An intelligent voice playing method includes displaying, by an electronic device, an interface of a first application, where the first application is used by a user to perform exercise training; capturing an image of a training action of the user; playing a video of a standard action, and displaying the image of the training action of the user; determining a plurality of to-be-selected voices triggered by a first action unit in the training action of the user, where the first action unit is one training action or a part of one training action; and selecting a voice from the to-be-selected voices for playing.

The present disclosure discloses a device for efficiently extracting adaptively selected contactless multi-player heart rates includes: an acquisition module that covers a court to obtain videos from a plurality of angles during players training; a valid player obtaining module configured to remove players with low contributions to training and games in the videos; a facial ROI extraction module configured to detect whether the facial ROIs of valid players contain perfect eye region features, and use the facial ROIs containing the eye region features as best facial ROIs for heart rate extraction; and an analysis and estimation module configured to analyze the detected best facial ROIs by using blind source separation, and estimate a RGB signal by a JADE algorithm to obtain the heart rate values of the valid players.

A basketball launching system for recording shooting statistics in association with locations other than passing locations. Controller(s) receive data from a user interface indicating selection of a pass location and one or more shooting locations which are spaced apart from the pass location and program a launching device to pass basketballs to a location at a basketball playing area corresponding to the selected pass location and record shooting performance information in association with an associated one of the selected shooting locations for each respective one of the passes.

A video acoustical method determines an impact point of a thrown body on a landing area, in particular for athletics throws disciplines, the body describing a trajectory in the air from a take-off area towards the landing area, the impact point being defined by the body hitting on the landing area. The method includes acquiring video exposures of the body impact on the landing area to a frame rate, each exposure showing one position of the body; calculating the body trajectory during at least the body impact on the landing area with the video exposures analysis; detecting an acoustical impact time due to the body hitting on the landing area; and determining the body impact point on the calculated trajectory with the detected acoustical impact time. A video acoustical system can determine an impact point of a thrown body on a landing area.

A paddling simulator includes a bar, a cable attached to the bar, a motor operationally coupled to the cable such that the motor can apply a force to the cable, and a controller configured to control the motor to generate a first tension in the cable during a propulsion phase of a paddling stroke and a second tension in the cable during a recovery phase of the paddling stroke.

A method may include obtaining sensor data from one or more activity sensors, each of the activity sensors being coupled to a respective area of a sports user. The method may include obtaining image data of the sports user and each of the activity sensors coupled to the sports user. The method may include identifying, by a machine learning module and based on the sensor data and the image data, a respective muscle associated with each respective area to which the activity sensors are coupled. The method may include identifying movement of the sports user based on the sensor data from the activity sensors and the identified body part. The method may include analyzing the identified movement of the sports user including evaluating a body posture of the sports user, identifying one or more movement patterns of the sports user, and/or performing an injury assessment for the sports user.

A tennis ball retriever for retrieving a tennis ball on and about a tennis court and for controllably releasing the ball includes a front-end ball collector having two spaced-apart blades defining a ball collection space. The retriever includes a means for gripping and securing a ball positioned at the fore end, and one or more detents for retaining the collected ball in the collection space until a programmed or manually-directed release toward a target location such as a tennis baseline. The retriever includes a processor-controller for controlling and directing the retriever during a retrieval session. The retriever may be remote-controlled such as by voice commands.

A system for providing golf information, the system which includes a green photographing unit for photographing an image of an area including a green on a golf course and communicatively connected to a communication network to transmit green image data to an outside, a golfer terminal that is carried by a golfer on the golf course and communicatively connected to a communication network to transmit golfer position data to the outside, and an information providing server that is communicatively connected to the communication network to generate golf information using the green image data and the golfer position data and transmit the generated golf information to the golfer terminal.

A system and method is disclosed for a surround-perspective motion annotation comprising: an image/video input for capturing and/or parsing into at least one image frame of a subject performing at least one motion from each of at least three perspectives; a vector generating module for generating a test vector or wire mesh corresponding to a pose of the subject in each of the captured/parsed frame from each of the perspectives; and an annotation module for inputting a drawing imposed on the test vector/mesh for a visual contrast against any one of a feature from the test vector/mesh from any one of the perspectives. Further disclosed embodiments include for a system and method for generating multi-perspective, color-coded deviations of a subject from a reference (color wheel). Further embodiments include for a system and method for generating an optimal motion signature (OMS) for the subject based on his or her generated color wheel.

A sports swing tracking system that has at least one computer processor, a camera system with a digital image sensor, the camera system operating at or greater than sixty frames per second at an exposure rate faster than one one-thousandth of a second. The sports swing tracking system also includes a distance calculating system designed to calculate the distance to an object of known size determined by a pixel array corresponding to the equivalent dimensions of the imaged object. The sports swing tracking system also includes a body frame pose estimator system designed to calculate the distance between each of thirteen or more body frame points and a motion mapping system designed to calculate changes in the three-dimensional location and attitude of at least one or more of the thirteen or more body frame points, an at least one ball point, and two or more points representing a sports instrument.