AI Sports Coaching Glossary

A computer vision technique that detects and tracks the positions of key body joints (keypoints) in images or video. Modern pose estimation models identify 17 to 33 landmarks per person — including shoulders, elbows, wrists, hips, knees, and ankles — and update their positions at up to 240 frames per second. SportsReflector uses pose estimation to track 25+ joints during athletic movements.

The sequence of body segments that transfer force from one to the next during an athletic movement. In a tennis serve, the kinetic chain runs from the feet through the legs, hips, trunk, shoulder, elbow, and wrist to the racquet. Each segment amplifies the force generated by the previous one. Breakdowns anywhere in the chain — such as early shoulder rotation or insufficient hip drive — reduce power and increase injury risk.

A real-time visual layer superimposed on live camera footage that displays coaching cues, movement paths, joint angle targets, and form corrections. SportsReflector's AR overlay shows the ideal movement trajectory alongside your actual motion, letting you self-correct in real time without a coach present. AR overlays are rendered at the same frame rate as the camera feed to maintain alignment with the athlete's body.

The application of mechanical principles to the study of human movement. In sports coaching, biomechanical analysis measures joint angles, angular velocities, force vectors, and timing relationships between body segments. AI-powered biomechanical analysis automates this process, producing objective measurements that previously required motion capture labs with specialized equipment.

The angle formed between two adjacent body segments at a joint, measured in degrees. For example, the elbow angle during a basketball free throw, the knee angle at the bottom of a squat, or the hip angle at address in a golf swing. Optimal joint angles vary by sport and movement phase. AI coaching apps calculate joint angles from keypoint positions and compare them against reference ranges for each movement.

The process of identifying specific anatomical landmarks in an image or video frame. In human pose estimation, keypoints correspond to joints such as the nose, eyes, ears, shoulders, elbows, wrists, hips, knees, and ankles. Deep learning models trained on large annotated datasets can detect these keypoints with sub-centimeter accuracy in real-world conditions.

A simplified representation of the human body as a set of joints (nodes) connected by limb segments (edges). Pose estimation models output a skeletal model that can be overlaid on video footage to visualize body position and movement. The skeletal model is the foundation for calculating joint angles, segment velocities, and movement timing.

A numerical rating (typically 0–100) that quantifies the quality of an athletic movement or exercise repetition. SportsReflector's form score is calculated by comparing measured biomechanical parameters — joint angles, timing, symmetry, range of motion — against sport-specific reference models. A score of 85+ indicates good technique; scores below 60 typically indicate a significant mechanical issue requiring correction.

A comparison of movement quality and joint angles between the left and right sides of the body. Asymmetries greater than 10–15% between sides are associated with elevated injury risk and compensatory movement patterns. SportsReflector's symmetry analysis flags significant left-right imbalances and tracks them over time to monitor whether training is correcting or worsening the asymmetry.

An automated evaluation of movement patterns that are statistically associated with increased injury probability. Common injury risk flags include knee valgus (inward knee collapse) during squats, excessive lumbar flexion during deadlifts, and early trunk rotation during throwing motions. AI injury risk assessment does not diagnose injuries but identifies movement patterns that warrant attention from a medical professional.

A visualization that estimates which muscle groups are most active during a given movement based on joint angles, segment positions, and movement velocity. While not a direct measurement of electrical muscle activity (EMG), AI-based muscle activation mapping provides an approximation of primary and secondary muscle engagement, helping athletes understand which muscles are driving their movements.

The angular difference between hip rotation and shoulder rotation at the top of the backswing in golf. A larger X-factor (typically 45–55 degrees in professional players) creates greater elastic energy in the trunk muscles, which is released during the downswing to generate clubhead speed. AI golf analysis measures X-factor by calculating the difference between hip and shoulder rotation angles at the transition point.

The rotational lag between the hips and shoulders during rotational athletic movements such as golf swings, baseball swings, and tennis groundstrokes. Effective hip-shoulder separation allows the hips to initiate the downswing while the shoulders remain coiled, creating a stretch-shortening cycle in the trunk muscles that amplifies power. AI analysis measures this separation in degrees and milliseconds.

