Convolutional Neural Network Implementation for Eye-Gaze Estimation on Low-Quality Consumer Imaging Systems

Abstract

Accurate and efficient eye gaze estimation is important for emerging consumer electronic systems such as driver monitoring systems and novel user interfaces. Such systems are required to operate reliably in difficult, unconstrained environments with low power consumption and at minimal cost. In this paper a new hardware friendly, convolutional neural network model with minimal computational requirements is introduced and assessed for efficient appearance-based gaze estimation. The model is tested and compared against existing appearance based CNN approaches, achieving better eye gaze accuracy with significantly fewer computational requirements. A brief updated literature review is also provided.

Deep Fusion for 3D Gaze Estimation From Natural Face Images Using Multi-Stream CNNs

“…They typically utilize a single camera to capture the eye images [20], [31] and can predict the gaze with low-resolution images. There are several appearance-based gaze estimation methods such as adaptive linear regression ALR [37], artificial neural networks [17], [18], [38], linear interpolation [31], visual saliency mapping [39], and Gaussian process regression [30]. Previously, appearance-based method operated on a stationary head pose and required a specific training data for each person [30], [31], [37].…”

“…Krafka et al initially proposed a weight sharing mechanism where they used an Alex-net like architecture to estimate a 2D gaze from still images [17]. Given that a face has two eyes, it seems reasonable to use dual eye channels to estimate a gaze [18]. Since eye gaze behavior is not static, the head movement is responsible for a gaze to locate a target of interest.…”

Content-Aware Eye Tracking for Autostereoscopic 3D Display

“…Further, smartphones and digital cameras can use the eye tracking method for autofocus on human eyes rather than whole faces [ 10 ]. Additionally, when the eye-position-tracking method is extended to gaze-tracking techniques when combined with eye glints information, its application extends to a variety of human–machine interactions [ 11 , 12 , 13 ].…”

Feature Point Registration Model of Farmland Surface and Its Application Based on a Monocular Camera

“…With the development of computer technology, currently, smart cameras are widely used in navigation, positioning, tracking, obstacle avoidance, monitoring, etc. [1,2]. Among them, visual measurement is becoming a research hotspot, which uses a camera to capture the static single frame image or dynamic sequence images of the target [3,4].…”