2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids) 2015
DOI: 10.1109/humanoids.2015.7363515
|View full text |Cite
|
Sign up to set email alerts
|

Yet another gaze detector: An embodied calibration free system for the iCub robot

Abstract: Abstract-The recognition of gaze as for example mutual gaze plays an important role in social interaction. Previous research shows that already infants are capable of detecting mutual gaze. Such abilities are relevant for robots to learn from interaction, for example detecting when the robot is being addressed. Although various gaze tracking methods have been proposed, few seem to be openly available for robotic platforms such as iCub. In this paper we will describe a gaze tracking system for humanoid robots t… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
11
0

Year Published

2016
2016
2023
2023

Publication Types

Select...
6
2

Relationship

0
8

Authors

Journals

citations
Cited by 15 publications
(11 citation statements)
references
References 15 publications
0
11
0
Order By: Relevance
“…Figure 3) displayed on a screen in the kitchen area of the smart apartment. The agent is able to detect faces and estimate the current visual focus of attention of the human interaction partner [43] with the help of a web-cam installed on top of the screen.…”
Section: Methodsmentioning
confidence: 99%
“…Figure 3) displayed on a screen in the kitchen area of the smart apartment. The agent is able to detect faces and estimate the current visual focus of attention of the human interaction partner [43] with the help of a web-cam installed on top of the screen.…”
Section: Methodsmentioning
confidence: 99%
“…In the original RT-GENE work, this sub-dataset is used to train the GANs that "remove" the eyetracking glasses from the subject's face. [29] and Schillingmann and Nagai [40], rely on features extracted by SIFT and HOG with a subsequent classification stage. However, the accuracy of these methods is reduced for extreme head angles and under varying skin colour and illumination.…”
Section: Related Workmentioning
confidence: 99%
“…Joint blink and gaze estimation There have been several preliminary works to integrate gaze estimation and blink detection in unified frameworks. Schillingmann and Nagai [40] use HOG features for both pupil location estimation and blink detection. Similarly, Chen et al [7] employ a heuristic based on the shape of the iris area.…”
Section: Related Workmentioning
confidence: 99%
“…To assess the gaze direction of currently observable persons the gaze detector from Schillingmann et al [29] is used. The implementation was extended to be able to receive video data via ROS and publish its results, containing relative gaze directions and face landmarks [19] for all observed persons via RSB for further processing.…”
Section: Addressee Recognitionmentioning
confidence: 99%