Basilio Noris

A wearable gaze tracking system for children in unconstrained environments

We present here a head-mounted gaze tracking system for the study of visual behavior in unconstrained environments. The system is designed both for adults and for infants as young as 1year of age. The system uses two CCD cameras to record a very wide field of view (96^ox96^o) that allows to study both central and peripheral vision. A small motor-driven mirror allows to obtain the direction of the wearers gaze with no need for active lighting and with little intrusiveness. The calibration of the system is done offline allowing experiments to be conducted with subjects who cannot cooperate in a calibration phase (e.g. very young children, animals). We use illumination normalization to increase the robustness of the system, and eye blinking detection to avoid tracking errors. We use Support Vector Regression to estimate a mapping between the appearance of the eyes and the corresponding gaze direction. The system can be used successfully indoors as well as outdoors and reaches an accuracy of 1.59^o with adults and 2.42^o with children.

Investigating Gaze of Children with ASD in Naturalistic Settings

Background Visual behavior is known to be atypical in Autism Spectrum Disorders (ASD). Monitor-based eye-tracking studies have measured several of these atypicalities in individuals with Autism. While atypical behaviors are known to be accentuated during natural interactions, few studies have been made on gaze behavior in natural interactions. In this study we focused on i) whether the findings done in laboratory settings are also visible in a naturalistic interaction; ii) whether new atypical elements appear when studying visual behavior across the whole field of view. Methodology/Principal Findings Ten children with ASD and ten typically developing children participated in a dyadic interaction with an experimenter administering items from the Early Social Communication Scale (ESCS). The children wore a novel head-mounted eye-tracker, measuring gaze direction and presence of faces across the childs field of view. The analysis of gaze episodes to faces revealed that children with ASD looked significantly less and for shorter lapses of time at the experimenter. The analysis of gaze patterns across the childs field of view revealed that children with ASD looked downwards and made more extensive use of their lateral field of view when exploring the environment. Conclusions/Significance The data gathered in naturalistic settings confirm findings previously obtained only in monitor-based studies. Moreover, the study allowed to observe a generalized strategy of lateral gaze in children with ASD when they were looking at the objects in their environment.

Social orienting of children with autism to facial expressions and speech: a study with a wearable eye-tracker in naturalistic settings.

This study investigates attention orienting to social stimuli in children with Autism Spectrum Conditions (ASC) during dyadic social interactions taking place in real-life settings. We study the effect of social cues that differ in complexity and distinguish between social cues produced by facial expressions of emotion and those produced during speech. We record the childrens gazes using a head-mounted eye-tracking device and report on a detailed and quantitative analysis of the motion of the gaze in response to the social cues. The study encompasses a group of children with ASC from 2 to 11-years old (n = 14) and a group of typically developing (TD) children (n = 17) between 3 and 6-years old. While the two groups orient overtly to facial expressions, children with ASC do so to a lesser extent. Children with ASC differ importantly from TD children in the way they respond to speech cues, displaying little overt shifting of attention to speaking faces. When children with ASC orient to facial expressions, they show reaction times and first fixation lengths similar to those presented by TD children. However, children with ASC orient to speaking faces slower than TD children. These results support the hypothesis that individuals affected by ASC have difficulties processing complex social sounds and detecting intermodal correspondence between facial and vocal information. It also corroborates evidence that people with ASC show reduced overt attention toward social stimuli.

Analysis of Head-Mounted Wireless Camera Videos for Early Diagnosis of Autism

In this paper we present a computer based approach to analysis of social interaction experiments for the diagnosis of autism spectrum disorders in young children of 6-18 months of age. We apply face detection on videos from a head-mounted wireless camera to measure the time a child spends looking at people. In-Plane rotation invariant Face Detection is used to detect faces from the diverse directions of the children’s head. Skin color detection is used to render the system more robust to cluttered environments and to the poor quality of the video recording.

Measuring gaze of children with autism spectrum disorders in naturalistic interactions

In this paper, we report on a study on gaze behavior by children with Autism Spectrum Disorder (ASD) during a dyadic interaction in a naturalistic environment. Twelve children with ASD were contrasted to twelve typically developing (TD) children, in a semi-structured interaction with a selection of items from the Early Social Communication Scale (ESCS). We used the WearCam, a novel head-mounted eye-tracker designed for children, to obtain gaze information across the broad field of view from the viewpoint of the child. Children with ASD looked downwards more often, and explored their lateral field of view more extensively compared to TD children. We discuss a number of hypotheses in support of these observations.

