Marco Porta

Artificial vision in road vehicles

The last few decades have witnessed the birth and growth of a new sensibility to transportation efficiency. In particular the need for efficient and improved people and goods mobility has pushed researchers to address the problem of intelligent transportation systems. This paper surveys the most advanced approaches to (partial) customization of the road following task, using on-board systems based on artificial vision. The functionalities of lane detection, obstacle detection and pedestrian detection are described and classified, and their possible application in future road vehicles is discussed.

Perspectives and challenges in e-learning: towards natural interaction paradigms

Abstract The role of Information and Communication Technologies (ICTs) in educational development has been world-wide recognized as a priority in order “to reinforce academic development, to widen access, to attain universal scope and to extend knowledge, as well as to facilitate education throughout life” (Council of Ministers of Education, Canada, Report of the Canadian Delegation to the UNESCO World Conference on Higher Education, Paris, October 5–9, 1998. http://www.cmec.ca/international/unesco WCHE98report.en.pdf ). As a consequence, developments in ICTs have had a significant impact on conventional higher education, as the university of the 21st century takes shape. By analyzing traditional learning models as opposed to new e-learning paradigms, this paper provides a global overview on future learning systems, from both technology- and user-centered perspectives. In particular, the visual component of the e-learning experience is emphasized as a significant feature for effective content development and delivery, while the adoption of new interaction paradigms based on multi-dimensional metaphors and perceptive interfaces is presented as a promising direction towards more natural and effective learning experiences.

Vision-based user interfaces: methods and applications

Abstract Within the class of perceptive user interfaces (i.e. interfaces providing the computer with perceptive capabilities), artificial vision is being exploited more and more as a new input modality, in addition to or in replacement of standard interaction paradigms. The aim of this paper is to provide a global view on the field of vision-based interfaces (VBIs), through the analysis of the methods used for their implementation and the exploration of the practical systems in which they have been employed. The focus will mostly be on techniques and prototypes intended for office and home PC-based use, as we are mainly interested in vision technology applied to ordinary computing environments. After a brief introduction to basic concepts about interfaces and image processing, the attention will be shifted to the four main areas in which VBIs find their maximum expression, namely head tracking, face/facial expression recognition, eye tracking and gesture recognition.

Vanishing point detection: representation analysis and new approaches

We introduce two different representation approaches and propose two techniques to estimate the position of vanishing points in an image, one bused on a probabilistic strategy and the other focused on a deterministic analysis. Unlike most of the methods so far developed, which exploit the Gaussian sphere, the new techniques operate in the (/spl rho/, /spl theta/) polar parameter space and in the (x, y) image plane coordinate space. Both the solutions are described and compared, through the discussion of the results obtained from their application to real images.

The Cognitive Effectiveness of Subtitle Processing

In an experimental study, we analyzed the cognitive processing of a subtitled film excerpt by adopting a methodological approach based on the integration of a variety of measures: eye-movement data, word recognition, and visual scene recognition. We tested the hypothesis that the processing of subtitled films is cognitively effective: It leads to a good understanding of film content without requiring a significant tradeoff between image processing and text processing. Following indications in the psycholinguistic literature, we also tested the hypothesis that two-line subtitles whose segmentation is syntactically incoherent can have a disruptive effect on information processing and recognition performance. The results highlighted the effectiveness of subtitle processing: Regardless of the quality of line segmentation, participants had a good understanding of the film content, they achieved good levels of performance in both word and scene recognition, and no tradeoff between text and image processing was detected. Eye-movement analyses enabled a further characterization of cognitive processing during subtitled film viewing. This article discusses the theoretical implications of the findings for both subtitling and multiple-source communication and highlights their methodological and applied implications.

GANT: Gaze analysis technique for human identification

Abstract Anatomical biometric recognition is widely used in a large number of civilian and government applications, within well-tested biometric parameters. New sensors and matching algorithms have led to the deployment of soft biometrics, which may provide a fast and reliable identity finding procedure. These traits are physical or behavioral human characteristics like skin color, eye color, and gait, used by humans to recognize their peers, presenting distinctiveness and permanence to identify an individual uniquely and reliably. This paper regards a novel Gaze ANalysis Technique, namely GANT, exploiting a graph-based representation of fixation points obtained by an eye tracker during human computer interaction. The main goal is to demonstrate the conjecture that the way an individual looks at an image might be a personal distinctive feature, i.e. a soft biometric application. A novel dataset acquired through the Tobii 1750 remote eye tracker has been used to demonstrate GANT accuracy in soft biometry, in terms of Receiver Operating Characteristic Curve (ROC), Equal Error Rate (EER) and Cumulative Match Curve (CMC).

Emotional e-learning through eye tracking

Besides proposing a short survey of eye tracking studies directly or indirectly connected with e-learning technology, in this paper we describe our ongoing research primarily directed to the development of an e-learning platform where eye data are exploited to obtain information about the students “emotional state”. The results of the preliminary tests presented here will be the starting point for more sophisticated experiments we are going to carry out.

Browsing large collections of images through unconventional visualization techniques

In this paper we describe some alternative methods intended for rapid and effective browsing of large collections of images. Specifically, we address the user who, not having a clear idea about what to search, needs to explore the entire image database to identify what he or she likes. The purpose of our approaches is to find techniques characterized by good trade-offs between browsing time and quality of the exploration.

An evolutionary approach to visual sensing for vehicle navigation

This paper presents an evolutionary approach able to process a digital image and detect tracks left by preceding vehicles on ice and snow in Antarctica. Biologically inspired by a colony of ants able to interact and cooperate to determine the shortest path to the food, this approach is based on autonomous agents moving along the image pixels and iteratively improving an initial coarse solution. The unfriendly Antarctic environment makes this image analysis problem extremely challenging, since light reflections, abruptly varying brightness conditions, and different terrain slopes must be considered as well. The ant-based approach is compared to a more traditional Hough-based solution and the results are discussed.

e5Learning, an E-Learning Environment Based on Eye Tracking

Userspsila eyes can be a meaningful source of information for e-learning systems. What we look at, and the way we do that, can in fact be exploited to improve the learning process, disclosing information which would otherwise remain concealed. In this paper we describe an e-learning environment where eye tracking is used to observe user behavior, in order to adapt content presentation in real-time. To achieve such purpose, we consider both the way learning activities are carried out and those eye signals that can be related to the userpsilas ldquoemotional statesrdquo.