Low Cost Real-time Eye Tracking System for Motorsports

Eye-tracking technology can be used to determine reaction time and cognitive abilities of a subject based on response time to visual changes and analysis of focus points and duration. In the context of motorsports, quantifying driver visual data adds to the wealth of information required for the mar...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:2022 29th IEEE International Conference on Electronics, Circuits and Systems (ICECS) s. 1 - 4
Hlavní autori: Xia, Yuanjie, Lunardi, Andrew, Heidari, Hadi, Ghannam, Rami
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 24.10.2022
Predmet:
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Eye-tracking technology can be used to determine reaction time and cognitive abilities of a subject based on response time to visual changes and analysis of focus points and duration. In the context of motorsports, quantifying driver visual data adds to the wealth of information required for the marginal performance gains that make up motorsport competition. Specifically, the gaze of drivers can be used to analyze and assess driving abilities and improve driving performance. Despite eye trackers being perfectly suited for this purpose, their high cost may impede their penetration in the motorsports industry. Therefore, we demonstrate a low-cost wearable real-time eye tracking system for motor sport applications. This system was mounted on a racing helmet to monitor the driver's gaze in real-time. A dual-camera system was used to capture both eye image and front view. The eye image was processed using OpenCV-Python to determine the gaze coordinates. Moreover, the gaze position was mapped into the front view to determine the wearer's line of sight. The eye tracking helmet was tested and demonstrated good accuracy, where the deviation angle was 3.8 degrees. These promising results further add to the growing body of knowledge in low cost eye trackers.
DOI:10.1109/ICECS202256217.2022.9970888