Gaze guided object recognition using a head-mounted eye tracker

Abstract

Wearable eye trackers open up a large number of opportunities to cater for the information needs of users in today's dynamic society. Users no longer have to sit in front of a traditional desk-mounted eye tracker to benefit from the direct feedback given by the eye tracker about users' interest. Instead, eye tracking can be used as a ubiquitous interface in a real-world environment to provide users with supporting information that they need. This paper presents a novel application of intelligent interaction with the environment by combining eye tracking technology with real-time object recognition. In this context we present i) algorithms for guiding object recognition by using fixation points ii) algorithms for generating evidence of users' gaze on particular objects iii) building a next generation museum guide called Museum Guide 2.0 as a prototype application of gaze-based information provision in a real-world environment. We performed several experiments to evaluate our gazebased object recognition methods. Furthermore, we conducted a user study in the context of Museum Guide 2.0 to evaluate the usability of the new gaze-based interface for information provision. These results show that an enormous amount of potential exists for using a wearable eye tracker as a human-environment interface.

Eye center localization and gaze gesture recognition for human–computer interaction

“…Some algorithms designed for laboratory environments experience dramatic performance deterioration in real-world scenarios. Regarding commercial eye trackers, these take the form of wearable devices [7] and/or expensive hardware configurations [8].…”

Automatic analysis of eye-tracking data using object detection algorithms

“…Using an eye-tracker with a high-resolution camera will improve the detection results for objects which are further away from the eye-tracker. Investigation of alternative or additive object detection algorithms is also part of future work, as well as a thourough comparision of our technique with the recently published work of Toyama [19]. To tackle the problems concerning double keypoints, we plan to explore other keypoint matching techniques, such as visual words [17].…”

Eye Tracking for Personal Visual Analytics

“…Unfortunately, these analysis methods re- quire extensive manual processing and labeling; there are only few automatic computer vision techniques that detect and recognize trained objects from a database to generate AOIs [17]. In summary, today's analysis methods for mobile eye tracking are restricted to professional users and come with extensive work for the setup of the experiments and post-processing of the data recorded.…”