DriverGaze360: OmniDirectional Driver Attention with Object-Level Guidance

TL;DR

This paper introduces DriverGaze360, a comprehensive 360-degree driver attention dataset and a panoramic attention prediction model that jointly learns attention maps and object guidance, improving spatial awareness in autonomous driving scenarios.

Contribution

The paper presents a large-scale 360-degree driver gaze dataset and a novel panoramic attention prediction network with object-level guidance, addressing limitations of previous narrow field-of-view approaches.

Findings

DriverGaze360-Net achieves state-of-the-art performance on panoramic attention prediction.

The dataset contains approximately 1 million gaze-labeled frames from 19 drivers.

Joint learning of attention maps and object guidance enhances spatial awareness.

Abstract

Predicting driver attention is a critical problem for developing explainable autonomous driving systems and understanding driver behavior in mixed human-autonomous vehicle traffic scenarios. Although significant progress has been made through large-scale driver attention datasets and deep learning architectures, existing works are constrained by narrow frontal field-of-view and limited driving diversity. Consequently, they fail to capture the full spatial context of driving environments, especially during lane changes, turns, and interactions involving peripheral objects such as pedestrians or cyclists. In this paper, we introduce DriverGaze360, a large-scale 360$^\circ$ field of view driver attention dataset, containing $\sim$1 million gaze-labeled frames collected from 19 human drivers, enabling comprehensive omnidirectional modeling of driver gaze behavior. Moreover, our panoramic attention prediction approach, DriverGaze360-Net, jointly learns attention maps and attended objects by employing an auxiliary semantic segmentation head. This improves spatial awareness and attention prediction across wide panoramic inputs. Extensive experiments demonstrate that DriverGaze360-Net achieves state-of-the-art attention prediction performance on multiple metrics on panoramic driving images. Dataset and method available at https://dfki-av.github.io/drivergaze360.