Provided is an adjustable basketball training device that includes a weighted base portion to provide upright support to the device on a flat surface, a main leg portion connected at a first end thereof with the base portion and adjustable therefrom in a vertical direction, extension arm portions securely connected together, and connected with a second end of the main leg portion and extending in a horizontal direction, each having a sensor sensing physical contact of the user with each extension arm portion, start and stop operation switch portions connected to the second end of the main leg portion and an end of an extension arm portion opposite an end connected with another extension arm portion of the extension arm portions attached to the second end of the main leg portion, and a digital counter which counts a total number of times the user physically contacts each extension arm portion.

Methods and systems for 3D ball trajectory reconstruction are disclosed. The methods and systems perform steps of receiving a 2D ball trajectory, a shooter's on-ground foot location, and a camera projection matrix; generating on-ground trajectory line assumptions based on the shooter's on-ground foot location and the 2D trajectory; reconstructing a candidate 3D trajectory for each on-ground trajectory line assumption, by determining a ball height for each on-ground projection point in the on-ground trajectory line and by curve fitting; evaluating each candidate 3D trajectory and selecting one with a best score as the reconstructed 3D ball trajectory. Embodiments of the present invention enable a resource-limited mobile device such as a smartphone to conduct the aforementioned steps. Also disclosed are benefits of the new methods, and alternative embodiments of implementation.

Techniques where a computer or mobile device performs video analysis of a person performing a physical activity such as a basketball jump shot are described. The computer or mobile device performs video analysis to (1) determine a frame of the video data that depicts a body position of the person in a release phase of the basketball jump shot, (2) process pixels in the determined frame to determine data relating to a release point for the basketball jump shot, (3) process pixels in a plurality of the frames to determine whether the basketball jump shot resulted in the basketball going through a hoop as a made shot, and (4) repeat these operations for a plurality of basketball jump shots by the person to thereby track the made shots and the release point data for the plurality of basketball jump shots by the person.

A basketball training assembly includes a cart that is rollable along a support surface. The cart can be positioned a selected distance from a basketball hoop on a basketball court. A lift is coupled to and extends upwardly from the cart. The lift is turned on to extend a predetermined distance upwardly from a home position on the cart. A barrier is coupled to the lift and the lift lifts the barrier the predetermined distance from the home position when the lift is turned on to simulates a defensive basketball player. A plurality of motion sensors is each coupled to the barrier to sense motion of a basketball player approaching the barrier. The lift is turned on when one or more of the motion sensors senses motion. Thus, the lift lifts the barrier when the basketball player approaches the barrier to take a shot during basketball practice.

Systems, methods, and other embodiments associated with instruction production are described. In one example, a system can comprise a difference component that makes an identification of a difference between an actual action of a user and a standard action for the user. The system also can comprise an instruction component that produces an instruction to instruct the user to change from the action of the user to the standard action for the user, where production of the instruction is based, at least in part, on the difference. The system further can comprise a non-transitory computer-readable medium configured to retain the instruction. Additionally, the system can comprise an output component configured to cause disclosure of the instruction.

Predicted feedback for improved motor training is advanced by detecting a trajectory and velocity of an object launched from a launch point by a human via a plurality of time-sequenced images from a plurality of cameras positioned at different angles relative to the launched object. From the images, an extrapolated pathway of the object toward a target is projected; and an evaluation is made as to whether the object, when following the extrapolated pathway, is projected to land within or pass through the target. A communication is then made to the human as to whether the object is projected to land within or pass through the target, wherein the communication occurs after launch yet substantially before the launched object would reach the target or a location at a distance from the launch point that matches the distance from the launch point to the target.

The disclosure provides embodiments of a training device and related methods of use.

A Basketball Training Article is provided and includes a hoop shelf having a shelf top, a shelf bottom, a shelf front and a shelf rear. The Basketball Training Article further includes a first gusset and a second gusset, wherein the first gusset and the second gusset are located securely associated with the shelf bottom to be located proximate the shelf rear, wherein the first gusset and the second gusset are configured to define a gusset cavity located between the first gusset and the second gusset.

Described is a system for predicting multi-agent movements. A Radon Cumulative Distribution Transform (Radon-CDT) is applied to pairs of signature-formations representing agent movements. Canonical correlation analysis (CCA) components are identified for the pairs of signature-formations. Then, a relationship between the pairs of signature formations is learned using the CCA components. A counter signature-formation for a new dataset is predicted using the learned relationship and a new signature-formation. Control parameters of a device can be adjusted based on the predicted counter signature-formation.

Wearable electronic devices that are designed to be worn on the head of a user while the user is swimming can determine swimming strokes and swimming performances of the user using motion sensors. Using a sound speaker, the wearable electronic device can play music and provide audio feedback to the swimmer. By comparing the swimming performance of the swimmer wearing the device with previously recorded swimming data, the wearable electronic device can provide audio comparison results to the swimmer while the swimmer is swimming in water. The wearable electronic device can also support similar functions for jumping actions.