The order and timing in which body segments reach their peak rotational velocity during a movement. In an efficient golf swing, the kinematic sequence progresses from pelvis to thorax to lead arm to club, with each segment accelerating and decelerating in sequence to transfer energy efficiently. Disruptions to the kinematic sequence — such as the shoulders peaking before the hips — reduce power and consistency.

A technique that reconstructs the three-dimensional positions of body joints from video footage, capturing depth information that 2D analysis cannot. Traditional 3D motion analysis required multiple synchronized cameras and reflective markers. Modern AI approaches (used by platforms like Sportsbox AI) can estimate 3D joint positions from a single smartphone camera using deep learning models trained on large 3D motion capture datasets.

The review of video footage one frame at a time to examine body position at specific moments during a movement. At 240 frames per second, each frame represents approximately 4 milliseconds of movement — sufficient to capture the position of the body at impact in a golf swing, the release point in a basketball shot, or the moment of maximum knee flexion in a squat.

A biomechanical template representing optimal technique for a specific movement, derived from analysis of elite athletes or established coaching principles. AI coaching apps compare an athlete's measured parameters against the reference model to calculate form scores and identify deviations. Reference models are sport-specific and may vary by skill level, body type, and movement style.

Coaching corrections and form cues delivered during or immediately after a movement, rather than in a post-session review. Real-time feedback is most effective when it is specific, actionable, and delivered within the motor learning window — typically within 3 seconds of the movement. SportsReflector's live camera mode provides real-time form scoring and AR overlay guidance during training.

The simultaneous or sequential analysis of a movement from multiple camera angles — typically face-on and down-the-line for golf, or front and side views for gym exercises. Multi-angle analysis provides a more complete picture of movement quality, as some faults (such as swing plane errors) are only visible from specific angles. SportsReflector supports multi-angle video upload and analysis.

The extent of movement available at a joint, measured in degrees. Adequate range of motion is a prerequisite for correct technique in most sports — insufficient hip mobility limits squat depth, restricted shoulder mobility affects overhead pressing form, and limited thoracic rotation reduces golf swing turn. AI coaching apps measure range of motion during movements and flag restrictions that may indicate mobility limitations.

An AI analysis feature that identifies when an athlete's form begins to deteriorate due to fatigue during a training session. Fatigue-related form breakdown is a primary cause of training injuries. SportsReflector's fatigue detection tracks form score trends across multiple repetitions and alerts the athlete when technique degradation reaches a threshold that increases injury risk.

An inward deviation of the knee joint during weight-bearing movements such as squats, lunges, and landings. Knee valgus is associated with increased ACL injury risk and is one of the most commonly flagged form errors in AI gym workout analysis. It is often caused by weak hip abductors, limited ankle dorsiflexion, or poor motor control. AI coaching apps detect valgus collapse by measuring the medial deviation of the knee keypoint relative to the hip and ankle.

A colloquial term for posterior pelvic tilt at the bottom of a squat, where the pelvis tucks under the spine and causes lumbar flexion. Butt wink is associated with increased compressive load on the lumbar discs and is a common form error flagged by AI squat analysis. It is often caused by limited hip flexion mobility or ankle dorsiflexion restriction. AI coaching apps detect butt wink by tracking the angle of the pelvis relative to the spine.

The process by which the nervous system acquires, refines, and stores movement patterns through practice. Effective motor learning requires accurate feedback delivered at the right time and frequency. AI coaching accelerates motor learning by providing objective, consistent feedback on every repetition — eliminating the subjective variability of human observation and the delay of waiting for a coach's response.

A composite metric that aggregates multiple biomechanical measurements into a single 0–100 rating for a specific athletic movement. Each sport has its own technique scoring model with different weighted parameters. For example, a basketball free throw technique score weights elbow alignment, release angle, and follow-through, while a golf swing technique score weights spine angle, hip rotation, and weight transfer.