Image capture system

摘要

A system is described that allows for the tracking of an exercise occurring within a physical environment. In one or more implementations, the system includes a depth sensing device configured to obtain depth values associated with a plurality of pixels. The depth values indicating distances from one or more physical objects in a physical environment to the depth sensing device. The system also includes a computing device in communication with the depth sensing device. The computing device includes a memory and a processor. The processor is configured to execute the one or more modules to cause the processor to: identify a point corresponding to at least one pixel representing a portion of at least one physical object within the physical environment based upon the pixel depth values; track the point through a plurality of image frames; and determine whether at least one repetition has occurred based upon the tracked point.

主权项

1. A computer implemented method having access to memory, the method providing a real-time three-dimensional representation of a physical environment captured by a depth sensing device, the computer implemented method comprising:
obtaining depth values associated with a plurality of pixels indicating distances from one or more physical objects in the physical environment to the depth sensing device; identifying a point corresponding to at least one pixel of the plurality of pixels as representing a portion of at least one physical object of the one or more physical objects within the physical environment based upon the pixel depth values, the at least one object utilized to perform an exercise, wherein identifying the point comprises selecting a starting pixel from the plurality of pixels; selecting a plurality pixels from the plurality of pixels; identifying at least two offset pixels of the plurality of offset pixels that are at least substantially equidistant and at least substantially collinear with the starting pixel; and selecting the starting pixel as the point; tracking the point through a plurality of image frames, the image frames representing the physical environment; and determining whether at least one repetition has occurred based upon the tracked point.