An apparatus, a method, and a computer program product for use in performing, monitoring, and evaluating the performance of therapeutic exercises. The apparatus includes a human-device interface and a motion sensor. In response to movement of the human-device interface, a controller receives motion data from the motion sensor, and transmits the motion data to a computing device. Based on the motion data, the computing device displays a graphical element that depicts the movement. The computing device compares the movement to a target motion, and if the movement matches the target motion, displays a graphical element indicating an exercise is being performed properly. If the movement does not match the target motion, the computing device indicates the exercise is not being performed properly and displays another graphical element indicating how to correct the motion.

An athletic training system has a data recording system and a data engine. The data recording system is configured to record an athletic competition event. The event may have a first team of players competing against a second team of players. The data engine is configured to receive data associated with the recorded athletic competition event. The data engine processes the data and displays the data as a replay of the event in animated form.

A method is disclosed for using an artificial intelligence engine to interact with a user of an exercise device during an exercise session. The method includes generating, by the artificial intelligence engine, a machine learning model trained to receive data as input, and based on the data, providing an output. While a user performs an exercise using the exercise device, the method includes receiving the data from an input peripheral of a computing device associated with the user. Based on the data being received from the input peripheral, the method includes determining, via the machine learning model, the output to control an aspect of the exercise device.

A system and method for implementing a virtual fitness application are disclosed. Embodiments may be built for various platforms, including web browsers and mobile phones. One embodiment uses pose estimation to count the repetitive motions of a fitness activity (e.g., running). In one embodiment, to count the repetitive motions, a repetitive motion counting process is used that is based on computing differences of Y-coordinates of key points of the user. The repetitive motion counting process includes selecting a proper pose of the user; computing one or more delta values (corresponding to Y-coordinate changes of the key points); and counting a given user movement as a repetitive motion based on a function (e.g., average) of the delta values. One embodiment uses the pose estimation and repetitive motion count results to provide a gamified experience, for example, a leaderboard, a stats report, instant visual feedback, badges, coins, and a social experience.

During a first time period and for a first user, a second user is automatically selected based on competitive data of the first user and competitive data of the second user, and a workout selection is sent to cause a video of a workout to be displayed during a second time period on a smart mirror of the first user and a smart mirror of the second user. During the second time period, a live stream of the first user exercising is displayed at the smart mirror of the second user, and a live stream of the second user exercising is received and displayed at the smart mirror of the first user. During the second time period, a performance score of the first user and a performance score of the second user is displayed at the smart mirrors of the first user and the second user.

Systems and methods are disclosed for generating and providing guided practices and coaching feedback (e.g., illustrated in 3D images, video, or audio) that allow golfers to follow along to improve their physical swing in a digital environment. The feedback may be provided with a 3D avatar using a biomechanical analysis of observed actions with a focus on representing actions through computer-generated 3D avatars. Physical quantities of biomechanical actions can be measured from the observations, and the system can analyze these values, compare them to target or optimal values, and use the observations and known biomechanical capabilities to generate the guided practices and coaching feedback.

Provided is a device for pitch detection within user-defined zones. The device detects a first gesture at a first height based on first output from all or some sensors, and detects a second gesture at a second height based on second output from all or some sensors. The device sets a top and bottom of the user-defined zone based on the first height and the second height, and tracks a location of an object relative to the user-defined zone based on third output, from a subset of sensors, that is generated in response to the object moving over or under the subset of sensors. The device discards output generated from two or more sensors that are not adjacent, measurements from adjacent sensors that differ by more than a distance threshold, and/or output from adjacent sensors with timestamps that differ by more than a time threshold.

A method includes causing display, during a first time period and via a first set of multiple smart mirrors, of live video depicting at least one user associated with the first set of multiple smart mirrors, without displaying a workout video. The method also includes causing display, during a second time period following and mutually exclusive of the first time period, and via a second set of multiple smart mirrors, of a workout video and a representation of at least one user associated with the second set of smart mirrors. The method also includes causing display, during a third time period following and mutually exclusive of the second time period, and via a third set of multiple smart mirrors, of live video depicting at least one user associated with the third set of multiple smart mirrors.

A method provides for optimizing at least one exercise. The method includes receiving first image data. The first image data includes first pixel data associated with the user performing the exercise at a first time. The method includes receiving second image data. The second image data includes second pixel data associated with the user performing the exercise at a second time. The method includes determining, based on a difference between the first pixel data and the second pixel data, deviation data associated with a profile of the user. The method includes generating outline data based on the deviation data and corresponding to a frontal area of the user. The method may also include determining drag coefficient data based on the frontal area of the user. The method includes determining, based on the outline data and the drag coefficient data, drag force data associated with the user using the exercise device.

A smart soccer goal for tracking and communicating motion of objects includes a goal frame; a net coupled to the goal frame including a plurality of lights; and one or more sensors coupled to the goal frame. A first sensor of the one or more sensors is directed to detecting movement within and immediately near the smart soccer goal and a second sensor of the one or more sensors is directed to detecting movement outside of the smart soccer goal.