Machine Vision-Based Analysis of Gaze and Visual Context

Basilio Noris
EPFL, 2011
EPFL thesis

Abstract

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 child's 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.

Official source

https://infoscience.epfl.ch/record/162431?ln=en

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Related concepts

Related publications

Basilio Noris
EPFL, 2011
EPFL thesis

Abstract

Official source

https://infoscience.epfl.ch/record/162431?ln=en

About this result

Related concepts (29)

Related concepts

Related publications (78)

Related publications

Related publications (78)

Social Network Analysis for Automatic Role Recognition

Sarah Favre

The computing community has shown a significant interest for the analysis of social interactions in the last decade. Different aspects of social interactions have been studied such as dominance, emotions, conflicts, etc. However, the recognition of roles has been neglected whereas these are a key aspect of social interactions. In fact, sociologists have shown not only that people play roles each time they interact, but also that roles shape behavior and expectations of interacting participants. The aim of this thesis is to fill this gap by investigating the problem of automatic role recognition in a wide range of interaction settings, including production environments, e.g. news and talk-shows, and spontaneous exchanges, e.g. meetings. The proposed role recognition approach includes two main steps. The first step aims at representing the individuals involved in an interaction with feature vectors accounting for their relationships with others. This step includes three main stages, namely segmentation of audio into turns (i.e. time intervals during which only one person talks), conversion of the sequence of turns into a social network, and use of the social network as a tool to extract features for each person. The second step uses machine learning methods to map the feature vectors into roles. The experiments have been carried out over roughly 90 hours of material. This is not only one of the largest databases ever used in literature on role recognition, but also the only one, to the best of our knowledge, including different interaction settings. In the experiments, the accuracy of the percentage of data correctly labeled in terms of roles is roughly 80% in production environments and 70% in spontaneous exchanges (lexical features have been added in the latter case). The importance of roles has been assessed in an application scenario as well. In particular, the thesis shows that roles help to segment talk-shows into stories, i.e. time intervals during which a single topic is discussed, with satisfactory performance. The main contributions of this thesis are as follows: To the best of our knowledge, this is the first work where social network analysis is applied to automatic analysis of conversation recordings. This thesis provides the first quantitative measure of how much roles constrain conversations, and a large corpus of recordings annotated in terms of roles. The results of this work have been published in one journal paper, and in five conference articles.

EPFL2011

Exploitation de connaissances sémantiques externes dans les représentations vectorielles en recherche documentaire

Florian Seydoux

The work presented in this thesis deals with several problems met in information retrieval (IR), task which one can summarise as identifying, in a collection of "documents", a subset of documents carrying a sought information, i.e.. relevant for a request expressed by a user. In the case of textual documents, to which we limited ourselves within the framework of this thesis, a significant part of the difficulty lies in ambiguity inherent to human languages. The interaction with the user is also approached in our work, by studying a tool enabling a natural language access to a database. Finally, some techniques which permit the visualisation of large collections of documents are also presented. In this document we first of all describe the principal models of IR by highlighting the relations which exist with some manual technics of IR and document retrieval, developed during the past centuries. We present the principle of document indexing, allowing us to represent documents in a multidimensional space, and the use of this representation by a vectorial model. After having reviewed the principal improvements made these last years with vectorial research systems, including the preprocessings of collections, the indexing mechanism and measurements of similarities between documents, we detail some recent usecases of additional semantic resources (semantic dictionaries, thesaurus, networks, ontologies) reported in scientific literature for the indexing task. We then present more in detail the semantic indexing principle of textual documents by using a thesaurus, consisting in integrating in the document's representation space at least part of the informational contents of hierarchical semantic resources. We propose a general framework allowing us to describe and position various possible techniques to carry out the semantic indexing by adapting, if possible, the specificity of the descriptions resulting from the semantic resources to the data to be represented. We use this framework to describe three families of criteria usable for semantic indexing, each one having its own characteristics. For each of these families, we give the specific algorithms allowing the computation of the criteria. The first two families allow us to consider several criteria already known in feature selection. Moreover we show that, unfortunately, many of these criteria are in fact not very effective for the considered task. The third family allows us to introduce a completely new criterion, the Minimum Redundancy Cut criterion (MRC), built on the basis of the information theory and allowing us to obtain index terms having a probability of occurrence in the collection of documents as well balanced as possible. Finally, we treat the case of semantic index independent of the data (statically choosen), allowing a parameterisation of the level of generality of the index terms. Some of the criteria suggested for semantic indexing has been empirically evaluated. To judge their relevance, we used a well known vectorial system (the Smart IR system) and measured the performances of IR obtained with various reference collections. Those collections was indexed on the basis of the studied criterion, by taking into account the strongly structuring semantic relation of hyper/hyponymy ("is-a" relation), given by two different semantic resources. By comparing results obtained with the performances of a traditional indexing (using the lemmas of the words as representation space), we can show on one hand the relevance of the semantic indexings (in RD) and on the other hand the quality of the proposed criterion (MRC). Concerning man-machine interaction, we present a general outline allowing to build in a relatively fast and systematic way systems with mixed initiative, giving the human user a large (and natural) latitude in the control of the dialogue. This outline is usable in typical database research-task applications (where the database is hidden to the user, but the latter knows exactly which information they wish to find) as well as advice-task applications, for which the users does not necessarily have a precise idea of their needs, and uses the system not only for specifing their wishes, but also a set of propositions as a final result. We particularly stress the techniques allowing us to obtain a robust system, able to deal with speech recognizer failures. Concerning the visualisation of large textual data collections, we present an application of the correspondences analysis (allowing to highlight similarities and oppositions for various groups of entity, built on the basis of additional features present in the DB) to the case of patents data. In addition, we propose a method (based on the bootstrap replication principle) allowing us to determine a confidence interval for relative positionings of various groups, thus permit to immediately judge the reliability of the visually apparent similarities or oppositions.

