摘要:
Data-driven item value determinations for a user-interested topic are automatically generated and made available to a user for rendering effective, efficient decisional choices on one or more aspects of the user-interested topic. Information on components of the user-interested topic relevant to a user's decisional choices are mined from the internet and collated to generate values that identify optimum user choices. User input is utilized to tailor generated value determinations for specific user preferences, issues and/or concerns. Data-driven item value determinations can be generated for a host of user-interested topics including, but not limited to, eating establishment nutritional choices and shopping mall criteria.
摘要:
In accordance with one or more aspects, a plane in a 3D coordinate system in which a 3D model is to be generated based on one or more 2D images is identified. A direction of extrusion for the plane is also identified. Additionally, a user identification of a region of interest on a 2D image is received and projected onto the plane. A location in the 3D model of the region of interest is then automatically identified by extruding the plane along the direction of extrusion until the region of interest in the plane matches a corresponding region of at least one of the one or more 2D images.
摘要:
Technologies are described herein for transitioning between a top-down map of a reconstructed structure within a 3-D scene and an associated local-navigation display. An application transitions between the top-down map and the local-navigation display by animating a view in a display window over a period of time while interpolating camera parameters from values representing a starting camera view to values representing an ending camera view. In one embodiment, the starting camera view is the top-down map view and the ending camera view is the camera view associated with a target photograph. In another embodiment, the starting camera view is the camera view associated with a currently-viewed photograph in the local-navigation display and the ending camera view is the top-down map.
摘要:
Technologies are described herein for generating and displaying top-down maps of reconstructed structures to improve navigation of photographs within a 3-D scene. A 3-D point cloud is computed from a collection of photographs of the scene. A top-down map is generated from the 3-D point cloud by projecting the points in the point cloud into a two-dimensional plane. The points in the projection may be filtered and/or enhanced to enhance the display of the top-down map. Finally, the top-down map is displayed to the user in conjunction with or as an alternative to the photographs from the reconstructed structure or scene.
摘要:
In one example, images may be used to create a model of a three-dimensional space, and the three-dimensional space may be annotated and/or edited. When a three-dimensional model of a space has been created, a user may associate various items with points in the three-dimensional space. For example, the user may create a note or a hyperlink, and may associate the note or hyperlink with a specific point in the space. Additionally, a user may experiment with the space by adding images to, or deleting images from, the space. Annotating and editing the space, rather than the underlying images, allows annotations and edits to be associated with the underlying objects depicted in the images, rather than with the images themselves.
摘要:
A method described herein includes the acts of receiving an image captured by a mobile computing device and automatically annotating the image to create an annotated image, wherein annotations on the annotated image provide instructions to a user of the mobile computing device. The method further includes transmitting the annotated image to the mobile computing device.
摘要:
One or more images of an object are obtained. These are then warped onto the object. The object may be divided into sites where sites are overlapping circular regions of the object. For each site, a neighborhood graph may be created where each site is a node in the graph and each pair of sites with overlapping regions is connected by an edge. A list of covers of each site may be created where the list contains all the possible labels for that node. Each image that covers part of the site may be reviewed including all possible shifts up to some number of pixels. A cost may be assigned to each cover and costs for each of the covers may be calculated. The cover with the lowest cost may be selected. If the costs are too high, the resolution may be lowered, one or more possible covers may be selected and then the analysis may be performed using the selected covers at a higher resolution.
摘要:
Feeds from cameras are better visualized by superimposing images based on the feeds onto map based on a two- or three-dimensional virtual map. For example, a traffic camera feed can be aligned with a roadway included in the map. Multiple videos can be aligned with roadways in the map and can also be aligned in time.
摘要:
Aggregated data associated with a geographic area may be obtained. The aggregated data may be dynamically distilled to obtain a presentation set of data based on a dynamically changing geographic location associated with the geographic area. A transmission of a stream of personalized audio data that is based on the presentation set of data may be initiated, via a device processor, to a receiving device associated with a user that is associated with the dynamically changing geographic location.
摘要:
Amalgamated maps, comprising interior maps overlaid on venues indicated in general maps can be automatically generated. Initially, interior maps can be obtained through targeted network searches, whose search results can be filtered to retain those that are most likely useable interior maps. A bounding polygon is generated for both interior map and venue exterior from general map. Subsequently, directional histograms representing orientations of lines in bounding polygons are generated and compared to automatically identify a rotation to align the interior map with the venue exterior from the general map. Anchor points are identified to locally deform the interior map, preserving internal structures, to better align with the venue exterior. Once aligned, the interior map can be combined with the general map, forming an amalgamated map. Updated geocoding can be performed based on locations of establishments in the venue as indicated by the interior map.