Apple has placed a tremendous amount time and technology into health matters including exercising using Apple Watch, iPhone, iPad and Apple TV that supports Apple Fitness+ which covers a series of unique workout that include workouts for the treadmill, cycling, rowing and so much more.  

Yesterday the U.S. Patent and Trademark Office officially published a patent application from Apple that relates primarily to advanced treadmill or bike training.

More specifically, Apple notes that a face tracker of a tracking device (e.g., face tracking software of a smartphone) receives video frames captured by a front-facing camera of the tracking device, such as a smartphone. The tracking device can be, for example, a smartphone resting on a tread mill console while a user is exercising on a treadmill.

The face tracker uses various coordinate transformations to track the motion of one or more features of the user's face. The face tracker is part of Apple Inc.'s ARKit®, and the facial features tracked include the user's face center (e.g., the user's nose), left eye and right eye. Each feature is represented by a Cartesian reference frame.

The face center reference frame is illustrated in FIG. 1A below and the reference frames for the left eye and right eye balls are illustrated in FIGS. 1B and 1C, respectively.

The translation aspect of these three matrices indicate the position of the center of the head/eyeballs, relative to a reference position represented by an anchor transform, where the anchor transform represents a real-world position and orientation of the user's face.

Apple's patent FIG. 2 below illustrates key features of a step that can be extracted from face tracking data to estimate the user's step cadence. 

In some embodiments, determining the grade of the surface on which the user is walking or running based on at least one of the device motion data or the face tracking data, further comprises: tracking a displacement envelope of a vertical axis of a face centered reference frame; responsive to the envelope changing, estimating the grade of the surface based on the face tracking data; and responsive to the envelope not changing, determining the grade of the surface based on device motion data output by a motion sensor of the device.

Advantages of the disclosed embodiments include: 1) providing a real-time treadmill fitness experience using the front-facing camera of a tracking device (e.g., a smartphone) when the device is not worn by the user; 2) track caloric expenditure during the user's workout using speed and grade estimated using a single camera; and 3) no need for body-worn sensors (e.g., a smartwatch) or fitness machine connectivity.

Apple's patent FIG. 4 below is block diagram of a system for estimating user step cadence and grade using face tracking data capture from video and device motion data.

Apple's patent FIG. 3C above illustrates device motion pitch data over time during a grade change for a treadmill design where the control/display console is connected to the running deck; FIG. 7 is a flow diagram of a process of tracking caloric expenditure using a camera

While the patent didn't specifically note the use of an exercise bike, it did indirectly by noting that patent figure "embodiments are not limited to treadmill workouts, but can be used with any exercise or exercise equipment where camera tracking data provides an indication of a fitness metric, including but not limited to tracking other parts of the human body.

For example, the disclosed embodiments are applicable to any exercise, health monitoring application or fitness machine where vertical or lateral face motion can be captured by a camera, including but not limited to counting squats, pull-ups or jump rope steps, where there is vertical motion of the face, or lateral motion of the face, such as side step exercises."

For full details, review Apple's patent application  20240041354.