Continuous Head Movement Estimator for Driver Assistance: Issues, Algorithms, and On-Road Evaluations

Abstract

Abstract-Analysis of a driver's head behavior is an integral part of a driver monitoring system. In particular, the head pose and dynamics are strong indicators of a driver's focus of attention. Many existing state-of-the-art head dynamic analyzers are, however, limited to single-camera perspectives, which are susceptible to occlusion of facial features from spatially large head movements away from the frontal pose. Nonfrontal glances away from the road ahead, however, are of special interest since interesting events, which are critical to driver safety, occur during those times. In this paper, we present a distributed camera framework for head movement analysis, with emphasis on the ability to robustly and continuously operate even during large head movements. The proposed system tracks facial features and analyzes their geometric configuration to estimate the head pose using a 3-D model. We present two such solutions that additionally exploit the constraints that are present in a driving context and video data to improve tracking accuracy and computation time. Furthermore, we conduct a thorough comparative study with different camera configurations. For experimental evaluations, we collected a novel head pose data set from naturalistic on-road driving in urban streets and freeways, with particular emphasis on events inducing spatially large head movements (e.g., merge and lane change). Our analyses show promising results.

Robust and continuous estimation of driver gaze zone by dynamic analysis of multiple face videos

“…To address above concerns, we have used distributed camera setup as proposed in [24] to continuously and accurately track head pose over wide operating range. Unlike stereo setup, the system does not require large overlap between two cameras.…”

“…A perspective selection procedure at later stage provides the final head pose estimation. We present a brief description of the head pose estimation method and refer readers to [24] for algorithmic details including camera selection and 'optimal' camera position determination. We provide details about the features extracted from the head pose and its dynamic, which is used by a classifier to determine the zone-membership (a probability that the driver's gaze belongs to a given gaze zone).…”

“…The challenge, however, lies in detecting the landmarks accurately and reliably. With recent advancement in robust facial landmark tracking [25], [26], even during partial occlusion and presence of glasses, geometric approaches have shown great potentials [24]. In our system, we track landmarks like eye corners, nose corners and nose tip as shown in Figure 1.…”

Where is the driver looking: Analysis of head, eye and iris for robust gaze zone estimation

“…Vision based systems are commonly used for this purpose as they provide non-contact and non-invasive solution. In recent years, a number of efforts [10], [11] have been made towards robust and continuous monitoring of the driver. Such systems are often focused on head pose alone due to robustness requirement.…”

Vision on Wheels: Looking at Driver, Vehicle, and Surround for On-Road Maneuver Analysis

“…Unfortunately, many head pose trackers do not provide a large operational range, and may fail when the driver is not looking forward [19]. Therefore, we follow the setup of [19] where a two camera system provides a simple solution to mitigate the problem.…”