Flexible vantage positioning using multiple data sources

A computer system comprising one or more processors and one or more computer-readable storage media storing instructions that, upon execution by the one or more processors, cause the computer system to, at least:

• receive, from a first camera of a plurality of cameras that are communicatively coupled to the computer system, a sequence of images that shows a motion of an object within a first field of view of the first camera, the first field of view showing a first portion of a physical topography, the first portion of the physical topography mapped to a three-dimensional (3D) coordinate space, the motion occurring during an event associated with the physical topography;
• identify the object shown in the sequence of images by at least using a computer vision model that is configured for a sports type of the event and that is trained to detect an object type of the object based at least in part on training images corresponding to the sports type of the event;
• determine a motion profile of the object that maps the motion of the object to the three-dimensional coordinate space;
• and
• providing the motion profile to a computing service, the motion profile operable for being combined with audiovisual data associated with the motion of the object within the physical topography, at least a portion of the audiovisual data also mapped to the three-dimensional coordinate space, and wherein the combined data is provided to a user device for presentation.

A non-transitory computer readable medium storing specific computer-executable instructions that, when executed by a processor of a computer system, cause the computer system to:

• map a portion of a physical topography, shown within a first field of view of a camera, to a three-dimensional (3D) coordinate space, the first field of view showing a first portion of a physical topography mapped to the 3D coordinate space;
• receive, from the camera, a sequence of images that shows a motion of an object within the first field of view of the camera, the motion occurring during an event associated with the physical topography;
• identify the object shown in the sequence of images by at least using a computer vision model that is configured for a sports type of the event and that is trained to detect an object type of the object based at least in part on training images corresponding to the sports type of the event;
• determine a motion profile of the object that maps the motion of the object to the three-dimensional coordinate space;
• obtain audiovisual data associated with the motion of the object through the portion of the physical topography shown within the first field of view, the audiovisual data mapped to at least one of (I) the three-dimensional coordinate space, or (II) a time period during which the motion of the object occurred;
• generate a three-dimensional animation based at least in part on combining the motion profile with the audiovisual data, the three-dimensional animation showing the motion of the object from a vantage position that corresponds to a second field of view;
• and
• provide the three-dimensional animation to a user device for presentation of the three-dimensional animation.