Few-shot identification of individuals in sports : the case of darts

Vec, Val (avtor), Kos, Anton (avtor), Bie, Rongfang (avtor), Jiao, Libin (avtor), Wang, Haodi (avtor), Zhang, Zheng (avtor), Tomažič, Sašo (avtor), Umek, Anton (avtor)

This paper contains an analysis of methods for person classification based on signals from wearable IMU sensors during sports. While this problem has been investigated in prior work, existing approaches have not addressed it within the context of few-shot or minimaldata scenarios. A few-shot scenario is especially useful as the main use case for person identification in sports systems is to be integrated into personalised biofeedback systems in sports. Such systems should provide personalised feedback that helps athletes learn faster. When introducing a new user, it is impractical to expect them to first collect many recordings. We demonstrate that the problem can be solved with over 90% accuracy in both open-set and closed-set scenarios using established methods. However, the challenge arises when applying few-shot methods, which do not require retraining the model to recognise new people. Most few-shot methods perform poorly due to feature extractors that learn dataset-specific representations, limiting their generalizability. To overcome this, we propose a combination of an unsupervised feature extractor and a prototypical network. This approach achieves 91.8% accuracy in the five-shot closed-set setting and 81.5% accuracy in the open-set setting, with a 99.6% rejection rate for unknown athletes.

• Jezik: Angleški jezik
• Ključne besede: biomechanical feedback, few-shot learning, open-set classification, person recognition, sensors, sports, unsupervised learning
• Vrsta gradiva: Članek v reviji
• Tipologija: 1.01 - Izvirni znanstveni članek
• Organizacija: FE - Fakulteta za elektrotehniko
• Status publikacije: Objavljeno
• Različica publikacije: Objavljena publikacija
• Leto izida: 2025
• Št. strani: 20 str.
• Številčenje: Vol. 16, issue 10,art. 865
• PID: 20.500.12556/RUL-174674
• UDK: 621.39:681.5
• ISSN pri članku: 2078-2489
• COBISS.SI-ID: 252329219
• Datum objave v RUL: 08.10.2025

Gradivo je del revije

• Naslov: Information
• Skrajšan naslov: Information
• Založnik: MDPI
• ISSN: 2078-2489
• COBISS.SI-ID: 18497046

Licence

• Licenca: CC BY 4.0, Creative Commons Priznanje avtorstva 4.0 Mednarodna
• Povezava: http://creativecommons.org/licenses/by/4.0/deed.sl
• Opis: To je standardna licenca Creative Commons, ki daje uporabnikom največ možnosti za nadaljnjo uporabo dela, pri čemer morajo navesti avtorja.

Sekundarni jezik

• Jezik: Slovenski jezik
• Ključne besede: biomehanska povratna informacija, učenje z malo primeri, klasifikacija z odprtim naborom razredov, prepoznava oseb, senzorji, šport, nenadzorovano učenje

Projekti

• Financer: ARIS - Javna agencija za znanstvenoraziskovalno in inovacijsko dejavnost Republike Slovenije
• Številka projekta: P2-0246
• Naslov: ICT4QoL - Informacijsko komunikacijske tehnologije za kakovostno življenje

• Financer: Central Universities of China
• Številka projekta: 2024ZKPYZN01