A Wearable Camera Detects Gaze Peculiarities during Social Interactions in Young Children with Pervasive Developmental Disorders

We report on the study of gazes, conducted on children with pervasive developmental disorders (PDD), by using a novel head-mounted eye-tracking device called the WearCam. Due to the portable nature of the WearCam, we are able to monitor naturalistic interactions between the children and adults. The study involved a group of 3- to 11-year-old children ( n=13) with PDD compared to a group of typically developing (TD) children ( n=13) between 2- and 6-years old. We found significant differences between the two groups, in terms of the proportion and the frequency of episodes of directly looking at faces during the whole set of experiments. We also conducted a differentiated analysis, in two social conditions, of the gaze patterns directed to an adults face when the adult addressed the child either verbally or through facial expression of emotion. We observe that children with PDD show a marked tendency to look more at the face of the adult when she makes facial expressions rather than when she speaks.

Aseba-Challenge: An Open-Source Multiplayer Introduction to Mobile Robots Programming

We present in this paper a realistic looking robotic survival challenge simulation. Using a model of the e-puck, an open-source mobile robot designed for educational purposes, our simulation allows several players to program the behaviour of e-pucks competing for food. The simulation was tested and well accepted by a hundred children between 7 and 16 years of age. We think that this type of simulations holds a great pedagogical potential because of their inherent fun.

Machine Vision-Based Analysis of Gaze and Visual Context

Visual behavior, and specifically gaze directed at objects and people, is a fundamental cue for understanding how children with Autism Spectrum Disorder (ASD) experience and respond to social interaction. Indeed atypical behaviors such as averting the gaze from faces, looking out of the corner of the eyes, and having difficulties disengaging from non-social stimuli, are well known symptoms of this developmental disorder. However, studying these atypicalities presents several technical challenges, both at a hardware and software level. Traditionally this type of analysis is done by viewing video recordings of the childs interaction and manually rating gaze behavior episodes. This data collection procedure is often a time consuming process, and all the results have to be checked by multiple raters to ensure reliability. When automated systems are used, issues of intrusiveness, robustness and reliability have to be taken into consideration, and their impact on the behavior of the child needs to be accounted for. Moreover, children often do not cooperate to the same extent as an adult participant in the experimental process. This thesis addresses the problem of studying the visual behavior of children during dyadic interactions, using tools from machine learning and computer vision. One focus is on the technical aspects of how to measure the direction of the gaze, and how to recognize what the child is looking at. Another is on the development of semi-automated data analysis collection methods that can be efficiently checked and corrected by the experimenter. The concrete contribution of this work is a set of algorithms and software tools that allow firstly the measurement of multiple gaze factors and the quantification of attentional episodes to objects and people, and secondly the analysis of their distributions, extrema, and spatio-temporal correlations. These tools are applied to the specific case of children affected by ASD, which allows the assessment of how their gaze strategies differ from typically developing children. To measure the direction of the gaze of children in a robust and unobtrusive way, the main recording tool employed is the WearCam: a head-mounted camera developed in our laboratory, that records the eyes of the child and an image of the broad field of view. The reflected images of the eyes are mapped to the coordinates of the gaze in the field of view by means of data-driven appearance-based methods. This is a different approach to the standard methods for gaze tracking, as it makes no use of active lighting, and allows the gathering of data to be postponed until after the recording. This is especially useful as it relieves the children from actively participating in a calibration phase. The task of identifying at which object or person the child is looking is approached through a semi-automated analysis of the recordings. A computationally intensive face and object detection system provides a preliminary estimation, while a faster on-line method can be used by the experimenter to correct that estimation by providing active cues. Furthermore, to allow faster processing of the recordings, a set of features specific to the relevant objects is extracted. The combination of these approaches greatly reduces the time needed to collect the data, while ensuring that reliable data is obtained. The development of these tools facilitates the studying of the behavior of children during natural interactions with an adult. Our approach is able to obtain information on several gaze factors, such as the frequency and length of fixations to faces, how extensively the gaze explores the broad field of view and the use of central vs. peripheral vision. The experimental observations obtained from the comparison of 29 children with autism to 29 typically developing children provide, in two separate studies, quantitative measurements in support of known deficits, such as reduced gaze to faces, downcast gaze and shorter fixations to social stimuli; deficits that were so far documented only in a qualitative manner. More importantly, the results highlight a novel hypothesis, not yet documented, suggesting that ASD children may use a strategy of continuous peripheral viewing to overcome their visual processing difficulties. These observations thus provide an experimental contribution to clinical research in autism.