new coordinate system to an old coordinate system corresponding to the preliminary frame, to align the 3D data representation with the updated localizer map;
- and
- generating a 3D model of the reference scene based on the aligned updated localizer map and the 3D data representation.
A computing apparatus comprising:
- a processor;
- and
- a memory storing instructions that, when executed by the processor, configure the apparatus to:
- acquire a preliminary localizer map of a reference scene, the preliminary localizer map including a preliminary frame that each is associated with a set of preliminary data points;
- capture, using a capture device, a plurality of new data points on the reference scene;
- determine a pose of the capture device related to the capture of the plurality of new data points;
- create a new frame, each of the new frame corresponding to one of the pose and being associated with a set of new data points of the plurality of new data points;
- select one or more target frames from the preliminary frame and the new frame;
- and
- generate an updated localizer map based on the one or more target frames and the associated sets of preliminary data points or new data points;
- acquire a 3D data representation of the reference scene;
- align the preliminary localizer map with the 3D data representation of the reference scene;
- transform the new frame from a new coordinate system to an old coordinate system corresponding to the preliminary frame, to align the 3D data representation with the updated localizer map;
- and
- generate a 3D model of the reference scene based on the aligned updated localizer map and the 3D data representation.
A non-transitory computer-readable storage medium, the non-transitory computer-readable storage medium including instructions that when executed by a computer, cause the computer to:
- acquire a preliminary localizer map of a reference scene, the preliminary localizer map including a preliminary frame that each is associated with a set of preliminary data points;
- capture, using a capture device, a plurality of new data points on the reference scene;
- determine a pose of the capture device related to the capture of the plurality of new data points;
- create a new frame, each of the new frame corresponding to one of the pose and being associated with a set of new data points of the plurality of new data points;
- select one or more target frames from the preliminary frame and the new frame;
- and
- generate an updated localizer map based on the one or more target frames and the associated sets of preliminary data points or new data points,
- acquire a 3D data representation of the reference scene;
- align the preliminary localizer map with the 3D data representation of the reference scene;
- transform the new frame from a new coordinate system to an old coordinate system corresponding to the preliminary frame, to align the 3D data representation with the updated localizer map;
- and
- generate a 3D model of the reference scene based on the aligned updated localizer map and the 3D data representation.
Dependencies are inferred from the claim text.