Search results for " Vision"

Complex objects classified by morphological shape analysis and elliptical Fourier descriptors

2005

This chapter deals with the classification of complex objects by morphological shape analysis and elliptical Fourier descriptors. An unsupervised method has been proposed to identify components with specific shapes by a simple edge detector and to classify them via the description of their contours. A particular application has been arranged in order to evaluate the goodness of this approach when discriminating between normal and pathological human megakaryocytes. Alterations in these cells can occur in many pathological processes and in such cases the pattern, size and shape of the cytoplasm and/or of the nucleus are extremely varied.

Variable fractional Fourier processor: a simple implementation: erratum

1997

Une nouvelle approche de classification de personnes à partir d'une plate-forme multi-kinect

2015

International audience; Dans ce papier nous présentons un descripteur 3D original pour la classification de personnes. Nous avons réalisé une plate-forme multi-kinect qui fait l'acquisition de nuages de points complets (c'est à dire selon une vue à 360°). Un post-traitement (suppression d'arrière-plan) isole les éléments qui sont candidats à représenter une personne. Notre descripteur exploite ces données et permet, au travers d'un classifieur SVM (Support Vector Machine), de classifier les personnes et de déterminer l'orientation du plan frontal de la personne. Il utilise la répartition spatiale et l'orientation des normales aux surfaces dans un procédé dérivé de celui des HOG (Histogram o…

Model selection using limiting distributions of second-order blind source separation algorithms

2015

Signals, recorded over time, are often observed as mixtures of multiple source signals. To extract relevant information from such measurements one needs to determine the mixing coefficients. In case of weakly stationary time series with uncorrelated source signals, this separation can be achieved by jointly diagonalizing sample autocovariances at different lags, and several algorithms address this task. Often the mixing estimates contain close-to-zero entries and one wants to decide whether the corresponding source signals have a relevant impact on the observations or not. To address this question of model selection we consider the recently published second-order blind identification proced…

Gear classification and fault detection using a diffusion map framework

2015

This article proposes a system health monitoring approach that detects abnormal behavior of machines. Diffusion map is used to reduce the dimensionality of training data, which facilitates the classification of newly arriving measurements. The new measurements are handled with Nyström extension. The method is trained and tested with real gear monitoring data from several windmill parks. A machine health index is proposed, showing that data recordings can be classified as working or failing using dimensionality reduction and warning levels in the low dimensional space. The proposed approach can be used with any system that produces high-dimensional measurement data. peerReviewed

Visual-manual in-car tasks decomposed: text entry and kinetic scrolling as the main sources of visual distraction

2013

Distraction effects of in-car tasks with a touch screen based navigation system user interface were studied in a driving simulator experiment with eye tracking. The focus was to examine which particular in-car task components visually distract drivers the most. The results indicate that all of the visual-manual in-car tasks led to increased levels of experienced demands and to lower driving speeds. The most significant finding was that text entry and kinetic scrolling of lists were the main sources of visual distraction whereas simple selection tasks with familiar target locations led to least severe distraction effects.

Designing browsing for in-car music player

2012

User interface features of a touch based mobile music player and their comparative impact on driver distraction when searching music albums were investigated. In a driving simulator experiment (N=18) three scrolling methods buttons, swipe and kinetic were compared, whereat the number of music tracks presented in a list-style format varied between three, five and seven items per page. Half of the participants used the music player in a portrait mode and half of them in a landscape mode. It was expected that swipe supports less severe distraction effects than kinetic or button due to systematic page-by-page scrolling and low levels of pointing accuracy required for browsing. Three items shoul…

Depth perception in tablet-based augmented reality at medium- and far-field distances

2013

Current augmented reality (AR) systems often fail to indicate the distance between the user and points of interest in the environment. Empirical evaluations of human depth perception in AR settings compared to real world settings are needed. Our goal in this study was to understand tablet-based AR depth perception by comparing it with real-world depth perception.

Using Video Conferencing and Video Recordings for Upper Secondary Distance Teaching: Teachers' View Points

2016

In Finland the “Isoverstas” (formely ISOverkosto) network of schools coordinates the development of upper secondary distance learning services. The community actually is quite extensive with 65 member schools. In this paper we introduce the results related using synchronous and asynchronous online video resources for distance teaching. The topic is approached broadly at the level of schools and different support services as well as the pedagogical practices of individual teachers. The research data consists of wiki stories written by teachers, the interviews of selected teachers, and an online survey. Data-based content analysis was chosen as the main analysis method with the aim of highlig…

Automatic dynamic texture segmentation using local descriptors and optical flow

2012

A dynamic texture (DT) is an extension of the texture to the temporal domain. How to segment a DT is a challenging problem. In this paper, we address the problem of segmenting a DT into disjoint regions. A DT might be different from its spatial mode (i.e., appearance) and/or temporal mode (i.e., motion field). To this end, we develop a framework based on the appearance and motion modes. For the appearance mode, we use a new local spatial texture descriptor to describe the spatial mode of the DT; for the motion mode, we use the optical flow and the local temporal texture descriptor to represent the temporal variations of the DT. In addition, for the optical flow, we use the histogram of orie…