Zeynep Yucel’s research while affiliated with Centrum Wiskunde & Informatica and other places

This paper elaborates on mechanisms for establishing visual joint attention for the design of robotic agents that learn through natural interfaces, following a developmental trajectory not unlike infants. We describe first the evolution of cognitive skills in infants and then the adaptation of cognitive development patterns in robotic design. A comprehensive outlook for cognitively inspired robotic design schemes pertaining to joint attention is presented for the last decade, with particular emphasis on practical implementation issues. A novel cognitively inspired joint attention fixation mechanism is defined for robotic agents.

Modeling the user's attention is useful for responsive and interactive systems. This paper proposes a method for establishing joint visual attention between an experimenter and an intelligent agent. A rapid procedure is described to track the 3D head pose of the experimenter, which is used to approximate the gaze direction. The head is modeled with a sparse grid of points sampled from the surface of a cylinder. We then propose to employ a bottom-up saliency model to single out interesting objects in the neighborhood of the estimated focus of attention. We report results on a series of experiments, where a human experimenter looks at objects placed at different locations of the visual field, and the proposed algorithm is used to locate target objects automatically. Our results indicate that the proposed approach achieves high localization accuracy and thus constitutes a useful tool for the construction of natural human-computer interfaces.

We developed an inexpensive computer vision-based method utilizing an algorithm which differentiates drug-induced behavioral alterations. The mice were observed in an open-field arena and their activity was recorded for 100 min. For each animal the first 50 min of observation were regarded as the drug-free period. Each animal was exposed to only one drug and they were injected (i.p.) with either amphetamine or cocaine as the stimulant drugs or morphine or diazepam as the inhibitory agents. The software divided the arena into virtual grids and calculated the number of visits (sojourn counts) to the grids and instantaneous speeds within these grids by analyzing video data. These spatial distributions of sojourn counts and instantaneous speeds were used to construct feature vectors which were fed to the classifier algorithms for the final step of matching the animals and the drugs. The software decided which of the animals were drug-treated at a rate of 96%. The algorithm achieved 92% accuracy in sorting the data according to the increased or decreased activity and then determined which drug was delivered. The method differentiated the type of psychostimulant or inhibitory drugs with a success ratio of 70% and 80%, respectively. This method provides a new way to automatically evaluate and classify drug-induced behaviors in mice.

Head pose and eye location estimation are two closely related issues which refer to similar application areas. In recent years, these problems have been studied individually in numerous works in the literature. Previous research shows that cylindrical head models and isophote based schemes provide satisfactory precision in head pose and eye location estimation, respectively. However, the eye locator is not adequate to accurately locate eye in the presence of extreme head poses. Therefore, head pose cues may be suited to enhance the accuracy of eye localization in the presence of severe head poses. In this paper, a hybrid scheme is proposed in which the transformation matrix obtained from the head pose is used to normalize the eye regions and, in turn the transformation matrix generated by the found eye location is used to correct the pose estimation procedure. The scheme is designed to (1) enhance the accuracy of eye location estimations in low resolution videos, (2) to extend the operating range of the eye locator and (3) to improve the accuracy and re-initialization capabilities of the pose tracker. From the experimental results it can be derived that the proposed unified scheme improves the accuracy of eye estimations by 16% to 23%. Further, it considerably extends its operating range by more than 15deg, by overcoming the problems introduced by extreme head poses. Finally, the accuracy of the head pose tracker is improved by 12% to 24%.

The application of action recognition algorithms onto driving safety systems is still an open area of research. In terms of driving safety, identification of head movements present more significant information in comparison to other actions of the driver. Therefore, in this study, we developed a cylindrical model based head pose estimator to track drivers' head movements. The experiments indicate that the proposed scheme presents significant accuracy in estimation of head pose.

Symptoms of epilepsy, which is characterized by abnormal brain electrical activity, can be observed on electroencephalography (EEG) signal. This paper employs models of chaotic measures of EEG and aims to help detection of epilepsy seizures and diagnosis of epileptic indicators in seizure-free signals.