What Do You See in Vehicle? Comprehensive Vision Solution for In-Vehicle Gaze Estimation

TL;DR

This paper introduces IVGaze, a comprehensive dataset and novel transformer-based methods for in-vehicle gaze estimation, addressing challenges of low-resolution images and annotation in real driving scenarios.

Contribution

The paper presents a new dataset, IVGaze, and innovative transformer-based models, GazeDPTR and Gaze Zone Classification, advancing in-vehicle gaze estimation research.

Findings

GazeDPTR achieves state-of-the-art performance on IVGaze.

The proposed gaze zone classification method outperforms existing approaches.

The dataset enables more accurate and robust in-vehicle gaze analysis.

Abstract

Driver's eye gaze holds a wealth of cognitive and intentional cues crucial for intelligent vehicles. Despite its significance, research on in-vehicle gaze estimation remains limited due to the scarcity of comprehensive and well-annotated datasets in real driving scenarios. In this paper, we present three novel elements to advance in-vehicle gaze research. Firstly, we introduce IVGaze, a pioneering dataset capturing in-vehicle gaze, collected from 125 subjects and covering a large range of gaze and head poses within vehicles. Conventional gaze collection systems are inadequate for in-vehicle use. In this dataset, we propose a new vision-based solution for in-vehicle gaze collection, introducing a refined gaze target calibration method to tackle annotation challenges. Second, our research focuses on in-vehicle gaze estimation leveraging the IVGaze. In-vehicle face images often suffer from low resolution, prompting our introduction of a gaze pyramid transformer that leverages transformer-based multilevel features integration. Expanding upon this, we introduce the dual-stream gaze pyramid transformer (GazeDPTR). Employing perspective transformation, we rotate virtual cameras to normalize images, utilizing camera pose to merge normalized and original images for accurate gaze estimation. GazeDPTR shows state-of-the-art performance on the IVGaze dataset. Thirdly, we explore a novel strategy for gaze zone classification by extending the GazeDPTR. A foundational tri-plane and project gaze onto these planes are newly defined. Leveraging both positional features from the projection points and visual attributes from images, we achieve superior performance compared to relying solely on visual features, substantiating the advantage of gaze estimation. Our project is available at https://yihua.zone/work/ivgaze.