EPFL2006

Recent advances in data processing and communication systems have led to a continuous increase in the amount of data communicated over today’s networks. These large volumes of data pose new challenges on the current networking infrastructure that only offers a best effort mechanism for data delivery. The emergence of new distributed network architectures, such as peer-to-peer networks and wireless mesh networks, and the need for efficient data delivery mechanisms have motivated researchers to reconsider the way that information is communicated and processed in the networks. This has given rise to a new research field called network coding. The network coding paradigm departs from the traditional routing principle where information is simply relayed by the network nodes towards the destination, and introduces some intelligence in the network through coding at the intermediate nodes. This in-network data processing has been proved to substantially improve the performance of data delivery systems in terms of throughput and error resilience in networks with high path diversity. Motivated by the promising results in the network coding research, we focus in this thesis on the design of network coding algorithms for simultaneous transmission of multiple data sources in overlay networks. We investigate several problems that arise in the context of inter-session network coding, namely (i) decoding delay minimization in inter-session network coding, (ii) distributed rate allocation for inter-session network coding and (iii) correlation-aware decoding of incomplete network coded data. We start by proposing a novel framework for data delivery from multiple sources to multiple clients in an overlay wireline network, where intermediate nodes employ randomized inter-session network coding. We consider networks with high resource diversity, which creates network coding opportunities with possibly large gains in terms of throughput, delay and error robustness. However, the coding operations in the intermediate nodes must be carefully designed in order to enable efficient data delivery. We look at the problem from the decoding delay perspective and design solutions that lead to a small decoding delay at clients through proper coding and rate allocation. We cast the optimization problem as a rate allocation problem, which seeks for the coding operations that minimize the average decoding delay in the client population. We demonstrate the validity of our algorithm through simulations in representative network topologies. The results show that an effective combination of intra- and inter-session network coding based on randomized linear coding permits to reach small decoding delays and to better exploit the available network resources even in challenging network settings. Next, we design a distributed rate allocation algorithm where the users decide locally how many intra- and inter-session network coded packets should be requested from the parent nodes in order to get minimal decoding delay. The capability to take coding decisions locally with only a partial knowledge of the network statistics is of crucial importance for applications where users are organized in dynamic overlay networks. We propose a receiver-driven communication protocol that operates in two rounds. First, the users request and obtain information regarding the network conditions and packet availability in their local neighborhood. Then, every user independently optimizes the rate allocation among different possible intra- and inter-session packet combinations to be requested from its parents. We also introduce the novel concept of equivalent flows, which permits to efficiently estimate the expected number of packets that are necessary for decoding and hence to simplify the rate allocation process. Experimental results indicate that our algorithm is capable of eliminating the bottlenecks and reducing the decoding delay of users with limited resources. We further investigate the application of the proposed distributed rate allocation algorithm to the transmission of video sequences and validate the performance of our system using the NS-3 simulator. The simulation results show that the proposed rate allocation algorithm is successful in improving the quality of the delivered video compared to intra-session network coding based solutions. Finally, we investigate the problem of decoding the source information from an incomplete set of network coded data with the help of source priors in a finite algebraic field. The inability to form a complete decoding system can be often caused by transmission losses or timing constraints imposed by the application. In this case, exact reconstruction of the source data by conventional algorithms such as Gaussian elimination is not feasible; however, partial recovery of the source data may still be possible, which can be useful in applications where approximate reconstruction is informative. We use the statistical characteristics of the source data in order to perform approximate decoding. We first analyze the performance of a hypothetical maximum a posteriori decoder, which recovers the source data from an incomplete set of network coded data given the joint statistics of the sources. We derive an upper bound on the probability of erroneous source sequence decoding as a function of the system parameters. We then propose a constructive solution to the approximate decoding problem and design an iterative decoding algorithm based on message passing, which jointly considers the network coding and the correlation constraints. We illustrate the performance of our decoding algorithm through extensive simulations on synthetic and real data sets. The results demonstrate that, even by using a simple correlation model expressed as a correlation noise between pairs of sources, the original source data can be partially decoded in practice from an incomplete set of network coded symbols. Overall, this thesis addresses several important issues related to the design of efficient data delivery methods with inter-session network coding. Our novel framework for decoding delay minimization can impact the development of practical inter-session network coding algorithms that are appropriate for applications with low delay requirements. Our rate allocation algorithms are able to exploit the high resource diversity of modern networking systems and represent an effective alternative in the development of distributed communication systems. Finally, our algorithm for data recovery from incomplete network coded data using correlation priors can contribute significantly to the improvement of the delivered data quality and provide new insights towards the design of joint source and network coding algorithms.

EPFL2013