Estimating visual attention from a head mounted IMU

Leelasawassuk, Teesid; Damen, Dima; Mayol-Cuevas, Walterio

doi:10.1145/2802083.2808394

Cited by 19 publications

(19 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The literature of using eye and/or head gaze for attention estimation is vast and spans many years. Recently, standard methods to detect gaze directions commonly involve eye trackers [8] or determining head orientation [9], [10]. The information about both head orientation and eye gaze has been linked to a person's focus of attention in the past [11], [12].…”

Section: Behaviour Cues For Attention Estimationmentioning

confidence: 99%

I Can See Your Aim: Estimating User Attention from Gaze for Handheld Robot Collaboration

Stolzenwald

Mayol-Cuevas

2018

2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Self Cite

View full text Add to dashboard Cite

This paper explores the estimation of user attention in the setting of a cooperative handheld robot -a robot designed to behave as a handheld tool but that has levels of task knowledge. We use a tool-mounted gaze tracking system, which after modelling via a pilot study, we use as a proxy for estimating the attention of the user. This information is then used for cooperation with users in a task of selecting and engaging with objects on a dynamic screen. Via a video game setup, we test various degrees of robot autonomy from fully autonomous, where the robot knows what it has to do and acts, to no autonomy where the user is in full control of the task. Our results measure performance and subjective metrics and show how the attention model benefits the interaction and preference of users.

show abstract

Section: Behaviour Cues For Attention Estimationmentioning

confidence: 99%

I Can See Your Aim: Estimating User Attention from Gaze for Handheld Robot Collaboration

Stolzenwald

Mayol-Cuevas

2018

2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Self Cite

View full text Add to dashboard Cite

show abstract

“…the where the user is looking at we opt for GlaciAR to use a fixed image location. This is backed by recent work that has investigated gaze fixations and that shows that for egocentric perception, when the user is interacting with things in the world, the location of where the user is fixating is concentrated around a small region in the image [9,8]. To compute the centre of mass of egocentric gaze fixations on the Glass' front camera image, we attach an eye gaze tracker to Glass and calibrate the location of where gaze is into it.…”

Section: Attention Detection Using Glassmentioning

confidence: 99%

“…Note that the spatial attention region is only computed if the system is in the attending mode as per equation 1. GlaciAR's attention model is simple yet robust, requiring minimal computational burden and no image measurements. Extending the work of [8], in this paper we perform a more exhaustive evaluation on how useful this attention model is for automated capture of relevant information. Figure 4 presents the user's motion signals acquired from the Glass' IMU including the relative acceleration (red) and relative angular velocity (blue) as the user is making a cup of tea.…”

Section: Attention Detection Using Glassmentioning

confidence: 99%

“…One way in which we can evaluate its performance is via its ability to detect objects that the user has interacted with. To do this we follow the procedure used in [8] where we attach a wearable gaze tracker (ASL Mobileye) to Glass for it to serve as one source of groundtruth. For this evaluation, we used 8 volunteers that were asked to wear the bundled device.…”

Section: Experimental Evaluationmentioning

confidence: 99%

See 1 more Smart Citation

Automated capture and delivery of assistive task guidance with an eyewear computer

Leelasawassuk

Damen

Mayol-Cuevas

2017

Proceedings of the 8th Augmented Human International Conference

Self Cite

View full text Add to dashboard Cite

General rightsThis document is made available in accordance with publisher policies. Please cite only the published version using the reference above. ABSTRACTIn this paper we describe and evaluate an assistive mixed reality system that aims to augment users in tasks by combining automated and unsupervised information collection with minimally invasive video guides. The result is a fully self-contained system that we call GlaciAR (Glass-enabled Contextual Interactions for Augmented Reality). It operates by extracting contextual interactions from observing users performing actions. GlaciAR is able to i) automatically determine moments of relevance based on a head motion attention model, ii) automatically produce video guidance information, iii) trigger these guides based on an object detection method, iv) learn without supervision from observing multiple users and v) operate fully on-board a current eyewear computer (Google Glass). We describe the components of GlaciAR together with user evaluations on three tasks. We see this work as a first step toward scaling up the notoriously difficult authoring problem in guidance systems and an exploration of enhancing user natural abilities via minimally invasive visual cues.

show abstract

“…In [8], a regression model is built to estimate eye-gaze from head motion via an IMU in Google Glass. Damen et.al [2] discovered task-relevant objects by using eye fixations and linking gaze points to locations in the global scene.…”

Section: Introductionmentioning

confidence: 99%