FIXEIN: A Wearable and Modular Eye Tracking System Based-on ROM and PETA for Real-time and Accurate Gaze Data
IEEE Sensors Journal, 2026 (SCI-Expanded, Scopus)
- Yayın Türü: Makale / Tam Makale
- Basım Tarihi: 2026
- Doi Numarası: 10.1109/jsen.2026.3734387
- Dergi Adı: IEEE Sensors Journal
- Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Aerospace Database, Compendex, INSPEC, Materials Science & Engineering Collection (ProQuest), Technology Collection (ProQuest)
- Anahtar Kelimeler: 3D printing, eye tracking system, marker detection, modular system, pupil detection, real-time system
- Yıldız Teknik Üniversitesi Adresli: Evet
Özet
Wearable Eye Tracking Systems (ETS) are increasingly used in applications such as behavioral analysis, medical diagnostics, education, and device control. However, existing ETS platforms are generally optimized for accuracy or hardware compactness while providing limited adaptability for procedure-specific experimental requirements. In many cases, modifying commercial or DIY systems requires substantial technical expertise. This study presents FIXEIN, a wearable and modular ETS architecture designed to improve adaptability across diverse experimental procedures, which can be solved with 2D calibration and pupillometry. FIXEIN introduces modularity at the hardware, and software levels, supporting plug-and-play sensor replacement, additional sensor integration, adjustable eye-camera positioning, interchangeable frame structures, and compatibility with users’ own eyeglasses. The software pipeline is designed as a plug-in–based structure enabling configurable pupil-detection and processing components. To validate the proposed architecture, the Retro Oriented Mind (ROM) pupil detector and the PETA correction framework were integrated as default pupil-processing modules. Experimental results show that FIXEIN operates at up to 120 Hz, achieves 98.85% test accuracy with 0.824° average angular error, and maintains a wearable configuration with 46–62 g facial load. These results indicate that experimentadaptive and modular ETS architectures can support real-time gaze tracking without sacrificing operational stability or usability.