New smart garment tracks a person's posture and exercise routine

New smart garment tracks a person's posture and exercise routine

Researchers at Cornell University have developed a new type of smart clothing that can track a person's posture and exercise routine but looks, wears and washes like a regular shirt -.

The new technology, called Seamfit, uses flexible conductive threads sewn into the neck, arm and side seams of a standard short-sleeve T-shirt.

The user does not need to manually log their workout as an artificial intelligence pipeline detects movements, identifies the exercise and counts repetitions. Afterwards, the user simply removes a circuit board on the back neckline and throws the sweaty shirt into the washing machine.

According to Catherine Yu, graduate student and lead researcher on the project, most existing body tracking clothing is tight and restrictive or embedded with bulky sensors.

We were interested in how we could make clothes smart without making them bulky or unusable, and to push practicality so that people could treat them the way they normally treat their clothes. “

Catherine Yu, graduate student and lead researcher on the project

Alternatively, athletes can choose fitness trackers such as smartwatches or rings, but these are additional devices that people may not want to wear while exercising and cannot track movement throughout the body.

The study, “SeamFit: Towards practical smart clothing for automated exercise logging,” published in the Proceedings of the ACM on interactive, mobile, wearable, and ubiquitous technologies, will be presented at UBIComp/ISWC 2025 in October.

To test the shirts' performance, the team recruited volunteers to perform a series of 14 exercises—including lunges, sit-ups, and bicep curls—during Seamfits. Without calibration or training for each user, SeamFit's model classified exercises with 93.4% accuracy and successfully counted repetitions. Counts that averaged less than one.

Seamfit works because when people exercise, the threads' capacity - their ability to store charge - changes as the threads move, deform and interact with the human body. The circuit board on the back cutout measures the capacities and transmits them to a computer via a Bluetooth connection. A customized, lightweight signal processing and machine learning pipeline then decodes the movements.

More broadly, this type of technology could help with human-AI interaction, as by tracking human movements and activities, AI can better understand when to interact and when to wait - e.g. B. when someone eats or sleeps.

“While this paper demonstrated the approach for a simple garment, we believe it can be easily adapted to a wide range of garments and can take advantage of the complex stitching patterns of advanced sportswear,” said co-author François Guimbretière, professor of information science.

Sources: