An Investigation on the Feasibility of Uncalibrated and Unconstrained Gaze Tracking for Human Assistive Applications by Using Head Pose Estimation

Abstract

This paper investigates the possibility of accurately detecting and tracking human gaze by using an unconstrained and noninvasive approach based on the head pose information extracted by an RGB-D device. The main advantages of the proposed solution are that it can operate in a totally unconstrained environment, it does not require any initial calibration and it can work in real-time. These features make it suitable for being used to assist human in everyday life (e.g., remote device control) or in specific actions (e.g., rehabilitation), and in general in all those applications where it is not possible to ask for user cooperation (e.g., when users with neurological impairments are involved). To evaluate gaze estimation accuracy, the proposed approach has been largely tested and results are then compared with the leading methods in the state of the art, which, in general, make use of strong constraints on the people movements, invasive/additional hardware and supervised pattern recognition modules. Experimental tests demonstrated that, in most cases, the errors in gaze estimation are comparable to the state of the art methods, although it works without additional constraints, calibration and supervised learning.

Deep Head Pose: Gaze-Direction Estimation in Multimodal Video

“…An iterative closest point (ICP) based mesh fitting approach has been employed for head pose detection [9], [18]. In [10] the candidate head poses are rendered and matched to the input depth image and the 6 degree of freedom pose is solved by optimizing via particle swarm optimisation.…”

“…This is distinct from approaches defined in literature. In [18] head pose is used for estimating gaze through a fixed sized disc surrounding the intersection point of the head pose ray and the object/camera plane. This approach does not incorporate the confidence of the head pose estimate to peak or diffuse the gaze estimate that our technique proposes.…”

Considered Factors of Online News Based on Respondents’ Eye Activity Using Eye-Tracker Analysis

“…The BAI questionnaire assesses the level of respondents' anxiety using a scale based on the respondents' answers to the existing 20 questions. There are four scales in BAI, namely low (0-7), medium (8)(9)(10)(11)(12)(13)(14)(15), high (16)(17)(18)(19)(20)(21)(22)(23)(24)(25), and severe . In this experiment, the BAI questionnaire was filled out by respondents after reading the three news articles provided in the context of real news content, and this can provoke impulses and respondents' memories to trigger anxiety.…”

“…This research focuses more on eye gaze because it acts as a basis to analyze user activities and performances due to its direct relationship with the concept of "attention" [21]. Automatic gaze tracking enables several applications in the fields of human-computer interaction (HCI) and human behavior analysis [22]. This study analyzed and evaluated eye-tracker measurements, including fixation time, total fixation, and gaze duration [23], of the respondents when viewing multimedia information, and analysis of eye-tracker measurements resulted in gaze data (gaze ratio and gaze duration).…”

Image Classification Using Naive Bayes Model for Deep Head Pose Estimation

“…An iterative closest point (ICP) based mesh fitting method has been proposed for head pose detection [10]. Work on head pose regression has been introduced for scene and human interaction understanding [3].…”