ITSC 2025 Paper Abstract

Paper WE-EA-T14.1

Nakazawa, Riku (Tokai University), Takenaka, Satoru (Mazda Motor Corporation), Homma, Yuya (Mazda Motor Corporation), Sato, Ariki (Mazda Motor Corporation), Kuwahara, Junichiro (Mazda Motor Corporation), Takemura, Kentaro (Tokai University)

Implicit Calibration of Point-Of-Gaze on Scene Image Using Smooth-Pursuit Eye Movements for Driver Monitoring

Scheduled for presentation during the Regular Session "S14b-Human Factors and Human Machine Interaction in Automated Driving" (WE-EA-T14), Wednesday, November 19, 2025, 13:30−13:50, Currumbin

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), November 18-21, 2025, Gold Coast, Australia

This information is tentative and subject to change. Compiled on October 19, 2025

Keywords Human-Machine Interaction Systems for Enhanced Driver Assistance and Safety

Abstract

Advanced driver assistance systems that estimate driver attention have been actively studied to reduce traffic accidents and improve driving comfort. Although significant progress has been made in the field of object detection, it is difficult to estimate driver attention effectively because there are several issues in calculating the point-of-gaze on scene images. Generally, user calibration is performed in advance; however, this is not a practical solution. Therefore, we propose implicit calibration using smooth-pursuit eye movements, in which the point-of-gaze is corrected using an optimal correction vector and regression. Experiments were conducted on a test course and public roads to demonstrate the effectiveness and feasibility of the proposed method while also highlighting its current limitations.