Disclosed herein is a system for testing motor skills involved in locomotor, non-locomotor, and manipulative activities. The system utilizes joint data created by a motion sensor during a subject's performance of an activity to determine the subject's motor skill proficiency for that activity. The system compares the subject's joint data to benchmark data to detect one or more phases of the activity. Based on the comparison, the system also determines the subject's proficiency in the particular motor skill tested. The system is embodied in a computer-implemented application that provides various user interfaces for navigating through the user interfaces, accessing a database of the system, testing a subject's motor skills, analyzing a subject's proficiency, and facilitating practice of motor skills.

A system includes wearable devices positioned on a subject in different locations. Each wearable device includes motion sensors that measure the subject's movement in three dimensions. The motion sensors generate raw sensory data as the subject performs a physical movement. A data filter is selected based on a condition of the subject and a designated movement corresponding to the physical movement, and used to convert the raw sensory data into formatted data. A level of compliance of the physical movement with a movement model for the designated movement is determined by applying comparative modeling techniques to the formatted data and the movement model. Real-time feedback is delivered dynamically to the subject by the wearable devices during the performance of the physical movement based on the level of compliance. The movement model can be generated, and the comparative modeling techniques can be selected, based on the condition of the subject.

A basketball training apparatus and a method for improving basketball shot making are disclosed. The basketball training apparatus includes a horizontal bar column, one or more brackets and a processing system. The horizontal bar column is configured to be mounted on a vertical structure and includes a plurality of longitudinal members. The one or more brackets are configured to be mounted on the vertical structure for horizontally adjoining the plurality of longitudinal members of the horizontal bar column together. The horizontal bar column is mounted onto the vertical structure using one or more brackets such that an optimum angle trajectory is created for an apex shot. The processing system operates an interactive device connected with the horizontal bar column. The interactive device is configured to track shot data associated with one or more shots performed by a player practicing on the basketball training apparatus.

An interactive exercise method includes streaming exercise content to an interactive video system for display via a mirror, the exercise content including a depiction of an instructor performing a repetitive movement. A video stream of a user performing the repetitive movement is received, via a camera of the interactive video system, and the user is detected in the video stream. The user or a body portion thereof is tracked in the video stream as the user performs the repetitive movement. The method also includes generating a measure of a difference between a form of the user performing the repetitive movement and a predetermined form for the repetitive movement. A corrective movement is displayed to the user, via the display and during the display of the instructor performing the repetitive movement, based on the measure, to conform the form of the user to the predetermined form for the repetitive movement.

A system and method for monitoring performance of a physical exercise routine. The system comprises a plurality of motion and position sensors configured to generate sensory information including at least a rate of movements of a user performing the physical exercise routine; a database containing routine information representing at least an optimal execution of the physical exercise routine; a training module configured to: compare the generated sensory information to the routine information to detect at least dissimilarities respective thereof, wherein the dissimilarities indicate if the pace of performing the physical exercise routine is incorrect; provide feedback to the user with at least instructions related to correcting the pace of performing the physical exercise routine; and a display for displaying the feedback.

A method of creating a scalable dynamic jointed skeleton (DJS) model for enhancing psychomotor leaning using augmented cognition methods realized by an artificial intelligence (AI) engine or image processor. The method involves extracting a DJS model from either live motion images of video files of an athlete, teacher, or expert to create a scalable reference model for using in training, whereby the AI engine extracts physical attributes of the subject including arm length, length, torso length as well as capturing successive movements of a motor skill such as swinging a gold club including position, stance, club position, swing velocity and acceleration, twisting, and more.

An interactive exercise method includes streaming exercise content to an interactive video system for display via a mirror, the exercise content including a depiction of an instructor performing a repetitive movement. A video stream of a user performing the repetitive movement is received, via a camera of the interactive video system, and the user is detected in the video stream. The user or a body portion thereof is tracked in the video stream as the user performs the repetitive movement. The method also includes generating a measure of a difference between a form of the user performing the repetitive movement and a predetermined form for the repetitive movement. A corrective movement is displayed to the user, via the display and during the display of the instructor performing the repetitive movement, based on the measure, to conform the form of the user to the predetermined form for the repetitive movement.

Systems and methods are disclosed for generating a 3D avatar and object fitting recommendations 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 3D avatars and object fitting recommendations.

A method of detecting and identifying postures and gestures of a human user generates a reference model from a reference image and obtains an image of action or gesture being performed. The image is of a user and his flexible and hand-held portable device, and the image comprises a second identification feature. A state of a second feature of the second identification feature in the reference model can generate posture identification. The state of the second feature comprises size, shape, and location of the second identification feature in the hands of the user. A portable device and a non-volatile storage medium of a computer are also disclosed.

A method, comprising providing playback of one or more sets of three dimensional positional data of a subject performing an activity; detecting input from an editor respective to the playback of the one or more sets of three dimensional positional data; and storing parameters of the activity based on the detected input in an activity profile for use in movement based instruction.