Train Like A Machine

The use of smart fitness sensors has increased notably in recent years. They are integrated into everyday devices such as fitness watches or wristbands and are often an important component of the individual training. Simultaneously, scientists are increasingly drawing attention to this field. A focus on methods such as pose estimation and artificial intelligence can be observed.

In this project, students explore how sensors and machine learning algorithms can be used to analyze sports exercises. Students work as teams on tasks they set themselves and in coordination with the project supervisors. Topics include, among others, the process of data preprocessing, the segmentation or labeling of data as well as feature engineering and classification.

André and Jan are happy to answer any questions! The latest semester announcement can be found here (as of April 2022).

Summer semester 2022 (2 groups)

Currently ongoing …

Winter semester 2021 (5 groups)

Group „DailyChallenge“
With the help of IMU sensors, squats were assessed in real time. The assessment was realized using the Dynamic Time Warping algorithm.

Group „Bauch-Beine-Po“
Using IMU sensors, an algorithm was developed to determine how many repetitions a person can still perform during a barbell exercise (repetitions in reserve).

Group „SmartUp“
Based on IMU sensors, the focus was placed on the detection of correctly executed pull-ups.

Group „Boxingmachine“
The goal was to classify correctly and incorrectly executed straight punches (Krav Maga) as such. IMU sensors were also used by this group.

Group „Tennisarm“
A table tennis serve detection system was implemented using an IMU sensor and machine learning.

Train Like A Machine

Summer semester 2022 (2 groups)

Winter semester 2021 (5 groups)

People

André Jeworutzki

Jan Schwarzer