Continuous Driver's Gaze Zone Estimation Using RGB-D Camera.

Yafei Wang,Xianping Fu,Zetian Mi,Guoliang Yuan,Jinjia Peng,Xueyan Ding,Zheng Liang

doi:10.3390/s19061287

Abstract

The driver gaze zone is an indicator of a driver’s attention and plays an important role in the driver’s activity monitoring. Due to the bad initialization of point-cloud transformation, gaze zone systems using RGB-D cameras and ICP (Iterative Closet Points) algorithm do not work well under long-time head motion. In this work, a solution for a continuous driver gaze zone estimation system in real-world driving situations is proposed, combining multi-zone ICP-based head pose tracking and appearance-based gaze estimation. To initiate and update the coarse transformation of ICP, a particle filter with auxiliary sampling is employed for head state tracking, which accelerates the iterative convergence of ICP. Multiple templates for different gaze zone are applied to balance the templates revision of ICP under large head movement. For the RGB information, an appearance-based gaze estimation method with two-stage neighbor selection is utilized, which treats the gaze prediction as the combination of neighbor query (in head pose and eye image feature space) and linear regression (between eye image feature space and gaze angle space). The experimental results show that the proposed method outperforms the baseline methods on gaze estimation, and can provide a stable head pose tracking for driver behavior analysis in real-world driving scenarios.

Highlights

Driver distraction and inattention are the key factors that cause traffic accidents
Driver head pose referring to our gaze zone are focused on areas which yaw ranges from −60 degree to +60 degree, pitch ranges from −45 degree to +45 degree and roll ranges from −10 degree to +10 degree
While the head pose estimation is applied on the 3D point-cloud that derives from the depth data, the gaze estimation is mainly performed on the RGB data

Summary

Introduction

Driver distraction and inattention are the key factors that cause traffic accidents. Distracted driving increases the probability of crashes as the drivers shift their attention from driving. Human-centric driving monitor technologies can be divided into two categories, intrusive-sensing technologies and remote-sensing technologies. While the intrusive-sensing technologies [1] detect head motion from attached head orientation sensors, some biomedical sensing technologies [2,3] measure the signals from the driver immediately and intuitively, but disturb the driver in the process, leading to inconvenience complaints. Vision-based applications usually mount the remote cameras inside the vehicle, and are capable of monitoring the driver in a non-contact and non-invasive way. These applications benefit from the advance in information technologies, and can present computer vision algorithms based on low-cost sensors.

Methods

Results

Conclusion