Wearable Soccer Shooting Analytics System

Soccer is the most widely played sport in the world, yet many players lack access to the coaching and training resources needed to improve technical skills such as shooting accuracy. Developing proper shooting mechanics often requires professional coaching, repeated practice with a goalkeeper, or access to specialized training facilities. As a result, many athletes rely on trial-and-error practice without receiving objective feedback about their technique. Most existing sports wearables focus on general performance metrics such as distance traveled, running speed, or heart rate. While useful, these measurements do not analyze the biomechanics of specific soccer skills such as kicking mechanics. In soccer, foot orientation at the moment of ball contact strongly influences shot direction and accuracy. Without quantitative measurements of this motion, players have a limited ability to understand or correct their shooting technique. The FootyTech project addresses this problem by developing a wearable sensing system integrated into a soccer cleat insole that measures foot orientation during a kick. Using embedded sensors and wireless communication, the system provides technique feedback through a mobile application. The goal is to create an accessible training tool that allows players to improve their shooting ability using objective motion data rather than subjective observation. FootyTech uses embedded sensing hardware, wireless communication, and signal processing to analyze soccer kicking mechanics. The system is built around the Seeed nRF52840 Sense, which integrates a six-axis inertial measurement unit (IMU) and a Bluetooth Low Energy (BLE) microcontroller in a compact form factor. The IMU measures three-axis acceleration and three-axis angular velocity to capture the linear and rotational motion of the foot during a kick. Embedded firmware continuously samples the sensor data and detects kick events using threshold-based analysis of acceleration and angular velocity. Once a kick is detected, a short window of sensor data is recorded and transmitted to a mobile application via BLE. The mobile application stores the sensor data and allows the user to enter the intended and actual shot location using a graphical goal interface. The system uses a rule-based analysis framework. Signal processing techniques extract features such as foot orientation at impact and peak angular velocity. These features are evaluated using predefined thresholds to determine technique consistency and provide feedback. The FootyTech prototype consists of an embedded sensing module, a wireless communication interface, and a mobile application. The sensing module is powered by a small lithium polymer battery. The electronics are housed in a protective TPU enclosure that is 3D printed and placed within a soccer cleat insole. The sensor is positioned near the ball of the foot where contact with the soccer ball typically occurs. This placement allows the IMU to measure the rotational orientation of the striking surface during a kick. Orientation features are then analyzed to evaluate shot consistency and technique. Initial testing confirms that the IMU can capture the short-duration dynamics of a kicking motion while achieving a sampling rate close to 800 Hz. Wireless communication tests show reliable data transmission between the sensor module and host device. Early data collection experiments demonstrate clear patterns in acceleration and angular velocity during kicking events. System performance will be assessed by analyzing prediction accuracy and consistency across repeated kicks. FootyTech provides an affordable and portable training tool that helps players improve their shooting technique using objective data. Unlike professional motion capture systems, the wearable design allows athletes to receive feedback during independent practice sessions without specialized equipment. The system could be used by individual players, youth academies, or coaches seeking additional performance data. Future development could integrate additional sensors or machine learning techniques to improve prediction accuracy and expand functionality. Overall, the project demonstrates how wearable embedded systems can be applied to sports training to provide accessible performance analysis and support athletic skill development.